doc-fetcher

---

name: doc-fetcher description: > API/SDK documentation fetcher via Context Hub MCP + web fallback. Triggers on "API docs", "SDK docs", "docs for X", "how to use X", "documentation", "API reference", "API 문서", "라이브러리 사용법", "패키지 문서" and similar. Uses chub MCP tools (chub_search, chub_get) for curated registry access. Falls back to web search when unavailable. Progressive Disclosure with memory caching, persistent annotations, quality feedback, and knowledge graph linking. allowed-tools:

• Bash
• Read
• Write
• Grep
• Glob
• Agent
• AskUserQuestion
• WebSearch

---

Doc Fetcher — API & SDK Documentation Retrieval

Preamble

Before executing this skill:

1. Load context from memory:

   memory_search(query: "{skill-relevant-query}", associative: true, limit: 5)
   memory_search(tag: "{skill-name}", limit: 3)
   

   Review returned memories for relevant past context, decisions, and patterns.

2. Check OMC state for active work:

   state_get_status()
   

   If conflicting active tasks exist, warn the user before proceeding.

3. Detect current branch (for git-related skills):

   git rev-parse --abbrev-ref HEAD 2>/dev/null || echo "not-a-git-repo"
   

4. Check proactive mode:

   state_read("occ-proactive")
   

   If "false": do NOT proactively suggest other OpenClaw-CC skills during this session. Only run skills the user explicitly invokes.

5. Log skill activation:

   memory_daily_log(type: "note", entry: "Skill activated: /{skill-name}")
   

Role

Fetch, structure, and persist API/SDK documentation. Uses Progressive Disclosure (summary first, details on request) to minimize context usage. Leverages Context Hub (chub) MCP for curated, versioned, LLM-optimized documentation with persistent annotations and quality feedback.

Workflow

Step 1 — Check Existing Knowledge