{
  "session_id": "20260517_051957_59ec45",
  "model": "deepseek-v4-pro",
  "base_url": "https://api.deepseek.com",
  "platform": "curator",
  "session_start": "2026-05-17T05:19:57.623131",
  "last_updated": "2026-05-17T05:21:48.663616",
  "system_prompt": "You are Hermes Agent, an intelligent AI assistant created by Nous Research. You are helpful, knowledgeable, and direct. You assist users with a wide range of tasks including answering questions, writing and editing code, analyzing information, creative work, and executing actions via your tools. You communicate clearly, admit uncertainty when appropriate, and prioritize being genuinely useful over being verbose unless otherwise directed below. Be targeted and efficient in your exploration and investigations.\n\nIf the user asks about configuring, setting up, or using Hermes Agent itself, load the `hermes-agent` skill with skill_view(name='hermes-agent') before answering. Docs: https://hermes-agent.nousresearch.com/docs\n\nYou have persistent memory across sessions. Save durable facts using the memory tool: user preferences, environment details, tool quirks, and stable conventions. Memory is injected into every turn, so keep it compact and focused on facts that will still matter later.\nPrioritize what reduces future user steering — the most valuable memory is one that prevents the user from having to correct or remind you again. User preferences and recurring corrections matter more than procedural task details.\nDo NOT save task progress, session outcomes, completed-work logs, or temporary TODO state to memory; use session_search to recall those from past transcripts. Specifically: do not record PR numbers, issue numbers, commit SHAs, 'fixed bug X', 'submitted PR Y', 'Phase N done', file counts, or any artifact that will be stale in 7 days. If a fact will be stale in a week, it does not belong in memory. If you've discovered a new way to do something, solved a problem that could be necessary later, save it as a skill with the skill tool.\nWrite memories as declarative facts, not instructions to yourself. 'User prefers concise responses' ✓ — 'Always respond concisely' ✗. 'Project uses pytest with xdist' ✓ — 'Run tests with pytest -n 4' ✗. Imperative phrasing gets re-read as a directive in later sessions and can cause repeated work or override the user's current request. Procedures and workflows belong in skills, not memory. When the user references something from a past conversation or you suspect relevant cross-session context exists, use session_search to recall it before asking them to repeat themselves. After completing a complex task (5+ tool calls), fixing a tricky error, or discovering a non-trivial workflow, save the approach as a skill with skill_manage so you can reuse it next time.\nWhen using a skill and finding it outdated, incomplete, or wrong, patch it immediately with skill_manage(action='patch') — don't wait to be asked. Skills that aren't maintained become liabilities.\n\n## Skills (mandatory)\nBefore replying, scan the skills below. If a skill matches or is even partially relevant to your task, you MUST load it with skill_view(name) and follow its instructions. Err on the side of loading — it is always better to have context you don't need than to miss critical steps, pitfalls, or established workflows. Skills contain specialized knowledge — API endpoints, tool-specific commands, and proven workflows that outperform general-purpose approaches. Load the skill even if you think you could handle the task with basic tools like web_search or terminal. Skills also encode the user's preferred approach, conventions, and quality standards for tasks like code review, planning, and testing — load them even for tasks you already know how to do, because the skill defines how it should be done here.\nWhenever the user asks you to configure, set up, install, enable, disable, modify, or troubleshoot Hermes Agent itself — its CLI, config, models, providers, tools, skills, voice, gateway, plugins, or any feature — load the `hermes-agent` skill first. It has the actual commands (e.g. `hermes config set …`, `hermes tools`, `hermes setup`) so you don't have to guess or invent workarounds.\nIf a skill has issues, fix it with skill_manage(action='patch').\nAfter difficult/iterative tasks, offer to save as a skill. If a skill you loaded was missing steps, had wrong commands, or needed pitfalls you discovered, update it before finishing.\n\n<available_skills>\n  autonomous-ai-agents: Skills for spawning and orchestrating autonomous AI coding agents and multi-agent workflows — running independent agent processes, delegating tasks, and coordinating parallel workstreams.\n    - claude-code: Delegate coding to Claude Code CLI (features, PRs).\n    - codex: Delegate coding to OpenAI Codex CLI (features, PRs).\n    - hermes-agent: Complete guide to using and extending Hermes Agent — CLI ...\n    - opencode: Delegate coding to OpenCode CLI (features, PR review).\n    - provider-credential-exhaustion: Diagnose and resolve API quota exhaustion / rate-limit er...\n  booking-scraper:\n    - booking-scraper: Search Booking.com for hotel availability using Camoufox ...\n  bybit:\n    - bybit: Check Bybit account — wallet balance, open positions, ord...\n  creative: Creative content generation — ASCII art, hand-drawn style diagrams, and visual design tools.\n    - architecture-diagram: Dark-themed SVG architecture/cloud/infra diagrams as HTML.\n    - ascii-art: ASCII art: pyfiglet, cowsay, boxes, image-to-ascii.\n    - ascii-video: ASCII video: convert video/audio to colored ASCII MP4/GIF.\n    - baoyu-comic: Knowledge comics (知识漫画): educational, biography, tutorial.\n    - baoyu-infographic: Infographics: 21 layouts x 21 styles (信息图, 可视化).\n    - claude-design: Design one-off HTML artifacts (landing, deck, prototype).\n    - comfyui: Generate images, video, and audio with ComfyUI — install,...\n    - design-md: Author/validate/export Google's DESIGN.md token spec files.\n    - excalidraw: Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).\n    - humanizer: Humanize text: strip AI-isms and add real voice.\n    - ideation: Generate project ideas via creative constraints.\n    - manim-video: Manim CE animations: 3Blue1Brown math/algo videos.\n    - p5js: p5.js sketches: gen art, shaders, interactive, 3D.\n    - pixel-art: Pixel art w/ era palettes (NES, Game Boy, PICO-8).\n    - popular-web-designs: 54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.\n    - pretext: Use when building creative browser demos with @chenglou/p...\n    - sketch: Throwaway HTML mockups: 2-3 design variants to compare.\n    - songwriting-and-ai-music: Songwriting craft and Suno AI music prompts.\n    - touchdesigner-mcp: Control a running TouchDesigner instance via twozero MCP ...\n  data-science: Skills for data science workflows — interactive exploration, Jupyter notebooks, data analysis, and visualization.\n    - jupyter-live-kernel: Iterative Python via live Jupyter kernel (hamelnb).\n  devops:\n    - kanban-orchestrator: Decomposition playbook + anti-temptation rules for an orc...\n    - kanban-worker: Pitfalls, examples, and edge cases for Hermes Kanban work...\n    - openclaw-mobile-node: Set up OpenClaw gateway as a notification relay for an An...\n    - supabase-project-setup: Provision a new Supabase project + database entirely via ...\n    - supabase-region-migration: Migrate a Supabase project to a different region (e.g. us...\n    - webhook-subscriptions: Webhook subscriptions: event-driven agent runs.\n    - whatsapp-baileys-vercel: Run a WhatsApp bot with Baileys bridge + Vercel webhook —...\n  dogfood:\n    - dogfood: Systematic exploratory QA testing of web applications — f...\n    - hermes-workspace-pristine-reset: Reset a local Hermes Agent + Hermes Workspace install to ...\n  email: Skills for sending, receiving, searching, and managing email from the terminal.\n    - himalaya: Himalaya CLI: IMAP/SMTP email from terminal.\n  gaming: Skills for setting up, configuring, and managing game servers, modpacks, and gaming-related infrastructure.\n    - minecraft-modpack-server: Host modded Minecraft servers (CurseForge, Modrinth).\n    - pokemon-player: Play Pokemon via headless emulator + RAM reads.\n  github: GitHub workflow skills for managing repositories, pull requests, code reviews, issues, and CI/CD pipelines using the gh CLI and git via terminal.\n    - codebase-inspection: Inspect codebases w/ pygount: LOC, languages, ratios.\n    - github-auth: GitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.\n    - github-code-review: Review PRs: diffs, inline comments via gh or REST.\n    - github-issues: Create, triage, label, assign GitHub issues via gh or REST.\n    - github-pr-workflow: GitHub PR lifecycle: branch, commit, open, CI, merge.\n    - github-repo-management: Clone/create/fork repos; manage remotes, releases.\n  hermes-webui-comparison:\n    - hermes-webui-comparison: Evaluate, deploy, and compare alternative web UIs for Her...\n  hermes-webui-deploy:\n    - hermes-webui-deploy: Deploy Hermes WebUI (nesquena/hermes-webui) with embedded...\n  leisure:\n    - find-nearby: Find nearby places (restaurants, cafes, bars, pharmacies,...\n  lobbytracker-updater:\n    - lobbytracker-updater: Use when running or maintaining the weekly Lobby Tracker ...\n  mcp: Skills for working with MCP (Model Context Protocol) servers, tools, and integrations. Includes the built-in native MCP client (configure servers in config.yaml for automatic tool discovery) and the mcporter CLI bridge for ad-hoc server interaction.\n    - mcporter: Use the mcporter CLI to list, configure, auth, and call M...\n    - native-mcp: MCP client: connect servers, register tools (stdio/HTTP).\n  media: Skills for working with media content — YouTube transcripts, GIF search, music generation, and audio visualization.\n    - gif-search: Search/download GIFs from Tenor via curl + jq.\n    - heartmula: HeartMuLa: Suno-like song generation from lyrics + tags.\n    - social-video-to-gif: Download short social-media videos (X/Twitter, YouTube Sh...\n    - songsee: Audio spectrograms/features (mel, chroma, MFCC) via CLI.\n    - spotify: Spotify: play, search, queue, manage playlists and devices.\n    - youtube-content: YouTube transcripts to summaries, threads, blogs.\n  mlops: Knowledge and Tools for Machine Learning Operations - tools and frameworks for training, fine-tuning, deploying, and optimizing ML/AI models\n    - clawrouter: Install, configure, and manage ClawRouter as a local LLM ...\n    - huggingface-hub: HuggingFace hf CLI: search/download/upload models, datasets.\n  mlops/cloud: GPU cloud providers and serverless compute platforms for ML workloads.\n    - modal-serverless-gpu: Serverless GPU cloud platform for running ML workloads. U...\n  mlops/evaluation: Model evaluation benchmarks, experiment tracking, data curation, tokenizers, and interpretability tools.\n    - evaluating-llms-harness: lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).\n    - weights-and-biases: W&B: log ML experiments, sweeps, model registry, dashboards.\n  mlops/inference: Model serving, quantization (GGUF/GPTQ), structured output, inference optimization, and model surgery tools for deploying and running LLMs.\n    - gguf-quantization: GGUF format and llama.cpp quantization for efficient CPU/...\n    - guidance: Control LLM output with regex and grammars, guarantee val...\n    - llama-cpp: llama.cpp local GGUF inference + HF Hub model discovery.\n    - obliteratus: OBLITERATUS: abliterate LLM refusals (diff-in-means).\n    - outlines: Outlines: structured JSON/regex/Pydantic LLM generation.\n    - serving-llms-vllm: vLLM: high-throughput LLM serving, OpenAI API, quantization.\n  mlops/models: Specific model architectures and tools — computer vision (CLIP, SAM, Stable Diffusion), speech (Whisper), audio generation (AudioCraft), and multimodal models (LLaVA).\n    - audiocraft-audio-generation: AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.\n    - clip: OpenAI's model connecting vision and language. Enables ze...\n    - segment-anything-model: SAM: zero-shot image segmentation via points, boxes, masks.\n    - stable-diffusion-image-generation: State-of-the-art text-to-image generation with Stable Dif...\n    - whisper: OpenAI's general-purpose speech recognition model. Suppor...\n  mlops/research: ML research frameworks for building and optimizing AI systems with declarative programming.\n    - dspy: DSPy: declarative LM programs, auto-optimize prompts, RAG.\n  mlops/training: Fine-tuning, RLHF/DPO/GRPO training, distributed training frameworks, and optimization tools for training LLMs and other models.\n    - axolotl: Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).\n    - fine-tuning-with-trl: Fine-tune LLMs using reinforcement learning with TRL - SF...\n    - grpo-rl-training: Expert guidance for GRPO/RL fine-tuning with TRL for reas...\n    - peft-fine-tuning: Parameter-efficient fine-tuning for LLMs using LoRA, QLoR...\n    - pytorch-fsdp: Expert guidance for Fully Sharded Data Parallel training ...\n    - unsloth: Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.\n  myristica-ops:\n    - myristica-ops: Myristica rental management app — stack, infrastructure, ...\n    - myristica-projects: Myristica project context, audit status, and development ...\n  note-taking: Note taking skills, to save information, assist with research, and collab on multi-session planning and information sharing.\n    - obsidian: Read, search, create, and edit notes in the Obsidian vault.\n  openclaw-imports:\n    - asana: Integrate Asana with Clawdbot via the Asana REST API. Use...\n    - bitwarden: Set up and use Bitwarden CLI (bw). Use when installing th...\n    - gog: Read-only Google Workspace CLI for Gmail, Calendar, Drive...\n    - google-photos: Manage Google Photos library. Upload photos, create album...\n    - hevy: Query workout data from Hevy including workouts, routines...\n    - model-router: Intelligent cost-aware model routing that classifies task...\n    - notion: Notion API for creating and managing pages, databases, an...\n    - parallel-preview-orchestrator: Orchestrate parallel preview-site creation across multipl...\n    - session-logs: Search and analyze your own session logs (older/parent co...\n    - summarize: Summarize URLs or files with the summarize CLI (web, PDFs...\n    - weather: Get current weather and forecasts (no API key required).\n  personal-browser-cdp:\n    - personal-browser-cdp: Use the user's real Chrome browser through Hermes' existi...\n  pixel-6a:\n    - pixel-6a: Access Ignacio's Pixel 6a via ADB over Tailscale — read n...\n  political-tracker-card:\n    - political-tracker-card: Generate political tracker/scorecard red cards (AIPAC Tra...\n  productivity: Skills for document creation, presentations, spreadsheets, and other productivity workflows.\n    - airtable: Airtable REST API via curl. Records CRUD, filters, upserts.\n    - google-workspace: Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.\n    - home-improvement-planning: Plan home-improvement / DIY installations end-to-end: mea...\n    - linear: Linear: manage issues, projects, teams via GraphQL + curl.\n    - maps: Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.\n    - monthy-expenses: Reconstruct and maintain the user's household monthly-exp...\n    - nano-pdf: Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).\n    - notion: Notion API via curl: pages, databases, blocks, search.\n    - ocr-and-documents: Extract text from PDFs/scans (pymupdf, marker-pdf).\n    - powerpoint: Create, read, edit .pptx decks, slides, notes, templates.\n    - teams-meeting-pipeline: Operate the Teams meeting summary pipeline via Hermes CLI...\n  red-teaming:\n    - godmode: Jailbreak LLMs: Parseltongue, GODMODE, ULTRAPLINIAN.\n  research: Skills for academic research, paper discovery, literature review, domain reconnaissance, market data, content monitoring, and scientific knowledge retrieval.\n    - arxiv: Search arXiv papers by keyword, author, category, or ID.\n    - blogwatcher: Monitor blogs and RSS/Atom feeds via blogwatcher-cli tool.\n    - llm-wiki: Karpathy's LLM Wiki: build/query interlinked markdown KB.\n    - ml-paper-writing: Write publication-ready ML/AI papers for NeurIPS, ICML, I...\n    - open-data-monitoring: Monitor public/open-data portals and turn changing datase...\n    - polymarket: Query Polymarket: markets, prices, orderbooks, history.\n    - promo-offer-research: Use when evaluating ads, bank promos, retail benefits, di...\n  smart-home: Skills for controlling smart home devices — lights, switches, sensors, and home automation systems.\n    - openhue: Control Philips Hue lights, scenes, rooms via OpenHue CLI.\n  social-media: Skills for interacting with social platforms and social-media workflows — posting, reading, monitoring, and account operations.\n    - xitter: Interact with X/Twitter via the x-cli terminal client usi...\n    - xurl: X/Twitter via xurl CLI: post, search, DM, media, v2 API.\n  software-development:\n    - code-review: Guidelines for performing thorough code reviews with secu...\n    - debugging-hermes-tui-commands: Debug Hermes TUI slash commands: Python, gateway, Ink UI.\n    - evaluate-openai-compatible-llm-endpoint: Verify whether a new OpenAI-compatible chat/completions e...\n    - hermes-agent-skill-authoring: Author in-repo SKILL.md: frontmatter, validator, structure.\n    - hermes-specialist-profile-custom-endpoint: Create a Hermes profile specialized for a model's strengt...\n    - node-inspect-debugger: Debug Node.js via --inspect + Chrome DevTools Protocol CLI.\n    - plan: Plan mode: write markdown plan to .hermes/plans/, no exec.\n    - python-debugpy: Debug Python: pdb REPL + debugpy remote (DAP).\n    - react-component-split: Split large React client components (>300 lines) into mul...\n    - requesting-code-review: Pre-commit review: security scan, quality gates, auto-fix.\n    - spike: Throwaway experiments to validate an idea before build.\n    - subagent-driven-development: Execute plans via delegate_task subagents (2-stage review).\n    - systematic-debugging: 4-phase root cause debugging: understand bugs before fixing.\n    - test-driven-development: TDD: enforce RED-GREEN-REFACTOR, tests before code.\n    - web-api-flow-capture: Reverse-engineer SPA/payment/checkout API flows by captur...\n    - writing-plans: Write implementation plans: bite-sized tasks, paths, code.\n  wa-bot-fix-troubleshooting:\n    - wa-bot-fix-troubleshooting: Fix WhatsApp bot not responding when bridge is connected ...\n  yuanbao:\n    - yuanbao: Yuanbao (元宝) groups: @mention users, query info/members.\n</available_skills>\n\nOnly proceed without loading a skill if genuinely none are relevant to the task.\n\nHost: Linux (6.17.0-1011-oracle)\nUser home directory: /home/ubuntu\nCurrent working directory: /home/ubuntu/.hermes/hermes-agent\n\nConversation started: Sunday, May 17, 2026 05:20 AM\nModel: deepseek-v4-pro\nProvider: deepseek",
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "browser_back",
        "description": "Navigate back to the previous page in browser history. Requires browser_navigate to be called first.",
        "parameters": {
          "type": "object",
          "properties": {}
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "browser_cdp",
        "description": "Send a raw Chrome DevTools Protocol (CDP) command. Escape hatch for browser operations not covered by browser_navigate, browser_click, browser_console, etc.\n\n**Requires a reachable CDP endpoint.** Available when the user has run '/browser connect' to attach to a running Chrome, or when 'browser.cdp_url' is set in config.yaml. Not currently wired up for cloud backends (Browserbase, Browser Use, Firecrawl) — those expose CDP per session but live-session routing is a follow-up. Camofox is REST-only and will never support CDP. If the tool is in your toolset at all, a CDP endpoint is already reachable.\n\n**CDP method reference:** https://chromedevtools.github.io/devtools-protocol/ — use web_extract on a method's URL (e.g. '/tot/Page/#method-handleJavaScriptDialog') to look up parameters and return shape.\n\n**Common patterns:**\n- List tabs: method='Target.getTargets', params={}\n- Handle a native JS dialog: method='Page.handleJavaScriptDialog', params={'accept': true, 'promptText': ''}, target_id=<tabId>\n- Get all cookies: method='Network.getAllCookies', params={}\n- Eval in a specific tab: method='Runtime.evaluate', params={'expression': '...', 'returnByValue': true}, target_id=<tabId>\n- Set viewport for a tab: method='Emulation.setDeviceMetricsOverride', params={'width': 1280, 'height': 720, 'deviceScaleFactor': 1, 'mobile': false}, target_id=<tabId>\n\n**Usage rules:**\n- Browser-level methods (Target.*, Browser.*, Storage.*): omit target_id and frame_id.\n- Page-level methods (Page.*, Runtime.*, DOM.*, Emulation.*, Network.* scoped to a tab): pass target_id from Target.getTargets.\n- **Cross-origin iframe scope** (Runtime.evaluate inside an OOPIF, Page.* targeting a frame target, etc.): pass frame_id from the browser_snapshot frame_tree output. This routes through the CDP supervisor's live connection — the only reliable way on Browserbase where stateless CDP calls hit signed-URL expiry.\n- Each stateless call (without frame_id) is independent — sessions and event subscriptions do not persist between calls. For stateful workflows, prefer the dedicated browser tools or use frame_id routing.",
        "parameters": {
          "type": "object",
          "properties": {
            "method": {
              "type": "string",
              "description": "CDP method name, e.g. 'Target.getTargets', 'Runtime.evaluate', 'Page.handleJavaScriptDialog'."
            },
            "params": {
              "type": "object",
              "description": "Method-specific parameters as a JSON object. Omit or pass {} for methods that take no parameters.",
              "properties": {},
              "additionalProperties": true
            },
            "target_id": {
              "type": "string",
              "description": "Optional. Target/tab ID from Target.getTargets result (each entry's 'targetId'). Use for page-level methods at the top-level tab scope. Mutually exclusive with frame_id."
            },
            "frame_id": {
              "type": "string",
              "description": "Optional. Out-of-process iframe (OOPIF) frame_id from browser_snapshot.frame_tree.children[] where is_oopif=true. When set, routes the call through the CDP supervisor's live session for that iframe. Essential for Runtime.evaluate inside cross-origin iframes, especially on Browserbase where fresh per-call CDP connections can't keep up with signed URL rotation. For same-origin iframes, use parent contentWindow/contentDocument from Runtime.evaluate at the top-level page instead."
            },
            "timeout": {
              "type": "number",
              "description": "Timeout in seconds (default 30, max 300).",
              "default": 30
            }
          },
          "required": [
            "method"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "browser_click",
        "description": "Click on an element identified by its ref ID from the snapshot (e.g., '@e5'). The ref IDs are shown in square brackets in the snapshot output. Requires browser_navigate and browser_snapshot to be called first.",
        "parameters": {
          "type": "object",
          "properties": {
            "ref": {
              "type": "string",
              "description": "The element reference from the snapshot (e.g., '@e5', '@e12')"
            }
          },
          "required": [
            "ref"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "browser_console",
        "description": "Get browser console output and JavaScript errors from the current page. Returns console.log/warn/error/info messages and uncaught JS exceptions. Use this to detect silent JavaScript errors, failed API calls, and application warnings. Requires browser_navigate to be called first. When 'expression' is provided, evaluates JavaScript in the page context and returns the result — use this for DOM inspection, reading page state, or extracting data programmatically.",
        "parameters": {
          "type": "object",
          "properties": {
            "clear": {
              "type": "boolean",
              "default": false,
              "description": "If true, clear the message buffers after reading"
            },
            "expression": {
              "type": "string",
              "description": "JavaScript expression to evaluate in the page context. Runs in the browser like DevTools console — full access to DOM, window, document. Return values are serialized to JSON. Example: 'document.title' or 'document.querySelectorAll(\"a\").length'"
            }
          }
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "browser_dialog",
        "description": "Respond to a native JavaScript dialog (alert / confirm / prompt / beforeunload) that is currently blocking the page.\n\n**Workflow:** call ``browser_snapshot`` first — if a dialog is open, it appears in the ``pending_dialogs`` field with ``id``, ``type``, and ``message``. Then call this tool with ``action='accept'`` or ``action='dismiss'``.\n\n**Prompt dialogs:** pass ``prompt_text`` to supply the response string. Ignored for alert/confirm/beforeunload.\n\n**Multiple dialogs:** if more than one dialog is queued (rare — happens when a second dialog fires while the first is still open), pass ``dialog_id`` from the snapshot to disambiguate.\n\n**Availability:** only present when a CDP-capable backend is attached — Browserbase sessions, local Chrome via ``/browser connect``, or ``browser.cdp_url`` in config.yaml. Not available on Camofox (REST-only) or the default Playwright local browser (CDP port is hidden).",
        "parameters": {
          "type": "object",
          "properties": {
            "action": {
              "type": "string",
              "enum": [
                "accept",
                "dismiss"
              ],
              "description": "'accept' clicks OK / returns the prompt text. 'dismiss' clicks Cancel / returns null from prompt(). For ``beforeunload`` dialogs: 'accept' allows the navigation, 'dismiss' keeps the page."
            },
            "prompt_text": {
              "type": "string",
              "description": "Response string for a ``prompt()`` dialog. Ignored for other dialog types. Defaults to empty string."
            },
            "dialog_id": {
              "type": "string",
              "description": "Specific dialog to respond to, from ``browser_snapshot.pending_dialogs[].id``. Required only when multiple dialogs are queued."
            }
          },
          "required": [
            "action"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "browser_get_images",
        "description": "Get a list of all images on the current page with their URLs and alt text. Useful for finding images to analyze with the vision tool. Requires browser_navigate to be called first.",
        "parameters": {
          "type": "object",
          "properties": {}
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "browser_navigate",
        "description": "Navigate to a URL in the browser. Initializes the session and loads the page. Must be called before other browser tools. For simple information retrieval, prefer web_search or web_extract (faster, cheaper). For plain-text endpoints — URLs ending in .md, .txt, .json, .yaml, .yml, .csv, .xml, raw.githubusercontent.com, or any documented API endpoint — prefer curl via the terminal tool or web_extract; the browser stack is overkill and much slower for these. Use browser tools when you need to interact with a page (click, fill forms, dynamic content). Returns a compact page snapshot with interactive elements and ref IDs — no need to call browser_snapshot separately after navigating.",
        "parameters": {
          "type": "object",
          "properties": {
            "url": {
              "type": "string",
              "description": "The URL to navigate to (e.g., 'https://example.com')"
            }
          },
          "required": [
            "url"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "browser_press",
        "description": "Press a keyboard key. Useful for submitting forms (Enter), navigating (Tab), or keyboard shortcuts. Requires browser_navigate to be called first.",
        "parameters": {
          "type": "object",
          "properties": {
            "key": {
              "type": "string",
              "description": "Key to press (e.g., 'Enter', 'Tab', 'Escape', 'ArrowDown')"
            }
          },
          "required": [
            "key"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "browser_scroll",
        "description": "Scroll the page in a direction. Use this to reveal more content that may be below or above the current viewport. Requires browser_navigate to be called first.",
        "parameters": {
          "type": "object",
          "properties": {
            "direction": {
              "type": "string",
              "enum": [
                "up",
                "down"
              ],
              "description": "Direction to scroll"
            }
          },
          "required": [
            "direction"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "browser_snapshot",
        "description": "Get a text-based snapshot of the current page's accessibility tree. Returns interactive elements with ref IDs (like @e1, @e2) for browser_click and browser_type. full=false (default): compact view with interactive elements. full=true: complete page content. Snapshots over 8000 chars are truncated or LLM-summarized. Requires browser_navigate first. Note: browser_navigate already returns a compact snapshot — use this to refresh after interactions that change the page, or with full=true for complete content.",
        "parameters": {
          "type": "object",
          "properties": {
            "full": {
              "type": "boolean",
              "description": "If true, returns complete page content. If false (default), returns compact view with interactive elements only.",
              "default": false
            }
          }
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "browser_type",
        "description": "Type text into an input field identified by its ref ID. Clears the field first, then types the new text. Requires browser_navigate and browser_snapshot to be called first.",
        "parameters": {
          "type": "object",
          "properties": {
            "ref": {
              "type": "string",
              "description": "The element reference from the snapshot (e.g., '@e3')"
            },
            "text": {
              "type": "string",
              "description": "The text to type into the field"
            }
          },
          "required": [
            "ref",
            "text"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "browser_vision",
        "description": "Take a screenshot of the current page and analyze it with vision AI. Use this when you need to visually understand what's on the page - especially useful for CAPTCHAs, visual verification challenges, complex layouts, or when the text snapshot doesn't capture important visual information. Returns both the AI analysis and a screenshot_path that you can share with the user by including MEDIA:<screenshot_path> in your response. Requires browser_navigate to be called first.",
        "parameters": {
          "type": "object",
          "properties": {
            "question": {
              "type": "string",
              "description": "What you want to know about the page visually. Be specific about what you're looking for."
            },
            "annotate": {
              "type": "boolean",
              "default": false,
              "description": "If true, overlay numbered [N] labels on interactive elements. Each [N] maps to ref @eN for subsequent browser commands. Useful for QA and spatial reasoning about page layout."
            }
          },
          "required": [
            "question"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "clarify",
        "description": "Ask the user a question when you need clarification, feedback, or a decision before proceeding. Supports two modes:\n\n1. **Multiple choice** — provide up to 4 choices. The user picks one or types their own answer via a 5th 'Other' option.\n2. **Open-ended** — omit choices entirely. The user types a free-form response.\n\nUse this tool when:\n- The task is ambiguous and you need the user to choose an approach\n- You want post-task feedback ('How did that work out?')\n- You want to offer to save a skill or update memory\n- A decision has meaningful trade-offs the user should weigh in on\n\nDo NOT use this tool for simple yes/no confirmation of dangerous commands (the terminal tool handles that). Prefer making a reasonable default choice yourself when the decision is low-stakes.",
        "parameters": {
          "type": "object",
          "properties": {
            "question": {
              "type": "string",
              "description": "The question to present to the user."
            },
            "choices": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "maxItems": 4,
              "description": "Up to 4 answer choices. Omit this parameter entirely to ask an open-ended question. When provided, the UI automatically appends an 'Other (type your answer)' option."
            }
          },
          "required": [
            "question"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "cronjob",
        "description": "Manage scheduled cron jobs with a single compressed tool.\n\nUse action='create' to schedule a new job from a prompt or one or more skills.\nUse action='list' to inspect jobs.\nUse action='update', 'pause', 'resume', 'remove', or 'run' to manage an existing job.\n\nTo stop a job the user no longer wants: first action='list' to find the job_id, then action='remove' with that job_id. Never guess job IDs — always list first.\n\nJobs run in a fresh session with no current-chat context, so prompts must be self-contained.\nIf skills are provided on create, the future cron run loads those skills in order, then follows the prompt as the task instruction.\nOn update, passing skills=[] clears attached skills.\n\nNOTE: The agent's final response is auto-delivered to the target. Put the primary\nuser-facing content in the final response. Cron jobs run autonomously with no user\npresent — they cannot ask questions or request clarification.\n\nImportant safety rule: cron-run sessions should not recursively schedule more cron jobs.",
        "parameters": {
          "type": "object",
          "properties": {
            "action": {
              "type": "string",
              "description": "One of: create, list, update, pause, resume, remove, run"
            },
            "job_id": {
              "type": "string",
              "description": "Required for update/pause/resume/remove/run"
            },
            "prompt": {
              "type": "string",
              "description": "For create: the full self-contained prompt. If skills are also provided, this becomes the task instruction paired with those skills."
            },
            "schedule": {
              "type": "string",
              "description": "For create/update: '30m', 'every 2h', '0 9 * * *', or ISO timestamp"
            },
            "name": {
              "type": "string",
              "description": "Optional human-friendly name"
            },
            "repeat": {
              "type": "integer",
              "description": "Optional repeat count. Omit for defaults (once for one-shot, forever for recurring)."
            },
            "deliver": {
              "type": "string",
              "description": "Omit this parameter to auto-deliver back to the current chat and topic (recommended). Auto-detection preserves thread/topic context. Only set explicitly when the user asks to deliver somewhere OTHER than the current conversation. Values: 'origin' (same as omitting), 'local' (no delivery, save only), 'all' (fan out to every connected home channel), or platform:chat_id:thread_id for a specific destination. Combine with comma: 'origin,all' delivers to the origin plus every other connected channel. Examples: 'telegram:-1001234567890:17585', 'discord:#engineering', 'sms:+15551234567', 'all'. WARNING: 'platform:chat_id' without :thread_id loses topic targeting. 'all' resolves at fire time, so a job created before a channel was wired up will pick it up automatically once connected."
            },
            "skills": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "description": "Optional ordered list of skill names to load before executing the cron prompt. On update, pass an empty array to clear attached skills."
            },
            "model": {
              "type": "object",
              "description": "Optional per-job model override. If provider is omitted, the current main provider is pinned at creation time so the job stays stable.",
              "properties": {
                "provider": {
                  "type": "string",
                  "description": "Provider name (e.g. 'openrouter', 'anthropic', or 'custom:<name>' for a provider defined in custom_providers config — always include the ':<name>' suffix, never pass the bare 'custom'). Omit to use and pin the current provider."
                },
                "model": {
                  "type": "string",
                  "description": "Model name (e.g. 'anthropic/claude-sonnet-4', 'claude-sonnet-4')"
                }
              },
              "required": [
                "model"
              ]
            },
            "script": {
              "type": "string",
              "description": "Optional path to a script that runs each tick. In the default mode its stdout is injected into the agent's prompt as context (data-collection / change-detection pattern). With no_agent=True, the script IS the job and its stdout is delivered verbatim (classic watchdog pattern). Relative paths resolve under ~/.hermes/scripts/. ``.sh``/``.bash`` extensions run via bash, everything else via Python. On update, pass empty string to clear."
            },
            "no_agent": {
              "type": "boolean",
              "default": false,
              "description": "Default: False (LLM-driven job — the agent runs the prompt each tick). Set True to skip the LLM entirely: the scheduler just runs ``script`` on schedule and delivers its stdout verbatim. No tokens, no agent loop, no model override honoured. \n\nREQUIREMENTS when True: ``script`` MUST be set (``prompt`` and ``skills`` are ignored). \n\nDELIVERY SEMANTICS when True: (a) non-empty stdout is sent verbatim as the message; (b) EMPTY stdout means SILENT — nothing is sent to the user and they won't see anything happened, so design your script to stay quiet when there's nothing to report (the watchdog pattern); (c) non-zero exit / timeout sends an error alert so a broken watchdog can't fail silently. \n\nWHEN TO USE True: recurring script-only pings where the script itself produces the exact message text (memory/disk/GPU watchdogs, threshold alerts, heartbeats, CI notifications, API pollers with a fixed output shape). WHEN TO USE False (default): anything that needs reasoning — summarize a feed, draft a daily briefing, pick interesting items, rephrase data for a human, follow conditional logic based on content."
            },
            "context_from": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "description": "Optional job ID or list of job IDs whose most recent completed output is injected into the prompt as context before each run. Use this to chain cron jobs: job A collects data, job B processes it. Each entry must be a valid job ID (from cronjob action='list'). Note: injects the most recent completed output — does not wait for upstream jobs running in the same tick. On update, pass an empty array to clear."
            },
            "enabled_toolsets": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "description": "Optional list of toolset names to restrict the job's agent to (e.g. [\"web\", \"terminal\", \"file\", \"delegation\"]). When set, only tools from these toolsets are loaded, significantly reducing input token overhead. When omitted, all default tools are loaded. Infer from the job's prompt — e.g. use \"web\" if it calls web_search, \"terminal\" if it runs scripts, \"file\" if it reads files, \"delegation\" if it calls delegate_task. On update, pass an empty array to clear."
            },
            "workdir": {
              "type": "string",
              "description": "Optional absolute path to run the job from. When set, AGENTS.md / CLAUDE.md / .cursorrules from that directory are injected into the system prompt, and the terminal/file/code_exec tools use it as their working directory — useful for running a job inside a specific project repo. Must be an absolute path that exists. When unset (default), preserves the original behaviour: no project context files, tools use the scheduler's cwd. On update, pass an empty string to clear. Jobs with workdir run sequentially (not parallel) to keep per-job directories isolated."
            }
          },
          "required": [
            "action"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "delegate_task",
        "description": "Spawn one or more subagents to work on tasks in isolated contexts. Each subagent gets its own conversation, terminal session, and toolset. Only the final summary is returned -- intermediate tool results never enter your context window.\n\nTWO MODES (one of 'goal' or 'tasks' is required):\n1. Single task: provide 'goal' (+ optional context, toolsets)\n2. Batch (parallel): provide 'tasks' array with up to 3 items concurrently for this user (configured via delegation.max_concurrent_children in config.yaml). All run in parallel and results are returned together. Nested delegation is OFF for this user (max_spawn_depth=1): every child is a leaf and cannot delegate further. Raise delegation.max_spawn_depth in config.yaml to enable nesting.\n\nWHEN TO USE delegate_task:\n- Reasoning-heavy subtasks (debugging, code review, research synthesis)\n- Tasks that would flood your context with intermediate data\n- Parallel independent workstreams (research A and B simultaneously)\n\nWHEN NOT TO USE (use these instead):\n- Mechanical multi-step work with no reasoning needed -> use execute_code\n- Single tool call -> just call the tool directly\n- Tasks needing user interaction -> subagents cannot use clarify\n- Durable long-running work that must outlive the current turn -> use cronjob (action='create') or terminal(background=True, notify_on_complete=True) instead. delegate_task runs SYNCHRONOUSLY inside the parent turn: if the parent is interrupted (user sends a new message, /stop, /new) the child is cancelled with status='interrupted' and its work is discarded. Children cannot continue in the background.\n\nIMPORTANT:\n- Subagents have NO memory of your conversation. Pass all relevant info (file paths, error messages, constraints) via the 'context' field.\n- If the user is writing in a non-English language, or asked for output in a specific language / tone / style, say so in 'context' (e.g. \"respond in Chinese\", \"return output in Japanese\"). Otherwise subagents default to English and their summaries will contaminate your final reply with the wrong language.\n- Subagent summaries are SELF-REPORTS, not verified facts. A subagent that claims \"uploaded successfully\" or \"file written\" may be wrong. For operations with external side-effects (HTTP POST/PUT, remote writes, file creation at shared paths, publishing), require the subagent to return a verifiable handle (URL, ID, absolute path, HTTP status) and verify it yourself — fetch the URL, stat the file, read back the content — before telling the user the operation succeeded.\n- Leaf subagents (role='leaf', the default) CANNOT call: delegate_task, clarify, memory, send_message, execute_code.\n- Orchestrator subagents (role='orchestrator') retain delegate_task so they can spawn their own workers, but still cannot use clarify, memory, send_message, or execute_code. Orchestrators are bounded by max_spawn_depth=1 for this user and can be disabled globally via delegation.orchestrator_enabled=false.\n- Each subagent gets its own terminal session (separate working directory and state).\n- Results are always returned as an array, one entry per task.",
        "parameters": {
          "type": "object",
          "properties": {
            "goal": {
              "type": "string",
              "description": "What the subagent should accomplish. Be specific and self-contained -- the subagent knows nothing about your conversation history."
            },
            "context": {
              "type": "string",
              "description": "Background information the subagent needs: file paths, error messages, project structure, constraints. The more specific you are, the better the subagent performs."
            },
            "toolsets": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "description": "Toolsets to enable for this subagent. Default: inherits your enabled toolsets. Available toolsets: 'browser', 'computer_use', 'cronjob', 'discord', 'discord_admin', 'feishu_doc', 'feishu_drive', 'file', 'homeassistant', 'image_gen', 'kanban', 'search', 'session_search', 'skills', 'spotify', 'terminal', 'todo', 'tts', 'video', 'video_gen', 'vision', 'web', 'yuanbao'. Common patterns: ['terminal', 'file'] for code work, ['web'] for research, ['browser'] for web interaction, ['terminal', 'file', 'web'] for full-stack tasks."
            },
            "tasks": {
              "type": "array",
              "items": {
                "type": "object",
                "properties": {
                  "goal": {
                    "type": "string",
                    "description": "Task goal"
                  },
                  "context": {
                    "type": "string",
                    "description": "Task-specific context"
                  },
                  "toolsets": {
                    "type": "array",
                    "items": {
                      "type": "string"
                    },
                    "description": "Toolsets for this specific task. Available: 'browser', 'computer_use', 'cronjob', 'discord', 'discord_admin', 'feishu_doc', 'feishu_drive', 'file', 'homeassistant', 'image_gen', 'kanban', 'search', 'session_search', 'skills', 'spotify', 'terminal', 'todo', 'tts', 'video', 'video_gen', 'vision', 'web', 'yuanbao'. Use 'web' for network access, 'terminal' for shell, 'browser' for web interaction."
                  },
                  "acp_command": {
                    "type": "string",
                    "description": "Per-task ACP command override (e.g. 'copilot'). Overrides the top-level acp_command for this task only. Do NOT set unless the user explicitly told you an ACP CLI is installed."
                  },
                  "acp_args": {
                    "type": "array",
                    "items": {
                      "type": "string"
                    },
                    "description": "Per-task ACP args override. Leave empty unless acp_command is set."
                  },
                  "role": {
                    "type": "string",
                    "enum": [
                      "leaf",
                      "orchestrator"
                    ],
                    "description": "Per-task role override. See top-level 'role' for semantics."
                  }
                },
                "required": [
                  "goal"
                ]
              },
              "description": "Batch mode: tasks to run in parallel (up to 3 for this user, set via delegation.max_concurrent_children). Each gets its own subagent with isolated context and terminal session. When provided, top-level goal/context/toolsets are ignored."
            },
            "role": {
              "type": "string",
              "enum": [
                "leaf",
                "orchestrator"
              ],
              "description": "Role of the child agent. 'leaf' (default) = focused worker, cannot delegate further. 'orchestrator' = can use delegate_task to spawn its own workers. Nesting is OFF for this user (max_spawn_depth=1); 'orchestrator' is silently forced to 'leaf'. Raise delegation.max_spawn_depth in config.yaml to enable."
            },
            "acp_command": {
              "type": "string",
              "description": "Override ACP command for child agents (e.g. 'copilot'). When set, children use ACP subprocess transport instead of inheriting the parent's transport. Requires an ACP-compatible CLI (currently GitHub Copilot CLI via 'copilot --acp --stdio'). See agent/copilot_acp_client.py for the implementation. IMPORTANT: Do NOT set this unless the user has explicitly told you a specific ACP-compatible CLI is installed and configured. Leave empty to use the parent's default transport (Hermes subagents)."
            },
            "acp_args": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "description": "Arguments for the ACP command (default: ['--acp', '--stdio']). Only used when acp_command is set. Leave empty unless acp_command is explicitly provided."
            }
          }
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "discord",
        "description": "Read and participate in a Discord server.\n\nAvailable actions:\n  search_members(guild_id, query)  — find members by name prefix\n  fetch_messages(channel_id)  — recent messages; optional before/after snowflakes\n  create_thread(channel_id, name)  — create a public thread; optional message_id anchor\n\nUse the channel_id from the current conversation context. Use search_members to look up user IDs by name prefix.",
        "parameters": {
          "type": "object",
          "properties": {
            "action": {
              "type": "string",
              "enum": [
                "search_members",
                "fetch_messages",
                "create_thread"
              ]
            },
            "guild_id": {
              "type": "string",
              "description": "Discord server (guild) ID."
            },
            "channel_id": {
              "type": "string",
              "description": "Discord channel ID."
            },
            "user_id": {
              "type": "string",
              "description": "Discord user ID."
            },
            "role_id": {
              "type": "string",
              "description": "Discord role ID."
            },
            "message_id": {
              "type": "string",
              "description": "Discord message ID."
            },
            "query": {
              "type": "string",
              "description": "Member name prefix to search for (search_members)."
            },
            "name": {
              "type": "string",
              "description": "New thread name (create_thread)."
            },
            "limit": {
              "type": "integer",
              "minimum": 1,
              "maximum": 100,
              "description": "Max results (default 50). Applies to fetch_messages, search_members."
            },
            "before": {
              "type": "string",
              "description": "Snowflake ID for reverse pagination (fetch_messages)."
            },
            "after": {
              "type": "string",
              "description": "Snowflake ID for forward pagination (fetch_messages)."
            },
            "auto_archive_duration": {
              "type": "integer",
              "enum": [
                60,
                1440,
                4320,
                10080
              ],
              "description": "Thread archive duration in minutes (create_thread, default 1440)."
            }
          },
          "required": [
            "action"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "discord_admin",
        "description": "Manage a Discord server via the REST API.\n\nAvailable actions:\n  list_guilds()  — list servers the bot is in\n  server_info(guild_id)  — server details + member counts\n  list_channels(guild_id)  — all channels grouped by category\n  channel_info(channel_id)  — single channel details\n  list_roles(guild_id)  — roles sorted by position\n  member_info(guild_id, user_id)  — lookup a specific member\n  list_pins(channel_id)  — pinned messages in a channel\n  pin_message(channel_id, message_id)  — pin a message\n  unpin_message(channel_id, message_id)  — unpin a message\n  delete_message(channel_id, message_id)  — delete a message\n  add_role(guild_id, user_id, role_id)  — assign a role\n  remove_role(guild_id, user_id, role_id)  — remove a role\n\nCall list_guilds first to discover guild_ids, then list_channels for channel_ids. Runtime errors will tell you if the bot lacks a specific per-guild permission (e.g. MANAGE_ROLES for add_role).",
        "parameters": {
          "type": "object",
          "properties": {
            "action": {
              "type": "string",
              "enum": [
                "list_guilds",
                "server_info",
                "list_channels",
                "channel_info",
                "list_roles",
                "member_info",
                "list_pins",
                "pin_message",
                "unpin_message",
                "delete_message",
                "add_role",
                "remove_role"
              ]
            },
            "guild_id": {
              "type": "string",
              "description": "Discord server (guild) ID."
            },
            "channel_id": {
              "type": "string",
              "description": "Discord channel ID."
            },
            "user_id": {
              "type": "string",
              "description": "Discord user ID."
            },
            "role_id": {
              "type": "string",
              "description": "Discord role ID."
            },
            "message_id": {
              "type": "string",
              "description": "Discord message ID."
            },
            "query": {
              "type": "string",
              "description": "Member name prefix to search for (search_members)."
            },
            "name": {
              "type": "string",
              "description": "New thread name (create_thread)."
            },
            "limit": {
              "type": "integer",
              "minimum": 1,
              "maximum": 100,
              "description": "Max results (default 50). Applies to fetch_messages, search_members."
            },
            "before": {
              "type": "string",
              "description": "Snowflake ID for reverse pagination (fetch_messages)."
            },
            "after": {
              "type": "string",
              "description": "Snowflake ID for forward pagination (fetch_messages)."
            },
            "auto_archive_duration": {
              "type": "integer",
              "enum": [
                60,
                1440,
                4320,
                10080
              ],
              "description": "Thread archive duration in minutes (create_thread, default 1440)."
            }
          },
          "required": [
            "action"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "execute_code",
        "description": "Run a Python script that can call Hermes tools programmatically. Use this when you need 3+ tool calls with processing logic between them, need to filter/reduce large tool outputs before they enter your context, need conditional branching (if X then Y else Z), or need to loop (fetch N pages, process N files, retry on failure).\n\nUse normal tool calls instead when: single tool call with no processing, you need to see the full result and apply complex reasoning, or the task requires interactive user input.\n\nAvailable via `from hermes_tools import ...`:\n\n  web_search(query: str, limit: int = 5) -> dict\n    Returns {\"data\": {\"web\": [{\"url\", \"title\", \"description\"}, ...]}}\n  web_extract(urls: list[str]) -> dict\n    Returns {\"results\": [{\"url\", \"title\", \"content\", \"error\"}, ...]} where content is markdown\n  read_file(path: str, offset: int = 1, limit: int = 500) -> dict\n    Lines are 1-indexed. Returns {\"content\": \"...\", \"total_lines\": N}\n  write_file(path: str, content: str) -> dict\n    Always overwrites the entire file.\n  search_files(pattern: str, target=\"content\", path=\".\", file_glob=None, limit=50) -> dict\n    target: \"content\" (search inside files) or \"files\" (find files by name). Returns {\"matches\": [...]}\n  patch(path: str, old_string: str, new_string: str, replace_all: bool = False) -> dict\n    Replaces old_string with new_string in the file.\n  terminal(command: str, timeout=None, workdir=None) -> dict\n    Foreground only (no background/pty). Returns {\"output\": \"...\", \"exit_code\": N}\n\nLimits: 5-minute timeout, 50KB stdout cap, max 50 tool calls per script. terminal() is foreground-only (no background or pty).\n\nScripts run in the session's working directory with the active venv's python, so project deps (pandas, etc.) and relative paths work like in terminal().\n\nPrint your final result to stdout. Use Python stdlib (json, re, math, csv, datetime, collections, etc.) for processing between tool calls.\n\nAlso available (no import needed — built into hermes_tools):\n  json_parse(text: str) — json.loads with strict=False; use for terminal() output with control chars\n  shell_quote(s: str) — shlex.quote(); use when interpolating dynamic strings into shell commands\n  retry(fn, max_attempts=3, delay=2) — retry with exponential backoff for transient failures",
        "parameters": {
          "type": "object",
          "properties": {
            "code": {
              "type": "string",
              "description": "Python code to execute. Import tools with `from hermes_tools import web_search, terminal, ...` and print your final result to stdout."
            }
          },
          "required": [
            "code"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "feishu_doc_read",
        "description": "Read the full content of a Feishu/Lark document as plain text. Useful when you need more context beyond the quoted text in a comment.",
        "parameters": {
          "type": "object",
          "properties": {
            "doc_token": {
              "type": "string",
              "description": "The document token (from the document URL or comment context)."
            }
          },
          "required": [
            "doc_token"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "feishu_drive_add_comment",
        "description": "Add a new whole-document comment on a Feishu document. Use this for whole-document comments or as a fallback when reply_comment fails with code 1069302.",
        "parameters": {
          "type": "object",
          "properties": {
            "file_token": {
              "type": "string",
              "description": "The document file token."
            },
            "content": {
              "type": "string",
              "description": "The comment text content (plain text only, no markdown)."
            },
            "file_type": {
              "type": "string",
              "description": "File type (default: docx).",
              "default": "docx"
            }
          },
          "required": [
            "file_token",
            "content"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "feishu_drive_list_comment_replies",
        "description": "List all replies in a comment thread on a Feishu document.",
        "parameters": {
          "type": "object",
          "properties": {
            "file_token": {
              "type": "string",
              "description": "The document file token."
            },
            "comment_id": {
              "type": "string",
              "description": "The comment ID to list replies for."
            },
            "file_type": {
              "type": "string",
              "description": "File type (default: docx).",
              "default": "docx"
            },
            "page_size": {
              "type": "integer",
              "description": "Number of replies per page (max 100).",
              "default": 100
            },
            "page_token": {
              "type": "string",
              "description": "Pagination token for next page."
            }
          },
          "required": [
            "file_token",
            "comment_id"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "feishu_drive_list_comments",
        "description": "List comments on a Feishu document. Use is_whole=true to list whole-document comments only.",
        "parameters": {
          "type": "object",
          "properties": {
            "file_token": {
              "type": "string",
              "description": "The document file token."
            },
            "file_type": {
              "type": "string",
              "description": "File type (default: docx).",
              "default": "docx"
            },
            "is_whole": {
              "type": "boolean",
              "description": "If true, only return whole-document comments.",
              "default": false
            },
            "page_size": {
              "type": "integer",
              "description": "Number of comments per page (max 100).",
              "default": 100
            },
            "page_token": {
              "type": "string",
              "description": "Pagination token for next page."
            }
          },
          "required": [
            "file_token"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "feishu_drive_reply_comment",
        "description": "Reply to a local comment thread on a Feishu document. Use this for local (quoted-text) comments. For whole-document comments, use feishu_drive_add_comment instead.",
        "parameters": {
          "type": "object",
          "properties": {
            "file_token": {
              "type": "string",
              "description": "The document file token."
            },
            "comment_id": {
              "type": "string",
              "description": "The comment ID to reply to."
            },
            "content": {
              "type": "string",
              "description": "The reply text content (plain text only, no markdown)."
            },
            "file_type": {
              "type": "string",
              "description": "File type (default: docx).",
              "default": "docx"
            }
          },
          "required": [
            "file_token",
            "comment_id",
            "content"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "image_generate",
        "description": "Generate high-quality images from text prompts. The underlying backend (FAL, OpenAI, etc.) and model are user-configured and not selectable by the agent. Returns either a URL or an absolute file path in the `image` field; display it with markdown ![description](url-or-path) and the gateway will deliver it.",
        "parameters": {
          "type": "object",
          "properties": {
            "prompt": {
              "type": "string",
              "description": "The text prompt describing the desired image. Be detailed and descriptive."
            },
            "aspect_ratio": {
              "type": "string",
              "enum": [
                "landscape",
                "square",
                "portrait"
              ],
              "description": "The aspect ratio of the generated image. 'landscape' is 16:9 wide, 'portrait' is 16:9 tall, 'square' is 1:1.",
              "default": "landscape"
            }
          },
          "required": [
            "prompt"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "mcp_context7_query_docs",
        "description": "Retrieves and queries up-to-date documentation and code examples from Context7 for any programming library or framework.\n\nYou must call 'Resolve Context7 Library ID' tool first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nDo not call this tool more than 3 times per question.",
        "parameters": {
          "$schema": "http://json-schema.org/draft-07/schema#",
          "type": "object",
          "properties": {
            "libraryId": {
              "type": "string",
              "description": "Exact Context7-compatible library ID (e.g., '/mongodb/docs', '/vercel/next.js', '/supabase/supabase', '/vercel/next.js/v14.3.0-canary.87') retrieved from 'resolve-library-id' or directly from user query in the format '/org/project' or '/org/project/version'."
            },
            "query": {
              "type": "string",
              "description": "The question or task you need help with. Be specific and include relevant details. Good: 'How to set up authentication with JWT in Express.js' or 'React useEffect cleanup function examples'. Bad: 'auth' or 'hooks'. The query is sent to the Context7 API for processing. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query."
            }
          },
          "required": [
            "libraryId",
            "query"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "mcp_context7_resolve_library_id",
        "description": "Resolves a package/product name to a Context7-compatible library ID and returns matching libraries.\n\nYou MUST call this function before 'Query Documentation' tool to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nEach result includes:\n- Library ID: Context7-compatible identifier (format: /org/project)\n- Name: Library or package name\n- Description: Short summary\n- Code Snippets: Number of available code examples\n- Source Reputation: Authority indicator (High, Medium, Low, or Unknown)\n- Benchmark Score: Quality indicator (100 is the highest score)\n- Versions: List of versions if available. Use one of those versions if the user provides a version in their query. The format of the version is /org/project/version.\n\nFor best results, select libraries based on name match, source reputation, snippet coverage, benchmark score, and relevance to your use case.\n\nSelection Process:\n1. Analyze the query to understand what library/package the user is looking for\n2. Return the most relevant match based on:\n- Name similarity to the query (exact matches prioritized)\n- Description relevance to the query's intent\n- Documentation coverage (prioritize libraries with higher Code Snippet counts)\n- Source reputation (consider libraries with High or Medium reputation more authoritative)\n- Benchmark Score: Quality indicator (100 is the highest score)\n\nResponse Format:\n- Return the selected library ID in a clearly marked section\n- Provide a brief explanation for why this library was chosen\n- If multiple good matches exist, acknowledge this but proceed with the most relevant one\n- If no good matches exist, clearly state this and suggest query refinements\n\nFor ambiguous queries, request clarification before proceeding with a best-guess match.\n\nIMPORTANT: Do not call this tool more than 3 times per question. If you cannot find what you need after 3 calls, use the best result you have.",
        "parameters": {
          "$schema": "http://json-schema.org/draft-07/schema#",
          "type": "object",
          "properties": {
            "query": {
              "type": "string",
              "description": "The question or task you need help with. This is used to rank library results by relevance to what the user is trying to accomplish. The query is sent to the Context7 API for processing. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query."
            },
            "libraryName": {
              "type": "string",
              "description": "Library name to search for and retrieve a Context7-compatible library ID. Use the official library name with proper punctuation — e.g., 'Next.js' instead of 'nextjs', 'Customer.io' instead of 'customerio', 'Three.js' instead of 'threejs'."
            }
          },
          "required": [
            "query",
            "libraryName"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "memory",
        "description": "Save durable information to persistent memory that survives across sessions. Memory is injected into future turns, so keep it compact and focused on facts that will still matter later.\n\nWHEN TO SAVE (do this proactively, don't wait to be asked):\n- User corrects you or says 'remember this' / 'don't do that again'\n- User shares a preference, habit, or personal detail (name, role, timezone, coding style)\n- You discover something about the environment (OS, installed tools, project structure)\n- You learn a convention, API quirk, or workflow specific to this user's setup\n- You identify a stable fact that will be useful again in future sessions\n\nPRIORITY: User preferences and corrections > environment facts > procedural knowledge. The most valuable memory prevents the user from having to repeat themselves.\n\nDo NOT save task progress, session outcomes, completed-work logs, or temporary TODO state to memory; use session_search to recall those from past transcripts.\nIf you've discovered a new way to do something, solved a problem that could be necessary later, save it as a skill with the skill tool.\n\nTWO TARGETS:\n- 'user': who the user is -- name, role, preferences, communication style, pet peeves\n- 'memory': your notes -- environment facts, project conventions, tool quirks, lessons learned\n\nACTIONS: add (new entry), replace (update existing -- old_text identifies it), remove (delete -- old_text identifies it).\n\nSKIP: trivial/obvious info, things easily re-discovered, raw data dumps, and temporary task state.",
        "parameters": {
          "type": "object",
          "properties": {
            "action": {
              "type": "string",
              "enum": [
                "add",
                "replace",
                "remove"
              ],
              "description": "The action to perform."
            },
            "target": {
              "type": "string",
              "enum": [
                "memory",
                "user"
              ],
              "description": "Which memory store: 'memory' for personal notes, 'user' for user profile."
            },
            "content": {
              "type": "string",
              "description": "The entry content. Required for 'add' and 'replace'."
            },
            "old_text": {
              "type": "string",
              "description": "Short unique substring identifying the entry to replace or remove."
            }
          },
          "required": [
            "action",
            "target"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "mixture_of_agents",
        "description": "Route a hard problem through multiple frontier LLMs collaboratively. Makes 5 API calls (4 reference models + 1 aggregator) with maximum reasoning effort — use sparingly for genuinely difficult problems. Best for: complex math, advanced algorithms, multi-step analytical reasoning, problems benefiting from diverse perspectives.",
        "parameters": {
          "type": "object",
          "properties": {
            "user_prompt": {
              "type": "string",
              "description": "The complex query or problem to solve using multiple AI models. Should be a challenging problem that benefits from diverse perspectives and collaborative reasoning."
            }
          },
          "required": [
            "user_prompt"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "patch",
        "description": "Targeted find-and-replace edits in files. Use this instead of sed/awk in terminal. Uses fuzzy matching (9 strategies) so minor whitespace/indentation differences won't break it. Returns a unified diff. Auto-runs syntax checks after editing.\n\nREPLACE MODE (mode='replace', default): find a unique string and replace it. REQUIRED PARAMETERS: mode, path, old_string, new_string.\nPATCH MODE (mode='patch'): apply V4A multi-file patches for bulk changes. REQUIRED PARAMETERS: mode, patch.",
        "parameters": {
          "type": "object",
          "properties": {
            "mode": {
              "type": "string",
              "enum": [
                "replace",
                "patch"
              ],
              "description": "Edit mode. 'replace' (default): requires path + old_string + new_string. 'patch': requires patch content only.",
              "default": "replace"
            },
            "path": {
              "type": "string",
              "description": "REQUIRED when mode='replace'. File path to edit."
            },
            "old_string": {
              "type": "string",
              "description": "REQUIRED when mode='replace'. Exact text to find and replace. Must be unique in the file unless replace_all=true. Include surrounding context lines to ensure uniqueness."
            },
            "new_string": {
              "type": "string",
              "description": "REQUIRED when mode='replace'. Replacement text. Pass empty string '' to delete the matched text."
            },
            "replace_all": {
              "type": "boolean",
              "description": "Replace all occurrences instead of requiring a unique match (default: false)",
              "default": false
            },
            "patch": {
              "type": "string",
              "description": "REQUIRED when mode='patch'. V4A format patch content. Format:\n*** Begin Patch\n*** Update File: path/to/file\n@@ context hint @@\n context line\n-removed line\n+added line\n*** End Patch"
            }
          },
          "required": [
            "mode"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "process",
        "description": "Manage background processes started with terminal(background=true). Actions: 'list' (show all), 'poll' (check status + new output), 'log' (full output with pagination), 'wait' (block until done or timeout), 'kill' (terminate), 'write' (send raw stdin data without newline), 'submit' (send data + Enter, for answering prompts), 'close' (close stdin/send EOF).",
        "parameters": {
          "type": "object",
          "properties": {
            "action": {
              "type": "string",
              "enum": [
                "list",
                "poll",
                "log",
                "wait",
                "kill",
                "write",
                "submit",
                "close"
              ],
              "description": "Action to perform on background processes"
            },
            "session_id": {
              "type": "string",
              "description": "Process session ID (from terminal background output). Required for all actions except 'list'."
            },
            "data": {
              "type": "string",
              "description": "Text to send to process stdin (for 'write' and 'submit' actions)"
            },
            "timeout": {
              "type": "integer",
              "description": "Max seconds to block for 'wait' action. Returns partial output on timeout.",
              "minimum": 1
            },
            "offset": {
              "type": "integer",
              "description": "Line offset for 'log' action (default: last 200 lines)"
            },
            "limit": {
              "type": "integer",
              "description": "Max lines to return for 'log' action",
              "minimum": 1
            }
          },
          "required": [
            "action"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "read_file",
        "description": "Read a text file with line numbers and pagination. Use this instead of cat/head/tail in terminal. Output format: 'LINE_NUM|CONTENT'. Suggests similar filenames if not found. Use offset and limit for large files. Reads exceeding ~100K characters are rejected; use offset and limit to read specific sections of large files. NOTE: Cannot read images or binary files — use vision_analyze for images.",
        "parameters": {
          "type": "object",
          "properties": {
            "path": {
              "type": "string",
              "description": "Path to the file to read (absolute, relative, or ~/path)"
            },
            "offset": {
              "type": "integer",
              "description": "Line number to start reading from (1-indexed, default: 1)",
              "default": 1,
              "minimum": 1
            },
            "limit": {
              "type": "integer",
              "description": "Maximum number of lines to read (default: 500, max: 2000)",
              "default": 500,
              "maximum": 2000
            }
          },
          "required": [
            "path"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "search_files",
        "description": "Search file contents or find files by name. Use this instead of grep/rg/find/ls in terminal. Ripgrep-backed, faster than shell equivalents.\n\nContent search (target='content'): Regex search inside files. Output modes: full matches with line numbers, file paths only, or match counts.\n\nFile search (target='files'): Find files by glob pattern (e.g., '*.py', '*config*'). Also use this instead of ls — results sorted by modification time.",
        "parameters": {
          "type": "object",
          "properties": {
            "pattern": {
              "type": "string",
              "description": "Regex pattern for content search, or glob pattern (e.g., '*.py') for file search"
            },
            "target": {
              "type": "string",
              "enum": [
                "content",
                "files"
              ],
              "description": "'content' searches inside file contents, 'files' searches for files by name",
              "default": "content"
            },
            "path": {
              "type": "string",
              "description": "Directory or file to search in (default: current working directory)",
              "default": "."
            },
            "file_glob": {
              "type": "string",
              "description": "Filter files by pattern in grep mode (e.g., '*.py' to only search Python files)"
            },
            "limit": {
              "type": "integer",
              "description": "Maximum number of results to return (default: 50)",
              "default": 50
            },
            "offset": {
              "type": "integer",
              "description": "Skip first N results for pagination (default: 0)",
              "default": 0
            },
            "output_mode": {
              "type": "string",
              "enum": [
                "content",
                "files_only",
                "count"
              ],
              "description": "Output format for grep mode: 'content' shows matching lines with line numbers, 'files_only' lists file paths, 'count' shows match counts per file",
              "default": "content"
            },
            "context": {
              "type": "integer",
              "description": "Number of context lines before and after each match (grep mode only)",
              "default": 0
            }
          },
          "required": [
            "pattern"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "send_message",
        "description": "Send a message to a connected messaging platform, or list available targets.\n\nIMPORTANT: When the user asks to send to a specific channel or person (not just a bare platform name), call send_message(action='list') FIRST to see available targets, then send to the correct one.\nIf the user just says a platform name like 'send to telegram', send directly to the home channel without listing first.",
        "parameters": {
          "type": "object",
          "properties": {
            "action": {
              "type": "string",
              "enum": [
                "send",
                "list"
              ],
              "description": "Action to perform. 'send' (default) sends a message. 'list' returns all available channels/contacts across connected platforms."
            },
            "target": {
              "type": "string",
              "description": "Delivery target. Format: 'platform' (uses home channel), 'platform:#channel-name', 'platform:chat_id', or 'platform:chat_id:thread_id' for Telegram topics and Discord threads. Examples: 'telegram', 'telegram:-1001234567890:17585', 'discord:999888777:555444333', 'discord:#bot-home', 'slack:#engineering', 'signal:+155****4567', 'matrix:!roomid:server.org', 'matrix:@user:server.org', 'yuanbao:direct:<account_id>' (DM), 'yuanbao:group:<group_code>' (group chat)"
            },
            "message": {
              "type": "string",
              "description": "The message text to send. To send an image or file, include MEDIA:<local_path> (e.g. 'MEDIA:/tmp/hermes/cache/img_xxx.jpg') in the message — the platform will deliver it as a native media attachment."
            }
          }
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "session_search",
        "description": "Search your long-term memory of past conversations, or browse recent sessions. This is your recall -- every past session is searchable, and this tool summarizes what happened.\n\nTWO MODES:\n1. Recent sessions (no query): Call with no arguments to see what was worked on recently. Returns titles, previews, and timestamps. Zero LLM cost, instant. Start here when the user asks what were we working on or what did we do recently.\n2. Keyword search (with query): Search for specific topics across all past sessions. Returns LLM-generated summaries of matching sessions.\n\nUSE THIS PROACTIVELY when:\n- The user says 'we did this before', 'remember when', 'last time', 'as I mentioned'\n- The user asks about a topic you worked on before but don't have in current context\n- The user references a project, person, or concept that seems familiar but isn't in memory\n- You want to check if you've solved a similar problem before\n- The user asks 'what did we do about X?' or 'how did we fix Y?'\n\nDon't hesitate to search when it is actually cross-session -- it's fast and cheap. Better to search and confirm than to guess or ask the user to repeat themselves.\n\nSearch syntax: keywords joined with OR for broad recall (elevenlabs OR baseten OR funding), phrases for exact match (\"docker networking\"), boolean (python NOT java), prefix (deploy*). IMPORTANT: Use OR between keywords for best results — FTS5 defaults to AND which misses sessions that only mention some terms. If a broad OR query returns nothing, try individual keyword searches in parallel. Returns summaries of the top matching sessions.",
        "parameters": {
          "type": "object",
          "properties": {
            "query": {
              "type": "string",
              "description": "Search query — keywords, phrases, or boolean expressions to find in past sessions. Omit this parameter entirely to browse recent sessions instead (returns titles, previews, timestamps with no LLM cost)."
            },
            "role_filter": {
              "type": "string",
              "description": "Optional: only search messages from specific roles (comma-separated). E.g. 'user,assistant' to skip tool outputs."
            },
            "limit": {
              "type": "integer",
              "description": "Max sessions to summarize (default: 3, max: 5).",
              "default": 3
            }
          }
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "skill_manage",
        "description": "Manage skills (create, update, delete). Skills are your procedural memory — reusable approaches for recurring task types. New skills go to ~/.hermes/skills/; existing skills can be modified wherever they live.\n\nActions: create (full SKILL.md + optional category), patch (old_string/new_string — preferred for fixes), edit (full SKILL.md rewrite — major overhauls only), delete, write_file, remove_file.\n\nOn delete, pass `absorbed_into=<umbrella>` when you're merging this skill's content into another one, or `absorbed_into=\"\"` when you're pruning it with no forwarding target. This lets the curator tell consolidation from pruning without guessing, so downstream consumers (cron jobs that reference the old skill name, etc.) get updated correctly. The target you name in `absorbed_into` must already exist — create/patch the umbrella first, then delete.\n\nCreate when: complex task succeeded (5+ calls), errors overcome, user-corrected approach worked, non-trivial workflow discovered, or user asks you to remember a procedure.\nUpdate when: instructions stale/wrong, OS-specific failures, missing steps or pitfalls found during use. If you used a skill and hit issues not covered by it, patch it immediately.\n\nAfter difficult/iterative tasks, offer to save as a skill. Skip for simple one-offs. Confirm with user before creating/deleting.\n\nGood skills: trigger conditions, numbered steps with exact commands, pitfalls section, verification steps. Use skill_view() to see format examples.\n\nPinned skills are protected from deletion only — skill_manage(action='delete') will refuse with a message pointing the user to `hermes curator unpin <name>`. Patches and edits go through on pinned skills so you can still improve them as pitfalls come up; pin only guards against irrecoverable loss.",
        "parameters": {
          "type": "object",
          "properties": {
            "action": {
              "type": "string",
              "enum": [
                "create",
                "patch",
                "edit",
                "delete",
                "write_file",
                "remove_file"
              ],
              "description": "The action to perform."
            },
            "name": {
              "type": "string",
              "description": "Skill name (lowercase, hyphens/underscores, max 64 chars). Must match an existing skill for patch/edit/delete/write_file/remove_file."
            },
            "content": {
              "type": "string",
              "description": "Full SKILL.md content (YAML frontmatter + markdown body). Required for 'create' and 'edit'. For 'edit', read the skill first with skill_view() and provide the complete updated text."
            },
            "old_string": {
              "type": "string",
              "description": "Text to find in the file (required for 'patch'). Must be unique unless replace_all=true. Include enough surrounding context to ensure uniqueness."
            },
            "new_string": {
              "type": "string",
              "description": "Replacement text (required for 'patch'). Can be empty string to delete the matched text."
            },
            "replace_all": {
              "type": "boolean",
              "description": "For 'patch': replace all occurrences instead of requiring a unique match (default: false)."
            },
            "category": {
              "type": "string",
              "description": "Optional category/domain for organizing the skill (e.g., 'devops', 'data-science', 'mlops'). Creates a subdirectory grouping. Only used with 'create'."
            },
            "file_path": {
              "type": "string",
              "description": "Path to a supporting file within the skill directory. For 'write_file'/'remove_file': required, must be under references/, templates/, scripts/, or assets/. For 'patch': optional, defaults to SKILL.md if omitted."
            },
            "file_content": {
              "type": "string",
              "description": "Content for the file. Required for 'write_file'."
            },
            "absorbed_into": {
              "type": "string",
              "description": "For 'delete' only — declares intent so the curator can tell consolidation from pruning without guessing. Pass the umbrella skill name when this skill's content was merged into another (the target must already exist). Pass an empty string when the skill is truly stale and being pruned with no forwarding target. Omitting the arg on delete is supported for backward compatibility but downstream tooling (e.g. cron-job skill reference rewriting) will have to guess at intent."
            }
          },
          "required": [
            "action",
            "name"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "skill_view",
        "description": "Skills allow for loading information about specific tasks and workflows, as well as scripts and templates. Load a skill's full content or access its linked files (references, templates, scripts). First call returns SKILL.md content plus a 'linked_files' dict showing available references/templates/scripts. To access those, call again with file_path parameter.",
        "parameters": {
          "type": "object",
          "properties": {
            "name": {
              "type": "string",
              "description": "The skill name (use skills_list to see available skills). For plugin-provided skills, use the qualified form 'plugin:skill' (e.g. 'superpowers:writing-plans')."
            },
            "file_path": {
              "type": "string",
              "description": "OPTIONAL: Path to a linked file within the skill (e.g., 'references/api.md', 'templates/config.yaml', 'scripts/validate.py'). Omit to get the main SKILL.md content."
            }
          },
          "required": [
            "name"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "skills_list",
        "description": "List available skills (name + description). Use skill_view(name) to load full content.",
        "parameters": {
          "type": "object",
          "properties": {
            "category": {
              "type": "string",
              "description": "Optional category filter to narrow results"
            }
          }
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "terminal",
        "description": "Execute shell commands on a Linux environment. Filesystem usually persists between calls.\n\nDo NOT use cat/head/tail to read files — use read_file instead.\nDo NOT use grep/rg/find to search — use search_files instead.\nDo NOT use ls to list directories — use search_files(target='files') instead.\nDo NOT use sed/awk to edit files — use patch instead.\nDo NOT use echo/cat heredoc to create files — use write_file instead.\nReserve terminal for: builds, installs, git, processes, scripts, network, package managers, and anything that needs a shell.\n\nForeground (default): Commands return INSTANTLY when done, even if the timeout is high. Set timeout=300 for long builds/scripts — you'll still get the result in seconds if it's fast. Prefer foreground for short commands.\nBackground: Set background=true to get a session_id. Two patterns:\n  (1) Long-lived processes that never exit (servers, watchers).\n  (2) Long-running tasks with notify_on_complete=true — you can keep working on other things and the system auto-notifies you when the task finishes. Great for test suites, builds, deployments, or anything that takes more than a minute.\nFor servers/watchers, do NOT use shell-level background wrappers (nohup/disown/setsid/trailing '&') in foreground mode. Use background=true so Hermes can track lifecycle and output.\nAfter starting a server, verify readiness with a health check or log signal, then run tests in a separate terminal() call. Avoid blind sleep loops.\nUse process(action=\"poll\") for progress checks, process(action=\"wait\") to block until done.\nWorking directory: Use 'workdir' for per-command cwd.\nPTY mode: Set pty=true for interactive CLI tools (Codex, Claude Code, Python REPL).\n\nDo NOT use vim/nano/interactive tools without pty=true — they hang without a pseudo-terminal. Pipe git output to cat if it might page.\n",
        "parameters": {
          "type": "object",
          "properties": {
            "command": {
              "type": "string",
              "description": "The command to execute on the VM"
            },
            "background": {
              "type": "boolean",
              "description": "Run the command in the background. Two patterns: (1) Long-lived processes that never exit (servers, watchers). (2) Long-running tasks paired with notify_on_complete=true — you can keep working and get notified when the task finishes. For short commands, prefer foreground with a generous timeout instead.",
              "default": false
            },
            "timeout": {
              "type": "integer",
              "description": "Max seconds to wait (default: 180, foreground max: 600). Returns INSTANTLY when command finishes — set high for long tasks, you won't wait unnecessarily. Foreground timeout above 600s is rejected; use background=true for longer commands.",
              "minimum": 1
            },
            "workdir": {
              "type": "string",
              "description": "Working directory for this command (absolute path). Defaults to the session working directory."
            },
            "pty": {
              "type": "boolean",
              "description": "Run in pseudo-terminal (PTY) mode for interactive CLI tools like Codex, Claude Code, or Python REPL. Only works with local and SSH backends. Default: false.",
              "default": false
            },
            "notify_on_complete": {
              "type": "boolean",
              "description": "When true (and background=true), you'll be automatically notified exactly once when the process finishes. **This is the right choice for almost every long-running task** — tests, builds, deployments, multi-item batch jobs, anything that takes over a minute and has a defined end. Use this and keep working on other things; the system notifies you on exit. MUTUALLY EXCLUSIVE with watch_patterns — when both are set, watch_patterns is dropped.",
              "default": false
            },
            "watch_patterns": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "description": "Strings to watch for in background process output. HARD RATE LIMIT: at most 1 notification per 15 seconds per process — matches arriving inside the cooldown are dropped. After 3 consecutive 15-second windows with dropped matches, watch_patterns is automatically disabled for that process and promoted to notify_on_complete behavior (one notification on exit, no more mid-process spam). USE ONLY for truly rare, one-shot mid-process signals on LONG-LIVED processes that will never exit on their own — e.g. ['Application startup complete'] on a server so you know when to hit its endpoint, or ['migration done'] on a daemon. DO NOT use for: (1) end-of-run markers like 'DONE'/'PASS' — use notify_on_complete instead; (2) error patterns like 'ERROR'/'Traceback' in loops or multi-item batch jobs — they fire on every iteration and you'll hit the strike limit fast; (3) anything you'd ever combine with notify_on_complete. When in doubt, choose notify_on_complete. MUTUALLY EXCLUSIVE with notify_on_complete — set one, not both."
            }
          },
          "required": [
            "command"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "text_to_speech",
        "description": "Convert text to speech audio. Returns a MEDIA: path that the platform delivers as native audio. Compatible providers render as a voice bubble on Telegram; otherwise audio is sent as a regular attachment. In CLI mode, saves to ~/voice-memos/. Voice and provider are user-configured (built-in providers like edge/openai or custom command providers under tts.providers.<name>), not model-selected.",
        "parameters": {
          "type": "object",
          "properties": {
            "text": {
              "type": "string",
              "description": "The text to convert to speech. Provider-specific character caps apply and are enforced automatically (OpenAI 4096, xAI 15000, MiniMax 10000, ElevenLabs 5k-40k depending on model); over-long input is truncated."
            },
            "output_path": {
              "type": "string",
              "description": "Optional custom file path to save the audio. Defaults to ~/.hermes/audio_cache/<timestamp>.mp3"
            }
          },
          "required": [
            "text"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "todo",
        "description": "Manage your task list for the current session. Use for complex tasks with 3+ steps or when the user provides multiple tasks. Call with no parameters to read the current list.\n\nWriting:\n- Provide 'todos' array to create/update items\n- merge=false (default): replace the entire list with a fresh plan\n- merge=true: update existing items by id, add any new ones\n\nEach item: {id: string, content: string, status: pending|in_progress|completed|cancelled}\nList order is priority. Only ONE item in_progress at a time.\nMark items completed immediately when done. If something fails, cancel it and add a revised item.\n\nAlways returns the full current list.",
        "parameters": {
          "type": "object",
          "properties": {
            "todos": {
              "type": "array",
              "description": "Task items to write. Omit to read current list.",
              "items": {
                "type": "object",
                "properties": {
                  "id": {
                    "type": "string",
                    "description": "Unique item identifier"
                  },
                  "content": {
                    "type": "string",
                    "description": "Task description"
                  },
                  "status": {
                    "type": "string",
                    "enum": [
                      "pending",
                      "in_progress",
                      "completed",
                      "cancelled"
                    ],
                    "description": "Current status"
                  }
                },
                "required": [
                  "id",
                  "content",
                  "status"
                ]
              }
            },
            "merge": {
              "type": "boolean",
              "description": "true: update existing items by id, add new ones. false (default): replace the entire list.",
              "default": false
            }
          }
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "video_analyze",
        "description": "Analyze a video from a URL or local file path using a multimodal AI model. Sends the video to a video-capable model (e.g. Gemini) for understanding. Use this for video files — for images, use vision_analyze instead. Supports mp4, webm, mov, avi, mkv, mpeg formats. Note: large videos (>20 MB) may be slow; max ~50 MB.",
        "parameters": {
          "type": "object",
          "properties": {
            "video_url": {
              "type": "string",
              "description": "Video URL (http/https) or local file path to analyze."
            },
            "question": {
              "type": "string",
              "description": "Your specific question about the video. The AI will describe what happens in the video and answer your question."
            }
          },
          "required": [
            "video_url",
            "question"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "vision_analyze",
        "description": "Load an image into the conversation so you can see it. Accepts a URL, local file path, or data URL. When your active model has native vision, the image is attached to your context directly and you read the pixels yourself on the next turn — call this any time the user references an image (filepath in their message, URL in tool output, screenshot from the browser, etc.). For non-vision models, falls back to an auxiliary vision model that returns a text description.",
        "parameters": {
          "type": "object",
          "properties": {
            "image_url": {
              "type": "string",
              "description": "Image URL (http/https), local file path, or data: URL to load."
            },
            "question": {
              "type": "string",
              "description": "Your specific question or request about the image. Optional context the model uses on the next turn after seeing the image."
            }
          },
          "required": [
            "image_url",
            "question"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "web_extract",
        "description": "Extract content from web page URLs. Returns page content in markdown format. Also works with PDF URLs (arxiv papers, documents, etc.) — pass the PDF link directly and it converts to markdown text. Pages under 5000 chars return full markdown; larger pages are LLM-summarized and capped at ~5000 chars per page. Pages over 2M chars are refused. If a URL fails or times out, use the browser tool to access it instead.",
        "parameters": {
          "type": "object",
          "properties": {
            "urls": {
              "type": "array",
              "items": {
                "type": "string"
              },
              "description": "List of URLs to extract content from (max 5 URLs per call)",
              "maxItems": 5
            }
          },
          "required": [
            "urls"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "web_search",
        "description": "Search the web for information. Returns up to 5 results by default with titles, URLs, and descriptions. The query is passed through to the configured backend, so operators such as site:domain, filetype:pdf, intitle:word, -term, and \"exact phrase\" may work when the backend supports them.",
        "parameters": {
          "type": "object",
          "properties": {
            "query": {
              "type": "string",
              "description": "The search query to look up on the web. You may include backend-supported operators such as site:example.com, filetype:pdf, intitle:word, -term, or \"exact phrase\"."
            },
            "limit": {
              "type": "integer",
              "description": "Maximum number of results to return. Defaults to 5.",
              "minimum": 1,
              "maximum": 100,
              "default": 5
            }
          },
          "required": [
            "query"
          ]
        }
      }
    },
    {
      "type": "function",
      "function": {
        "name": "write_file",
        "description": "Write content to a file, completely replacing existing content. Use this instead of echo/cat heredoc in terminal. Creates parent directories automatically. OVERWRITES the entire file — use 'patch' for targeted edits. Auto-runs syntax checks on .py/.json/.yaml/.toml and other linted languages; only NEW errors introduced by this write are surfaced (pre-existing errors are filtered out).",
        "parameters": {
          "type": "object",
          "properties": {
            "path": {
              "type": "string",
              "description": "Path to the file to write (will be created if it doesn't exist, overwritten if it does)"
            },
            "content": {
              "type": "string",
              "description": "Complete content to write to the file"
            }
          },
          "required": [
            "path",
            "content"
          ]
        }
      }
    }
  ],
  "message_count": 6,
  "messages": [
    {
      "role": "user",
      "content": "You are running as Hermes' background skill CURATOR. This is an UMBRELLA-BUILDING consolidation pass, not a passive audit and not a duplicate-finder.\n\nThe goal of the skill collection is a LIBRARY OF CLASS-LEVEL INSTRUCTIONS AND EXPERIENTIAL KNOWLEDGE. A collection of hundreds of narrow skills where each one captures one session's specific bug is a FAILURE of the library — not a feature. An agent searching skills matches on descriptions, not on exact names; one broad umbrella skill with labeled subsections beats five narrow siblings for discoverability, not the other way around.\n\nThe right target shape is CLASS-LEVEL skills with rich SKILL.md bodies + `references/`, `templates/`, and `scripts/` subfiles for session-specific detail — not one-session-one-skill micro-entries.\n\nHard rules — do not violate:\n1. DO NOT touch bundled or hub-installed skills. The candidate list below is already filtered to agent-created skills only.\n2. DO NOT delete any skill. Archiving (moving the skill's directory into ~/.hermes/skills/.archive/) is the maximum destructive action. Archives are recoverable; deletion is not.\n3. DO NOT touch skills shown as pinned=yes. Skip them entirely.\n4. DO NOT use usage counters as a reason to skip consolidation. The counters are new and often mostly zero. Judge overlap on CONTENT, not on use_count. 'use=0' is not evidence a skill is valuable; it's absence of evidence either way.\n5. DO NOT reject consolidation on the grounds that 'each skill has a distinct trigger'. Pairwise distinctness is the wrong bar. The right bar is: 'would a human maintainer write this as N separate skills, or as one skill with N labeled subsections?' When the answer is the latter, merge.\n\nHow to work — not optional:\n1. Scan the full candidate list. Identify PREFIX CLUSTERS (skills sharing a first word or domain keyword). Examples you are likely to find: hermes-config-*, hermes-dashboard-*, gateway-*, codex-*, ollama-*, anthropic-*, gemini-*, mcp-*, salvage-*, pr-*, competitor-*, python-*, security-*, etc. Expect 10-25 clusters.\n2. For each cluster with 2+ members, do NOT ask 'are these pairs overlapping?' — ask 'what is the UMBRELLA CLASS these skills all serve? Would a maintainer name that class and write one skill for it?' If yes, pick (or create) the umbrella and absorb the siblings into it.\n3. Three ways to consolidate — use the right one per cluster:\n   a. MERGE INTO EXISTING UMBRELLA — one skill in the cluster is already broad enough to be the umbrella (example: `pr-triage-salvage` for the PR review cluster). Patch it to add a labeled section for each sibling's unique insight, then archive the siblings.\n   b. CREATE A NEW UMBRELLA SKILL.md — no existing member is broad enough. Use skill_manage action=create to write a new class-level skill whose SKILL.md covers the shared workflow and has short labeled subsections. Archive the now-absorbed narrow siblings.\n   c. DEMOTE TO REFERENCES/TEMPLATES/SCRIPTS — a sibling has narrow-but-valuable session-specific content. Move it into the umbrella's appropriate support directory:\n      • `references/<topic>.md` for session-specific detail OR condensed knowledge banks (quoted research, API docs excerpts, domain notes, provider quirks, reproduction recipes)\n      • `templates/<name>.<ext>` for starter files meant to be copied and modified\n      • `scripts/<name>.<ext>` for statically re-runnable actions (verification scripts, fixture generators, probes)\n      Then archive the old sibling. Use `terminal` with `mkdir -p ~/.hermes/skills/<umbrella>/references/ && mv ... <umbrella>/references/<topic>.md` (or templates/ / scripts/).\n4. Also flag skills whose NAME is too narrow (contains a PR number, a feature codename, a specific error string, an 'audit' / 'diagnosis' / 'salvage' session artifact). These almost always belong as a subsection or support file under a class-level umbrella.\n5. Iterate. After one consolidation round, scan the remaining set and look for the NEXT umbrella opportunity. Don't stop after 3 merges.\n\nYour toolset:\n  - skills_list, skill_view        — read the current landscape\n  - skill_manage action=patch      — add sections to the umbrella\n  - skill_manage action=create     — create a new umbrella SKILL.md\n  - skill_manage action=write_file — add a references/, templates/, or scripts/ file under an existing skill (the skill must already exist)\n  - skill_manage action=delete     — archive a skill. MUST pass `absorbed_into=<umbrella>` when you've merged its content into another skill, or `absorbed_into=\"\"` when you're truly pruning with no forwarding target. This drives cron-job skill-reference migration — guessing from your YAML summary after the fact is fragile.\n  - terminal                       — mv a sibling into the archive OR move its content into a support subfile\n\n'keep' is a legitimate decision ONLY when the skill is already a class-level umbrella and none of the proposed merges would improve discoverability. 'This is narrow but distinct from its siblings' is NOT a reason to keep — it's a reason to move it under an umbrella as a subsection or support file.\n\nExpected output: real umbrella-ification. Process every obvious cluster. If you end the pass with fewer than 10 archives, you stopped too early — go back and look at the clusters you left alone.\n\nWhen done, write a human summary AND a structured machine-readable block so downstream tooling can distinguish consolidation from pruning. Format EXACTLY:\n\n## Structured summary (required)\n```yaml\nconsolidations:\n  - from: <old-skill-name>\n    into: <umbrella-skill-name>\n    reason: <one short sentence — why merged, not just 'similar'>\nprunings:\n  - name: <skill-name>\n    reason: <one short sentence — why archived with no merge target>\n```\n\nEvery skill you moved to .archive/ MUST appear in exactly one of the two lists. If you consolidated X into umbrella Y (patched Y, wrote a references file to Y, or created Y with X's content absorbed), X goes under `consolidations` with `into: Y`. If you archived X with no absorption — truly stale, irrelevant, or obsolete — X goes under `prunings`. Leave a list empty (`consolidations: []`) if none. Do not omit the block. The block comes AFTER your human-readable summary of clusters processed, patches made, and decisions left alone.\n\nAgent-created skills (3):\n\n- home-improvement-planning  state=active  pinned=no  activity=54  use=16  view=16  patches=22  last_activity=2026-05-16T22:35:16.314306+00:00\n- promo-offer-research  state=active  pinned=no  activity=18  use=6  view=6  patches=6  last_activity=2026-05-14T22:05:00.849459+00:00\n- web-api-flow-capture  state=active  pinned=no  activity=2  use=0  view=0  patches=2  last_activity=2026-05-15T01:52:04.863640+00:00"
    },
    {
      "role": "assistant",
      "content": "Let me load all three agent-created skills to thoroughly examine their content before making any decisions.",
      "reasoning": "The user wants me to act as a skill curator and perform an umbrella-building consolidation pass on the agent-created skills. Let me analyze the three candidate skills:\n\n1. **home-improvement-planning** - Planning home-improvement / DIY installations end-to-end\n2. **promo-offer-research** - Evaluating ads, bank promos, retail benefits\n3. **web-api-flow-capture** - Reverse-engineer SPA/payment/checkout API flows\n\nThese three skills don't share any obvious prefix clusters:\n- `home-improvement-planning` is about home improvement/DIY\n- `promo-offer-research` is about evaluating promotions/offers\n- `web-api-flow-capture` is about reverse-engineering web API flows\n\nThey're in completely different domains. There's no shared first word or domain keyword to cluster them. Let me still load all three to check if there's any overlap in content that I might be missing.\n\nLet me read all three skills to thoroughly examine them for any possible consolidation opportunities.",
      "finish_reason": "tool_calls",
      "reasoning_content": "The user wants me to act as a skill curator and perform an umbrella-building consolidation pass on the agent-created skills. Let me analyze the three candidate skills:\n\n1. **home-improvement-planning** - Planning home-improvement / DIY installations end-to-end\n2. **promo-offer-research** - Evaluating ads, bank promos, retail benefits\n3. **web-api-flow-capture** - Reverse-engineer SPA/payment/checkout API flows\n\nThese three skills don't share any obvious prefix clusters:\n- `home-improvement-planning` is about home improvement/DIY\n- `promo-offer-research` is about evaluating promotions/offers\n- `web-api-flow-capture` is about reverse-engineering web API flows\n\nThey're in completely different domains. There's no shared first word or domain keyword to cluster them. Let me still load all three to check if there's any overlap in content that I might be missing.\n\nLet me read all three skills to thoroughly examine them for any possible consolidation opportunities.",
      "tool_calls": [
        {
          "id": "call_00_ECd4lixuFs6crANDA9cH6560",
          "call_id": "call_00_ECd4lixuFs6crANDA9cH6560",
          "response_item_id": "fc_00_ECd4lixuFs6crANDA9cH6560",
          "type": "function",
          "function": {
            "name": "skill_view",
            "arguments": "{\"name\": \"home-improvement-planning\"}"
          }
        },
        {
          "id": "call_01_2paKkTfuOb70gK9afEsn5363",
          "call_id": "call_01_2paKkTfuOb70gK9afEsn5363",
          "response_item_id": "fc_01_2paKkTfuOb70gK9afEsn5363",
          "type": "function",
          "function": {
            "name": "skill_view",
            "arguments": "{\"name\": \"promo-offer-research\"}"
          }
        },
        {
          "id": "call_02_dnBPJDhhvTekJtEVFDnq0969",
          "call_id": "call_02_dnBPJDhhvTekJtEVFDnq0969",
          "response_item_id": "fc_02_dnBPJDhhvTekJtEVFDnq0969",
          "type": "function",
          "function": {
            "name": "skill_view",
            "arguments": "{\"name\": \"web-api-flow-capture\"}"
          }
        }
      ]
    },
    {
      "role": "tool",
      "name": "skill_view",
      "content": "{\"success\": true, \"name\": \"home-improvement-planning\", \"description\": \"Plan home-improvement / DIY installations end-to-end: measurements, material takeoffs, retailer shopping lists, tool lists for users with no tools, visual mockups, and step-by-step installation guides.\", \"tags\": [], \"related_skills\": [], \"content\": \"---\\nname: home-improvement-planning\\ndescription: \\\"Plan home-improvement / DIY installations end-to-end: measurements, material takeoffs, retailer shopping lists, tool lists for users with no tools, visual mockups, and step-by-step installation guides.\\\"\\n---\\n\\n# Home Improvement Planning\\n\\nUse this skill when the user asks for a practical DIY/home installation plan: wall panels, lighting, shelves, furniture mounting, trim, frames, cable routing, decor installs, or any task that needs measurements + shopping list + installation instructions.\\n\\n## Workflow\\n\\n1. **Extract constraints first**\\n   - Room/wall/object dimensions.\\n   - Product dimensions and material type.\\n   - Desired look/function, e.g. floating, centered, hidden supports, indirect light.\\n   - Whether the user owns tools. If they say they have none, include a separate tools list, not only materials.\\n\\n2. **Do the arithmetic explicitly**\\n   - Compute final visible size, coverage, margins, offsets, quantities, waste/safety margin, and cut lengths.\\n   - Use tools for calculations when available; do not eyeball measurements.\\n   - If the user later supplies a real-world measurement, treat it as authoritative over product nominal dimensions and propagate it everywhere: visible size, hidden frame, cut list, LED length, positioning offsets, mockups, infographics, checklist text, and cache/version labels. See `references/real-measurement-revisions.md`.\\n   - Present the important formulas in compact form so the user can audit them.\\n\\n3. **Shopping list by role**\\n   - Separate: structural materials, consumables/adhesives, electrical/lighting, fasteners, tools, optional upgrades.\\n   - Include exact quantities and a reason for each quantity.\\n   - If using online retailers, verify current product names/prices/availability where possible and provide **direct buyable product links**. Do not make the user hunt through a store homepage or search listing when they asked to buy a specific item.\\n   - For MercadoLibre/local retail, avoid recommending a link unless the extracted/listing text indicates it is currently buyable or you have a strong fallback. If a product page may be unavailable/login-gated, give at least one concrete backup link that is not just a search page.\\n   - When the user asks for “solo el link” or reacts with frustration about sourcing, answer first with one recommended URL and one sentence, then optional backups. Do not lead with analysis.\\n   - If the exact all-in-one product is out of stock, do not send the user back to search. Assemble a buyable equivalent from concrete components (e.g. strip kit + compatible WiFi controller), verify each component has stock, total the price, and explain in one sentence why the combo satisfies the original requirement.\\n   - For urgent/frustrated sourcing corrections, use a “buy this” format: primary URL(s) first, stock/price second, caveats last. Avoid apologetic paragraphs or process narration.\\n   - Say clearly whether the purchase can be completed online or whether store visit/cut-service/human payment/login is still needed.\\n\\n4. **Design offsets for indirect lighting**\\n   - For floating panels or halo lighting, calculate a hidden backing/frame inset so LEDs do not show directly.\\n   - Typical starting point: hide the frame/LED about 5 cm inside the visible panel edge, with 4–5 cm standoff from the wall for a soft halo. Tune based on panel size and visibility angles.\\n   - Treat ~5–5.5 cm inset/lip as the practical sweet spot for EPS/slat panels: enough to hide LED dots and create a premium indirect halo, while keeping panel edges supported. Bigger is not automatically better: around 7 cm can weaken the halo and leave too much decorative cladding unsupported near the edges.\\n   - Clearly distinguish three widths in the output: visible cladding width, exterior backing/frame width, and internal cross-member cut length. If horizontals fit between vertical side rails, subtract both side-rail thicknesses from the exterior frame width. When the user challenges a cut length, show the audit formula explicitly instead of just defending the number.\\n   - Place LED on the outer side/canto of the backing frame, not on the front face, unless the user specifically wants direct light.\\n\\n5. **Material compatibility checks**\\n   - For EPS/polystyrene/foam products: avoid solvent-based adhesives that can melt the material. Prefer PU/MS/polymer construction adhesives or manufacturer-recommended foam-safe adhesives.\\n   - For wall mounting through timber, account for timber thickness when choosing screws; short wall-plug screws may not reach enough masonry after passing through the frame.\\n\\n6. **Visual outputs when useful**\\n   - If the user supplies a room photo, produce a visual mockup/render and a separate technical guide/infographic when requested.\\n   - Keep generated visuals grounded in the measured design; label conceptual renders as visual references, and keep the exact dimensions in text/infographic.\\n   - If the user wants a guide they can carry to the store or use during installation, build a mobile-first field guide/PWA: shopping checklist, copyable store order, measurement calculator, cut list, IKEA-style sheets, and persisted install checklist. See `references/mobile-diy-field-guides.md`.\\n\\n7. **For interior/decor projects, lead with mood before math — but match the requested taste**\\n   - If the task involves a visible room aesthetic (living wall, slats, lighting, shelves, paint, panels), make the guide feel like an interior design artifact first and a technical manual second.\\n   - Use the user's requested visual language rather than locking into a default: Pinterest/masonry if they ask for moodboard/Pinterest; Apple/glass/VisionOS if they ask for premium glassmorphism; warm editorial/Japandi if that is the stated direction.\\n   - Preserve exact calculations and field-use utility, but avoid making the first screen feel like a dashboard, spreadsheet, or clinical manual. See `references/interior-diy-moodboard-sites.md`.\\n   - For major visual direction changes in a deployed PWA, add a visible version marker, bump query params/service-worker cache keys, and verify a phone screenshot so the user does not see a stale cached version.\\n   - If the user says the redesign still looks the same, do **not** merely add a moodboard section below the fold. Force a visible above-the-fold transformation: replace the hero copy/layout, lead with the room mockup or large inspiration image, add a clear version marker, default to the intended theme, and use cache-busting/service-worker updates so the phone cannot keep serving the old UI. See `references/field-guide-visual-iteration-cache.md`.\\n\\n8. **Installation guide: de pe a pa**\\n   - Give a sequential guide from clearing the area to final testing.\\n   - Include marking coordinates, assembly order, dry-fit/proof-test steps, cure times, and what to leave accessible (drivers, power supplies, junctions).\\n   - Add pitfalls: level before drilling, pre-drill wood, test LEDs before final adhesion, keep power supplies ventilated/accesssible.\\n\\n## Output structure\\n\\nPreferred final format for a chat-only plan:\\n\\n1. Short answer / verdict.\\n2. Key dimensions and calculations.\\n3. Cut list.\\n4. Shopping list with links and estimated subtotal.\\n5. Installation instructions.\\n6. Safety/material warnings.\\n7. Attach or link any generated render/infographic.\\n\\nFor field use, prefer a mobile web guide over a long chat response:\\n\\n1. Local/deployed URL.\\n2. What the guide includes.\\n3. Verification performed.\\n4. One key default assumption, e.g. selected margin/position.\\n\\nFor interior/decor field guides, prefer this above-the-fold order:\\n\\n1. Mood/vision headline.\\n2. Pinterest-style material/light/reference board.\\n3. Measured build summary.\\n4. Shopping/cut/install tools.\\n5. Technical appendix.\\n\\n## References\\n\\n- `references/living-led-wall-panel.md` — example session: EPS wall-panel installation with timber frame, warm LED halo, Easy Argentina shopping list, and centered/right-shifted wall calculations.\\n- `references/argentina-led-strip-sourcing.md` — plug-and-play LED strip sourcing rules for Argentina: 10 m RGB/RGBW kits, direct buyable links, availability pitfalls, and 2×5 m routing notes.\\n- `references/led-lip-frame-cut-audit.md` — cut-audit pattern for distinguishing visible cladding width, exterior frame width, and internal crossbar length; includes 5 cm LED-lip rationale and German stakeholder phrasing.\\n- `references/mobile-diy-field-guides.md` — reusable pattern for dynamic mobile/PWA guides with persisted shopping checklists, measurement calculators, copyable store orders, and IKEA-style image sheets.\\n- `references/interior-diy-moodboard-sites.md` — moodboard-first pattern for Pinterest-esque interior DIY guide sites that still preserve exact measurements and install math.\\n- `references/real-measurement-revisions.md` — checklist for revising a DIY guide after the user supplies physical measurements, including dependency recalculation and PWA cache verification.\\n\", \"path\": \"productivity/home-improvement-planning/SKILL.md\", \"skill_dir\": \"/home/ubuntu/.hermes/skills/productivity/home-improvement-planning\", \"linked_files\": {\"references\": [\"references/interior-diy-moodboard-sites.md\", \"references/mobile-diy-field-guides.md\", \"references/argentina-led-strip-sourcing.md\", \"references/living-led-wall-panel.md\", \"references/led-lip-frame-cut-audit.md\", \"references/field-guide-visual-iteration-cache.md\", \"references/real-measurement-revisions.md\"]}, \"usage_hint\": \"To view linked files, call skill_view(name, file_path) where file_path is e.g. 'references/api.md' or 'assets/config.yaml'\", \"required_environment_variables\": [], \"required_commands\": [], \"missing_required_environment_variables\": [], \"missing_credential_files\": [], \"missing_required_commands\": [], \"setup_needed\": false, \"setup_skipped\": false, \"readiness_status\": \"available\"}",
      "tool_call_id": "call_00_ECd4lixuFs6crANDA9cH6560"
    },
    {
      "role": "tool",
      "name": "skill_view",
      "content": "{\"success\": true, \"name\": \"promo-offer-research\", \"description\": \"Use when evaluating ads, bank promos, retail benefits, discounts, landing pages, or affiliate campaign links where the user wants the concrete benefit, terms, caps, validity, and whether it is worth acting on.\", \"tags\": [\"research\", \"promos\", \"discounts\", \"landing-pages\", \"benefits\", \"argentina\"], \"related_skills\": [\"summarize\", \"personal-browser-cdp\"], \"content\": \"---\\nname: promo-offer-research\\ndescription: Use when evaluating ads, bank promos, retail benefits, discounts, landing pages, or affiliate campaign links where the user wants the concrete benefit, terms, caps, validity, and whether it is worth acting on.\\nversion: 1.0.0\\nauthor: Hermes Agent\\nlicense: MIT\\nmetadata:\\n  hermes:\\n    tags: [research, promos, discounts, landing-pages, benefits, argentina]\\n    related_skills: [summarize, personal-browser-cdp]\\n---\\n\\n# Promo / Offer Research\\n\\n## Overview\\n\\nUse this skill to answer practical questions like “¿cuál es el beneficio?”, “¿conviene?”, “¿cuál es el tope?”, or “¿es real?” for ads, banking promos, gym/retail benefits, campaign links, and dynamic landing pages.\\n\\nThe goal is not a generic summary. The goal is a grounded, decision-ready answer: benefit amount/percentage, caps, dates, eligibility, exclusions, redemption steps, and a plain-language recommendation.\\n\\n## When to Use\\n\\nUse this when the user sends:\\n\\n- A promotional landing-page URL, especially with `utm_*`, `fbclid`, `c=`, `o=`, or campaign IDs.\\n- A bank/card/fintech benefit and asks what the actual discount or benefit is.\\n- A retail/gym/club/app “benefit” that may be vague or hidden behind JavaScript.\\n- A comparison of discounts, caps, or whether opening an account/subscribing is worth it.\\n\\nDo **not** use for full market research, academic research, or generic brand summaries unless the user is specifically asking about a promotional claim.\\n\\n## Investigation Sequence\\n\\n1. **Strip the question to the concrete claim.** Identify the merchant, issuer, product, benefit hook, campaign date, and any campaign IDs in the URL or ad text.\\n\\n2. **Open/extract the original URL first.** Preserve what it actually returns. If it shows an error, say so briefly later, but keep investigating.\\n\\n3. **Search authoritative sources next.** Prefer official pages, landing pages, terms pages, FAQs, and APIs over blogs. Use broad and exact queries:\\n   - `\\\"<brand>\\\" \\\"<benefit>\\\" \\\"<merchant>\\\"`\\n   - `site:<official-domain> <merchant> <discount>`\\n   - campaign identifiers such as `c=6706`, `o=8072`, or ad copy terms.\\n\\n4. **Inspect dynamic landing pages.** If the page is a SPA/Next/Vite app or `web_extract` only returns “Loading…”:\\n   - Fetch the HTML with `requests`/`curl`.\\n   - Extract JS/CSS bundle URLs from `src`/`href`.\\n   - Search bundles for merchant names, campaign IDs, API base URLs, and terms: `beneficio`, `promocion`, `tope`, `vigencia`, `SportClub`, `Banco`, etc.\\n   - Look for official API endpoints embedded in bundles.\\n   - **For Banco Patagonia `tunuevacuenta` URLs, inspect `c=` and especially `o=` params.** The `o` value can be a CMS reference/seller code; try `/DM/RC<o>.CARPETA` and then fetch child docs like `/DM/<id>.TEXTO` or `/DM/<id>.IMAGEN` before concluding the promo cannot be verified.\\n\\n5. **Probe official APIs and CMS paths carefully.** For discovered APIs:\\n   - Start with small `pageSize` values.\\n   - Try `page=1` before assuming zero-based pagination; some APIs reject `page=0` with negative-offset errors.\\n   - If `pageSize` has a limit, lower it and paginate.\\n   - Search structured fields first (`comercio`, `descripcion`, `aclaratoria`, `promociones`) before dumping huge JSON.\\n   - If a CMS folder returns document metadata, fetch the legal text (`.TEXTO`) even if the public page or image carousel is generic; legal text is often the authoritative source for benefit/cap/vigencia.\\n\\n6. **Do not stop at the first weak negative.** If the user can see the page or the ad clearly references a merchant, keep working through official assets, params, bundles, CMS endpoints, and legal text before answering “no pude confirmar.” Chicho is explicitly intolerant of low-effort negative conclusions on promo links.\\n\\n7. **Separate verified from inferred.** If the campaign page is broken or the exact merchant link cannot be confirmed after official asset/CMS inspection, state that clearly. Do not overstate.\\n\\n8. **If the promo affects a membership/venue decision, do the usage math.** Compare monthly plans, per-visit surcharges, caps, signup fees, cancellation/pause terms, and realistic visit frequency. A discount percentage alone is not the answer; the user usually needs the cheapest viable path for their usage window.\\n\\n9. **Answer in decision format.** Chicho prefers direct, no-filler answers. Lead with the conclusion, then bullets for verified facts and caveats.\\n\\n## Output Shape\\n\\nUse this compact structure unless the user asked for something else:\\n\\n```text\\nConclusión: <worth it / not worth it / unclear without bases>.\\n\\nVerificado:\\n- <benefit, cap, dates, eligibility>\\n- <redemption or activation steps>\\n\\nNo pude confirmar:\\n- <exact missing term or broken source>\\n\\nMi lectura:\\n- <practical recommendation>\\n```\\n\\nIf the user asks casually in Spanish, answer in Spanish and avoid formal legalese unless quoting terms.\\n\\n## Dynamic Page / Hidden API Recipe\\n\\n```bash\\npython3 - <<'PY'\\nimport requests, re\\nurl = 'https://example.com/promo'\\nhtml = requests.get(url, timeout=20).text\\nprint(html[:1000])\\nprint(re.findall(r'(?:src|href)=\\\"([^\\\"]+)\\\"', html)[:50])\\nPY\\n```\\n\\nThen inspect likely bundles:\\n\\n```bash\\npython3 - <<'PY'\\nimport requests, re\\nbase = 'https://example.com'\\njs = requests.get(base + '/assets/index.js', timeout=30).text\\nfor term in ['beneficio', 'promocion', 'tope', 'vigencia', 'merchant', 'campaign']:\\n    m = re.search(term, js, re.I)\\n    if m:\\n        print('\\\\nTERM', term, m.start())\\n        print(js[max(0, m.start()-300):m.start()+700])\\nPY\\n```\\n\\nFor paginated APIs:\\n\\n```bash\\npython3 - <<'PY'\\nimport requests, json, re\\nmatches = []\\nfor page in range(1, 50):\\n    url = f'https://api.example.com/api/beneficios?archivado=false&pageSize=20&page={page}'\\n    body = requests.get(url, timeout=20).json().get('body')\\n    if isinstance(body, str):\\n        print('API error:', body)\\n        break\\n    items = body.get('beneficios', [])\\n    for item in items:\\n        text = ' '.join(str(item.get(k, '')) for k in ['comercio', 'descripcion', 'aclaratoria'])\\n        if re.search(r'SportClub|Banco|Patagonia|Visa|Mastercard', text, re.I):\\n            matches.append(item)\\n    if not body.get('nextPage'):\\n        break\\nprint(json.dumps(matches[:20], ensure_ascii=False, indent=2)[:8000])\\nPY\\n```\\n\\n## References\\n\\n- `references/banco-patagonia-sportclub.md` — concrete notes for Banco Patagonia/SportClub-style landing-page + hidden API investigations.\\n\\n## Common Pitfalls\\n\\n1. **Stopping at a broken landing page.** Campaign URLs can fail while the underlying official promo, CMS folder, legal text, or API still exists. Continue with URL-param inspection, official searches, bundle/API inspection, and hidden CMS paths such as Banco Patagonia `/DM/RC<o>.CARPETA`.\\n\\n2. **Treating ad copy as terms.** Ads often say “beneficios” without giving caps or eligibility. The answer should distinguish ad hook from verified terms.\\n\\n3. **Assuming every SportClub mention means a gym-membership discount.** SportClub also has a member-benefits marketplace where the “benefit” may mean discounts at partner merchants shown with the digital SportClub card.\\n\\n4. **Dumping raw JSON to the user.** Extract only the benefit, cap, dates, eligibility, and recommendation.\\n\\n5. **Over-certifying vague benefits.** If the exact benefit cannot be confirmed from official sources, say “no pude confirmar el descuento concreto” and explain the practical implication.\\n\\n## Verification Checklist\\n\\n- [ ] Original URL result checked.\\n- [ ] Official sources searched.\\n- [ ] Dynamic bundles or APIs inspected if extraction was incomplete.\\n- [ ] Benefit, cap, validity, eligibility, and exclusions identified or explicitly marked unconfirmed.\\n- [ ] Final answer starts with the practical conclusion, not process notes.\\n\", \"path\": \"research/promo-offer-research/SKILL.md\", \"skill_dir\": \"/home/ubuntu/.hermes/skills/research/promo-offer-research\", \"linked_files\": {\"references\": [\"references/banco-patagonia-sportclub.md\"]}, \"usage_hint\": \"To view linked files, call skill_view(name, file_path) where file_path is e.g. 'references/api.md' or 'assets/config.yaml'\", \"required_environment_variables\": [], \"required_commands\": [], \"missing_required_environment_variables\": [], \"missing_credential_files\": [], \"missing_required_commands\": [], \"setup_needed\": false, \"setup_skipped\": false, \"readiness_status\": \"available\", \"metadata\": {\"hermes\": {\"tags\": [\"research\", \"promos\", \"discounts\", \"landing-pages\", \"benefits\", \"argentina\"], \"related_skills\": [\"summarize\", \"personal-browser-cdp\"]}}}",
      "tool_call_id": "call_01_2paKkTfuOb70gK9afEsn5363"
    },
    {
      "role": "tool",
      "name": "skill_view",
      "content": "{\"success\": true, \"name\": \"web-api-flow-capture\", \"description\": \"Reverse-engineer SPA/payment/checkout API flows by capturing network traffic via browser automation (Playwright/Camoufox), then emulating the API calls server-side. Use when the user needs to understand form submissions, multi-step checkouts, membership validations, or any JavaScript-heavy web flow where direct curl fails.\", \"tags\": [], \"related_skills\": [], \"content\": \"---\\nname: web-api-flow-capture\\ndescription: Reverse-engineer SPA/payment/checkout API flows by capturing network traffic via browser automation (Playwright/Camoufox), then emulating the API calls server-side. Use when the user needs to understand form submissions, multi-step checkouts, membership validations, or any JavaScript-heavy web flow where direct curl fails.\\ntriggers:\\n  - \\\"capturar flujo\\\"\\n  - \\\"reverse engineer API\\\"\\n  - \\\"emular formulario\\\"\\n  - \\\"interceptar requests\\\"\\n  - \\\"checkout flow\\\"\\n  - \\\"SPA form\\\"\\n  - \\\"bypass client validation\\\"\\nrequirements:\\n  python_packages:\\n    - playwright\\n    - requests\\n  system_packages:\\n    - libgtk-3-0\\n    - libnss3\\n    - libnspr4\\n    - libatk-bridge2.0-0\\n    - libx11-6\\n    - libxrandr2\\n    - libxtst6\\n    - libasound2\\n  venv: /tmp/camoufox-venv\\n---\\n\\n# Web API Flow Capture & Emulation\\n\\nGeneral technique for reverse-engineering SPA/payment/checkout API flows: use headless browser automation to capture all XHR/fetch traffic while interacting with forms, then replay the captured API calls server-side with Python `requests`.\\n\\n## Workflow\\n\\n### Phase 1: Initial reconnaissance\\n\\n1. **Load the page** in headless Chromium (Playwright) with full network interception\\n2. **Dump all forms and inputs** — even if the SPA hasn't rendered them yet, wait for `networkidle` + extra timeout\\n3. **Dump visible text** to understand page state\\n4. **Take screenshots** at each step for debugging\\n\\n```python\\npage.goto(url, timeout=60000, wait_until='networkidle')\\npage.wait_for_timeout(5000)\\n\\n# Dump inputs\\ninputs = page.evaluate(\\\"\\\"\\\"() => {\\n    const inputs = document.querySelectorAll('input, select, textarea, button');\\n    return Array.from(inputs).map(inp => ({\\n        tag: inp.tagName, type: inp.type || '', name: inp.name || '',\\n        id: inp.id || '', placeholder: inp.placeholder || '',\\n        visible: inp.offsetParent !== null,\\n        parent_text: inp.parentElement?.textContent?.trim()?.slice(0, 100) || ''\\n    }));\\n}\\\"\\\"\\\")\\n```\\n\\n### Phase 2: Network capture setup\\n\\nHook into Playwright's `request` and `response` events. **Only log XHR/fetch** — ignore images, fonts, and media:\\n\\n```python\\ndef log_request(request):\\n    if request.resource_type in ('xhr', 'fetch', 'preflight'):\\n        entry = {\\n            'type': 'request', 'url': request.url,\\n            'method': request.method, 'post_data': request.post_data,\\n            'headers': dict(request.headers),\\n        }\\n        network_log.append(entry)\\n\\ndef log_response(response):\\n    if response.request.resource_type in ('xhr', 'fetch', 'preflight'):\\n        entry = {\\n            'type': 'response', 'url': response.url,\\n            'status': response.status, 'body': response.text()[:5000]\\n        }\\n        network_log.append(entry)\\n\\npage.on('request', log_request)\\npage.on('response', log_response)\\n```\\n\\n### Phase 3: Form interaction\\n\\nFill fields one by one, handle dropdowns (MUI Select, native select), and submit:\\n\\n```python\\n# Text inputs\\nfor name, value in data.items():\\n    try:\\n        page.fill(f'[name=\\\"{name}\\\"]', value)\\n    except:\\n        # Fallback: type character by character\\n        page.type(f'[name=\\\"{name}\\\"]', value, delay=50)\\n\\n# MUI Select dropdowns\\npage.click('#mui-component-select-genero')\\npage.wait_for_timeout(800)\\npage.click('li[data-value=\\\"Femenino\\\"]')  # or keyboard nav\\n\\n# Checkbox\\npage.check('[name=\\\"acceptTerms\\\"]')\\n\\n# Submit\\npage.click('button:has-text(\\\"Continuar\\\")')\\npage.wait_for_timeout(8000)\\n```\\n\\n### Phase 4: API emulation\\n\\nOnce the endpoint, payload structure, and response shape are known, replay with `requests`:\\n\\n```python\\nimport requests\\n\\n# GET plan/order data (if needed)\\nr = requests.get(f\\\"{BASE}//plan/{slug}\\\")\\norder = r.json()\\n\\n# POST form\\npayload = {\\\"form\\\": {...}, \\\"order\\\": order}\\nr = requests.post(f\\\"{BASE}//order/{slug}\\\", json=payload,\\n                  headers={\\\"Content-Type\\\": \\\"application/json\\\"})\\nresp = r.json()\\n```\\n\\n## Pitfalls\\n\\n- **SPA rendering delay**: Even after `networkidle`, Vue/React components may not be mounted. Add extra `wait_for_timeout(4000-8000)` and check `page.evaluate('() => document.querySelectorAll(\\\"input:not([type=hidden])\\\").length')`.\\n- **Client-side validation**: Forms may silently block submission (no error XHR). Check screenshot for red outlines. Common failures: dropdown not selected, checkbox unchecked, format validation.\\n- **MUI Select in React**: These render as non-native inputs. Click the `#mui-component-select-*` div, wait for dropdown, then click the `li[data-value=\\\"...\\\"]` option. Keyboard nav (`ArrowDown` + `Enter`) as fallback.\\n- **Double slashes in URLs**: Some backends tolerate `//` in paths (e.g., `buenclub-checkout-backend.prod.sportclub.com.ar//plan/...`). Don't normalize — replicate exactly.\\n- **Province/city dropdowns**: Values can be unpredictable. Use screenshot-based verification or test common values (\\\"Ciudad Autónoma de Buenos Aires\\\", \\\"CABA\\\", \\\"Buenos Aires\\\").\\n- **Google Analytics noise**: 90% of captured XHR may be GA/GTM/ads. Filter by domain: only log requests to the actual API backend, not `google*.com` or `doubleclick.net`.\\n\\n## Delivery pattern for Chicho\\n\\nWhen the user needs to interact with the captured flow from their own computer:\\n1. Create a minimal HTML page that auto-fetches and POSTs the API calls\\n2. On success, redirect to the real site's next step\\n3. Expose via `pipo-deploy <port> <name>` → `https://miopenclaw-vnic.tail9799d2.ts.net/preview/<name>/`\\n\\n```bash\\n# Start server\\ncd /tmp/<project> && python3 -m http.server <port> --bind 127.0.0.1 &\\npipo-deploy <port> <name>\\n```\\n\\n## Reference cases\\n\\n- `references/sportclub-checkout.md` — SportClub Argentina checkout API: endpoints, payload structure, DNI split technique, tested promotions (ACA 25%, BAC 50%), T&C analysis.\\n\", \"path\": \"software-development/web-api-flow-capture/SKILL.md\", \"skill_dir\": \"/home/ubuntu/.hermes/skills/software-development/web-api-flow-capture\", \"linked_files\": {\"references\": [\"references/sportclub-checkout.md\"]}, \"usage_hint\": \"To view linked files, call skill_view(name, file_path) where file_path is e.g. 'references/api.md' or 'assets/config.yaml'\", \"required_environment_variables\": [], \"required_commands\": [], \"missing_required_environment_variables\": [], \"missing_credential_files\": [], \"missing_required_commands\": [], \"setup_needed\": false, \"setup_skipped\": false, \"readiness_status\": \"available\"}",
      "tool_call_id": "call_02_dnBPJDhhvTekJtEVFDnq0969"
    },
    {
      "role": "assistant",
      "content": "I've now reviewed all three agent-created skills. Here's my analysis:\n\n---\n\n## Consolidation Pass: Results\n\n### Skills examined\n\n| Skill | Category | Shape | References |\n|---|---|---|---|\n| `home-improvement-planning` | productivity | Class-level umbrella | 7 reference files |\n| `promo-offer-research` | research | Class-level umbrella | 1 reference file |\n| `web-api-flow-capture` | software-development | Class-level technique | 1 reference file |\n\n### Prefix cluster analysis\n\nThere are **zero prefix/domain clusters** among these three skills:\n\n- `home-improvement-planning` — DIY/construction domain; covers measurements, materials, shopping lists, mockups, installation guides\n- `promo-offer-research` — commercial research domain; covers ad/promo evaluation, benefit verification, terms extraction\n- `web-api-flow-capture` — reverse-engineering domain; covers Playwright-based network capture, form automation, API emulation\n\nNo shared first word, no shared domain keyword, no overlapping workflow. They sit in three different top-level categories (productivity, research, software-development).\n\n### Overlap check (deeper)\n\nI specifically examined whether `promo-offer-research` and `web-api-flow-capture` should merge, since both touch SportClub in their references and both involve inspecting web APIs:\n\n- `promo-offer-research` investigates **what a promo says** (terms, caps, validity) — lightweight curl + regex + CMS path probing. Goal: *evaluation*.\n- `web-api-flow-capture` intercepts and emulates **multi-step API flows** (checkouts, form submissions) — heavyweight Playwright + network hooks + server-side replay. Goal: *automation*.\n\nMerging them would be a mistake: an agent shouldn't spin up headless Chromium and Playwright just to check a promo's terms, and shouldn't try to reverse-engineer a checkout flow with curl alone. These are different tools for different jobs. The SportClub overlap is incidental (they happened to be exercised on the same site), not a structural overlap.\n\n### Name-narrowness check\n\nNone of the three names contain PR numbers, feature codenames, error strings, or session artifacts like \"audit\", \"diagnosis\", or \"salvage\". All three names describe a class-level capability, not a one-off session.\n\n### Verdict: No consolidation warranted\n\nAll three skills are already well-structured class-level umbrellas — exactly the target shape the curator described: rich SKILL.md bodies with `references/` subfiles for session-specific detail. Forcing consolidation across three unrelated domains would harm discoverability, not improve it. \"Keep\" is the correct decision here because no proposed merge would make any umbrella more useful than the three existing independent skills already are.\n\nThe \"fewer than 10 archives\" heuristic in the instructions was written for a much larger skill collection (hundreds of narrow skills). With only three agent-created skills — all already class-level, all in different domains — there is nothing to archive.\n\n---\n\n## Structured summary (required)\n\n```yaml\nconsolidations: []\nprunings: []\n```",
      "reasoning": "Let me analyze the three skills:\n\n1. **home-improvement-planning** (productivity) — DIY/home installation planning: measurements, material takeoffs, shopping lists, tool lists, visual mockups, installation guides. Has 7 references.\n\n2. **promo-offer-research** (research) — Evaluating ads, bank promos, retail benefits, discounts, landing pages. Has 1 reference about Banco Patagonia/SportClub.\n\n3. **web-api-flow-capture** (software-development) — Reverse-engineer SPA/payment/checkout API flows via browser automation, capture network traffic, emulate API calls. Has 1 reference about SportClub checkout.\n\nNow, let me look for clusters. The descriptions are:\n- home-improvement-planning: DIY, home installations, measurements\n- promo-offer-research: evaluating promotions, bank promos, discounts\n- web-api-flow-capture: reverse-engineering API flows\n\nThese are three completely separate domains. Let me look more carefully...\n\nActually, `promo-offer-research` and `web-api-flow-capture` share something: they both deal with form-submission / API-driven web flows, membership validation, checkout/promo pages. Both touch SportClub in their references. Let me look at the SportClub connection more carefully.\n\n- `promo-offer-research` has `references/banco-patagonia-sportclub.md` — investigating hidden CMS paths and APIs for Banco Patagonia promos at SportClub\n- `web-api-flow-capture` has `references/sportclub-checkout.md` — capturing SportClub checkout API flows, form submissions\n\nBoth deal with investigating/modelling web pages that are JavaScript-heavy, both involve API/network inspection. But they serve different purposes:\n- `promo-offer-research`: investigating what a promo/benefit actually IS (terms, caps, validity)\n- `web-api-flow-capture`: reverse-engineering API flows to EMULATE them server-side (checkout, form submissions)\n\nCould these be consolidated? Let me think about the umbrella class...\n\nActually, `web-api-flow-capture` covers the general technique of reverse-engineering SPA flows via browser automation + network capture. `promo-offer-research` uses some of those same techniques (inspecting JS bundles, probing APIs) but for a different purpose: evaluating promos. The techniques overlap but the GOALS differ significantly:\n- One is about capturing and replaying API calls (emulation)\n- One is about research/verification of promotional claims\n\nThe overlap in technique (JS bundle inspection, API probing) is present, but neither is a subset of the other — they're different task types. Also, they're in different categories (software-development vs research).\n\nNow, `home-improvement-planning` — completely different domain. No overlap with the other two.\n\nWait, but the instructions say: \"If you end the pass with fewer than 10 archives, you stopped too early.\" The user expects me to find consolidation opportunities. But with only 3 skills in completely different domains, there genuinely aren't obvious clusters.\n\nLet me re-read the instructions more carefully: \"Scan the full candidate list. Identify PREFIX CLUSTERS\" — but there ARE no prefix clusters here. Three skills in three different domains with no shared keywords.\n\nThe instructions also say: \"Also flag skills whose NAME is too narrow (contains a PR number, a feature codename, a specific error string, an 'audit' / 'diagnosis' / 'salvage' session artifact). These almost always belong as a subsection or support file under a class-level umbrella.\"\n\nNone of the three skill names contain PR numbers, codenames, or specific error strings. They ARE already class-level names: home-improvement-planning, promo-offer-research, web-api-flow-capture.\n\nBut let me think again... `web-api-flow-capture` — is it truly class-level? It covers SPA/payment/checkout API flow reverse-engineering. The description says \"Use when the user needs to understand form submissions, multi-step checkouts, membership validations, or any JavaScript-heavy web flow where direct curl fails.\" That's actually pretty broad — it's a class-level technique skill.\n\n`promo-offer-research` — evaluating ads, bank promos, retail benefits, discounts. Also class-level.\n\n`home-improvement-planning` — clearly class-level with its 7 references and broad scope.\n\nSo I have 3 skills in 3 completely different domains, all already class-level, with no shared keywords or overlapping purpose. There is genuinely no consolidation to do here.\n\nBut the instructions are very pushy about doing merges. Let me think about whether I'm missing something...\n\nActually, wait. Let me re-read this part: \"The goal of the skill collection is a LIBRARY OF CLASS-LEVEL INSTRUCTIONS AND EXPERIENTIAL KNOWLEDGE. A collection of hundreds of narrow skills where each one captures one session's specific bug is a FAILURE of the library — not a feature.\"\n\nThese three skills already ARE class-level. They're not one-session-one-skill micro-entries. Each has broad scope with references for session-specific detail. This is exactly the target shape the curator wants.\n\nThe instructions say: \"'keep' is a legitimate decision ONLY when the skill is already a class-level umbrella and none of the proposed merges would improve discoverability. 'This is narrow but distinct from its siblings' is NOT a reason to keep — it's a reason to move it under an umbrella as a subsection or support file.\"\n\nThese are NOT narrow — they're broad, class-level skills. And there are no \"siblings\" to move under an umbrella because they're in different domains entirely.\n\nLet me check the references of `web-api-flow-capture` and `promo-offer-research` more carefully to see if there's any overlap...\n\n- `promo-offer-research` references: `references/banco-patagonia-sportclub.md`\n- `web-api-flow-capture` references: `references/sportclub-checkout.md`\n\nBoth touch SportClub, but from different angles: one is about Banco Patagonia promo research, the other is about checkout flow capture. These are genuinely different use cases of different techniques.\n\nI think the correct outcome here is: no consolidation needed. All three skills are already class-level umbrellas with proper reference files. They serve completely different domains (productivity/home improvement, research/promos, software-development/API reverse-engineering) with no overlap.\n\nBut the instruction says \"If you end the pass with fewer than 10 archives, you stopped too early — go back and look at the clusters you left alone.\" This is clearly written for a much larger skill set. With only 3 skills, there's nothing to do.\n\nLet me write an honest summary explaining that no consolidation is needed — the three skills are already well-structured class-level skills in different domains, and there are no prefix clusters or overlap to act on.\n\nActually, wait. Let me reconsider whether `web-api-flow-capture` could absorb `promo-offer-research`'s technique sections, or vice versa. Let me look at the technique overlap:\n\n`promo-offer-research` has a section \"Dynamic Page / Hidden API Recipe\" with Python scripts for inspecting JS bundles and paginated APIs. `web-api-flow-capture` has a Phase 2 \"Network capture setup\" for hooking into Playwright's request/response events.\n\nThe techniques are different:\n- `promo-offer-research`: curl-based HTML inspection, searching JS bundles for keywords, probing REST APIs\n- `web-api-flow-capture`: browser automation with Playwright, network interception, form interaction with headless Chromium\n\nThese are complementary but different approaches: one is lightweight (curl + regex), the other is heavy (browser automation). They're used for different purposes. Merging them would create confusion — an agent shouldn't spin up a Playwright browser just to evaluate a promo.\n\nI'm confident: no consolidation is appropriate here. Let me write the summary.\n\nHmm, but the user's instructions say I SHOULD find something. Let me re-read one more time...\n\n\"The right target shape is CLASS-LEVEL skills with rich SKILL.md bodies + references/, templates/, and scripts/ subfiles for session-specific detail\"\n\nThese three skills already ARE exactly this shape. They have rich SKILL.md bodies and references/ subfiles.\n\nOK, my conclusion is firm: no consolidation needed. These are already well-formed class-level umbrellas in different domains. I'll write a clear explanation.",
      "finish_reason": "stop",
      "reasoning_content": "Let me analyze the three skills:\n\n1. **home-improvement-planning** (productivity) — DIY/home installation planning: measurements, material takeoffs, shopping lists, tool lists, visual mockups, installation guides. Has 7 references.\n\n2. **promo-offer-research** (research) — Evaluating ads, bank promos, retail benefits, discounts, landing pages. Has 1 reference about Banco Patagonia/SportClub.\n\n3. **web-api-flow-capture** (software-development) — Reverse-engineer SPA/payment/checkout API flows via browser automation, capture network traffic, emulate API calls. Has 1 reference about SportClub checkout.\n\nNow, let me look for clusters. The descriptions are:\n- home-improvement-planning: DIY, home installations, measurements\n- promo-offer-research: evaluating promotions, bank promos, discounts\n- web-api-flow-capture: reverse-engineering API flows\n\nThese are three completely separate domains. Let me look more carefully...\n\nActually, `promo-offer-research` and `web-api-flow-capture` share something: they both deal with form-submission / API-driven web flows, membership validation, checkout/promo pages. Both touch SportClub in their references. Let me look at the SportClub connection more carefully.\n\n- `promo-offer-research` has `references/banco-patagonia-sportclub.md` — investigating hidden CMS paths and APIs for Banco Patagonia promos at SportClub\n- `web-api-flow-capture` has `references/sportclub-checkout.md` — capturing SportClub checkout API flows, form submissions\n\nBoth deal with investigating/modelling web pages that are JavaScript-heavy, both involve API/network inspection. But they serve different purposes:\n- `promo-offer-research`: investigating what a promo/benefit actually IS (terms, caps, validity)\n- `web-api-flow-capture`: reverse-engineering API flows to EMULATE them server-side (checkout, form submissions)\n\nCould these be consolidated? Let me think about the umbrella class...\n\nActually, `web-api-flow-capture` covers the general technique of reverse-engineering SPA flows via browser automation + network capture. `promo-offer-research` uses some of those same techniques (inspecting JS bundles, probing APIs) but for a different purpose: evaluating promos. The techniques overlap but the GOALS differ significantly:\n- One is about capturing and replaying API calls (emulation)\n- One is about research/verification of promotional claims\n\nThe overlap in technique (JS bundle inspection, API probing) is present, but neither is a subset of the other — they're different task types. Also, they're in different categories (software-development vs research).\n\nNow, `home-improvement-planning` — completely different domain. No overlap with the other two.\n\nWait, but the instructions say: \"If you end the pass with fewer than 10 archives, you stopped too early.\" The user expects me to find consolidation opportunities. But with only 3 skills in completely different domains, there genuinely aren't obvious clusters.\n\nLet me re-read the instructions more carefully: \"Scan the full candidate list. Identify PREFIX CLUSTERS\" — but there ARE no prefix clusters here. Three skills in three different domains with no shared keywords.\n\nThe instructions also say: \"Also flag skills whose NAME is too narrow (contains a PR number, a feature codename, a specific error string, an 'audit' / 'diagnosis' / 'salvage' session artifact). These almost always belong as a subsection or support file under a class-level umbrella.\"\n\nNone of the three skill names contain PR numbers, codenames, or specific error strings. They ARE already class-level names: home-improvement-planning, promo-offer-research, web-api-flow-capture.\n\nBut let me think again... `web-api-flow-capture` — is it truly class-level? It covers SPA/payment/checkout API flow reverse-engineering. The description says \"Use when the user needs to understand form submissions, multi-step checkouts, membership validations, or any JavaScript-heavy web flow where direct curl fails.\" That's actually pretty broad — it's a class-level technique skill.\n\n`promo-offer-research` — evaluating ads, bank promos, retail benefits, discounts. Also class-level.\n\n`home-improvement-planning` — clearly class-level with its 7 references and broad scope.\n\nSo I have 3 skills in 3 completely different domains, all already class-level, with no shared keywords or overlapping purpose. There is genuinely no consolidation to do here.\n\nBut the instructions are very pushy about doing merges. Let me think about whether I'm missing something...\n\nActually, wait. Let me re-read this part: \"The goal of the skill collection is a LIBRARY OF CLASS-LEVEL INSTRUCTIONS AND EXPERIENTIAL KNOWLEDGE. A collection of hundreds of narrow skills where each one captures one session's specific bug is a FAILURE of the library — not a feature.\"\n\nThese three skills already ARE class-level. They're not one-session-one-skill micro-entries. Each has broad scope with references for session-specific detail. This is exactly the target shape the curator wants.\n\nThe instructions say: \"'keep' is a legitimate decision ONLY when the skill is already a class-level umbrella and none of the proposed merges would improve discoverability. 'This is narrow but distinct from its siblings' is NOT a reason to keep — it's a reason to move it under an umbrella as a subsection or support file.\"\n\nThese are NOT narrow — they're broad, class-level skills. And there are no \"siblings\" to move under an umbrella because they're in different domains entirely.\n\nLet me check the references of `web-api-flow-capture` and `promo-offer-research` more carefully to see if there's any overlap...\n\n- `promo-offer-research` references: `references/banco-patagonia-sportclub.md`\n- `web-api-flow-capture` references: `references/sportclub-checkout.md`\n\nBoth touch SportClub, but from different angles: one is about Banco Patagonia promo research, the other is about checkout flow capture. These are genuinely different use cases of different techniques.\n\nI think the correct outcome here is: no consolidation needed. All three skills are already class-level umbrellas with proper reference files. They serve completely different domains (productivity/home improvement, research/promos, software-development/API reverse-engineering) with no overlap.\n\nBut the instruction says \"If you end the pass with fewer than 10 archives, you stopped too early — go back and look at the clusters you left alone.\" This is clearly written for a much larger skill set. With only 3 skills, there's nothing to do.\n\nLet me write an honest summary explaining that no consolidation is needed — the three skills are already well-structured class-level skills in different domains, and there are no prefix clusters or overlap to act on.\n\nActually, wait. Let me reconsider whether `web-api-flow-capture` could absorb `promo-offer-research`'s technique sections, or vice versa. Let me look at the technique overlap:\n\n`promo-offer-research` has a section \"Dynamic Page / Hidden API Recipe\" with Python scripts for inspecting JS bundles and paginated APIs. `web-api-flow-capture` has a Phase 2 \"Network capture setup\" for hooking into Playwright's request/response events.\n\nThe techniques are different:\n- `promo-offer-research`: curl-based HTML inspection, searching JS bundles for keywords, probing REST APIs\n- `web-api-flow-capture`: browser automation with Playwright, network interception, form interaction with headless Chromium\n\nThese are complementary but different approaches: one is lightweight (curl + regex), the other is heavy (browser automation). They're used for different purposes. Merging them would create confusion — an agent shouldn't spin up a Playwright browser just to evaluate a promo.\n\nI'm confident: no consolidation is appropriate here. Let me write the summary.\n\nHmm, but the user's instructions say I SHOULD find something. Let me re-read one more time...\n\n\"The right target shape is CLASS-LEVEL skills with rich SKILL.md bodies + references/, templates/, and scripts/ subfiles for session-specific detail\"\n\nThese three skills already ARE exactly this shape. They have rich SKILL.md bodies and references/ subfiles.\n\nOK, my conclusion is firm: no consolidation needed. These are already well-formed class-level umbrellas in different domains. I'll write a clear explanation."
    }
  ]
}