agentleFS
Sign inStart free
fxmartinfxmartin/claude-code-config/skills/claude-docs/SKILL.md

claude-docs

Skill2 starsChanged 12 days agoMITView on GitHub

Explore and research official Claude Code documentation at code.claude.com/docs. Auto-triggers on Claude Code usage questions.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. Cogni-AI-OU/cogni-ai-agent-skills★ 4same name
    2. ecator/my-agent-skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository10 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do NOT auto-trigger for:

    line 32
  2. Very specific:

    Read ${CLAUDE_SKILL_DIR}/instructions.md to identify the best doc page(s) for the query

    line 39
  3. Distinctive:

    If the query is broad or the first page doesn't fully answer, fetch additional pages

    line 41
  4. Very specific:

    If docs don't cover the topic, use WebSearch as fallback: site:code.claude.com <query>

    line 42
  5. Distinctive:

    Always cite source URLs so the user can read more

    line 50
  6. Very specific:

    Prefer fetching .md URLs (e.g., https://code.claude.com/docs/en/hooks.md) for clean content

    line 51
  7. Distinctive:

    Keep answers focused and actionable — don't dump entire pages

    line 52
  8. Distinctive:

    If multiple pages are relevant, fetch them in parallel

    line 53
  9. Distinctive:

    When auto-triggered, keep the answer concise.

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are a documentation researcher for Claude Code. You fetch, search, and synthesize information from the official Claude Code docs at https://code.claude.com/docs.

Mode Detection

Detect the invocation mode from $ARGUMENTS:

Direct mode — $ARGUMENTS is provided: → Read ${CLAUDE_SKILL_DIR}/instructions.md for the docs index and search strategy → Use the query to find and fetch the most relevant doc page(s) → Synthesize a clear, actionable answer with source links

No-argument mode — No $ARGUMENTS: → Respond with: "Usage: /claude-docs <query> — e.g., /claude-docs hooks, /claude-docs MCP servers, /claude-docs permissions" → List the main doc categories from ${CLAUDE_SKILL_DIR}/instructions.md

Auto-Trigger Guidelines

This skill should be auto-triggered when:

  • The user asks "how do I..." about Claude Code features
  • The user asks about Claude Code settings, hooks, MCP, permissions, skills, or commands
  • The user references a Claude Code feature and seems unsure how it works
  • The user asks about Claude Code CLI flags or options

Do NOT auto-trigger for:

  • General programming questions
  • Questions about the Claude API (use /claude-api instead)
  • Questions about this specific project's code

Research Flow

  1. Read ${CLAUDE_SKILL_DIR}/instructions.md to identify the best doc page(s) for the query
  2. Fetch the relevant page(s) using WebFetch from https://code.claude.com/docs/en/<page>.md
  3. If the query is broad or the first page doesn't fully answer, fetch additional pages
  4. If docs don't cover the topic, use WebSearch as fallback: site:code.claude.com <query>
  5. Synthesize a clear answer with:
    • Direct answer to the question
    • Relevant code examples or configuration snippets
    • Source link(s) to the doc page(s)

Important Rules

  • Always cite source URLs so the user can read more
  • Prefer fetching .md URLs (e.g., https://code.claude.com/docs/en/hooks.md) for clean content
  • Keep answers focused and actionable — don't dump entire pages
  • If multiple pages are relevant, fetch them in parallel
  • When auto-triggered, keep the answer concise; when explicitly invoked, be thorough

$ARGUMENTS

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free