official-docs
Always look up and refer to official Anthropic / Claude Code documentation. Use when the user asks about sub-agents, memory, CLAUDE.md, .claude directory, skills, hooks, MCP, plugins, common workflows, settings, or any Claude Code / Claude API feature. Never answer from memory.
- License 许可
- MIT
- 最近更新
- 2026-10-25
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- official-docs
- description
- Always look up and refer to official Anthropic / Claude Code documentation. Use when the user asks about sub-agents, memory, CLAUDE.md, .claude directory, skills, hooks, MCP, plugins, common workflows, settings, or any Claude Code / Claude API feature. Never answer from memory.
03 SKILL.md 正文
Official Documentation Lookup
When the question is about Claude Code or Anthropic platform features:
- Use WebSearch with site:code.claude.com/docs or site:platform.claude.com
- Follow up with WebFetch on the best matching official page
- Answer only from the fetched official content
- Cite the exact URL
Preferred starting points:
04 同仓库更多 Skills
repo-doc-audit
Performs a comprehensive Repository Documentation Audit and Governance Standard (RDAGS) against an entire codebase. Use this skill whenever the user wants to audit, evaluate, or assess repository documentation — including requests like "audit my repo docs", "find doc inconsistencies", "check for documentation drift", "governance review", "find dead or orphan knowledge", "check my CLAUDE.md or AGENTS.md for accuracy", or any systematic documentation quality evaluation. Always trigger this skill when the user asks to run a documentation audit or governance review, even if they describe only part of the standard (e.g., "check traceability" or "find contradictions in my docs"). Produces five output files: Repository-Audit-Report.md (full 18-section report) plus Direct-Contradictions.md, Semantic-Contradictions.md, Traceability-Failures.md, and Proposed-Repository-Governance-Improvements.md as standalone action-oriented findings documents.
writing-great-skills
Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
write-a-skill
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
teach
Teach the user a new skill or concept, within this workspace.
self-reflect
Enterprise-grade forensic self-reflection over recent git history. Multi-axis audit with pass/fail gates, mandate compliance matrix, platform drift forensics, test quality review, and ranked generation constraints.
handoff
Compact the current conversation into a handoff document for another agent to pick up.