compound-agent-doc-gardener
Audits project documentation for freshness, accuracy, and completeness
Install / Use
npx skills add Nathandela/compound-agentInstalls into whichever agent you are using.
Gemini Rules
Gemini CLI config
Quality Score
Category
Content & MediaSupported Platforms
Skill content
View source on GitHubname: compound-agent-doc-gardener description: Audits project documentation for freshness, accuracy, and completeness
Doc Gardener
Role
Audit project documentation for freshness, accuracy, and completeness. Identify stale docs, missing references, and broken links. Ensure docs/INDEX.md accurately reflects the documentation tree.
Instructions
- Read
docs/INDEX.mdto get the documentation map - Use Glob to find all .md files under docs/
- Cross-reference: every doc in INDEX should exist on disk, every doc on disk should be in INDEX
- For each doc, check:
- Does it reference files/functions that still exist? (use Grep)
- Does it describe the current behavior? (compare with source)
- Is the last-modified date reasonable?
- Flag issues and create beads issues for stale docs
Deployment
Subagent spawned via the Task tool. Return findings directly to the caller.
Output Format
Per document:
- STALE: References outdated code or behavior
- MISSING: Referenced in INDEX but file not found
- SUPERSEDED: Content duplicated or replaced elsewhere
- OK: Current and accurate
Related Skills
siyuan
46.4kAn open-source, privacy-first, self-hosted knowledge workspace where humans and AI agents work together 开源、隐私优先、自托管的知识工作空间,让人与智能体在此协作
humanizer
51.1kAgent skill that removes signs of AI-generated writing from text
oh-story-claudecode
7.0kClaude Code / Codex / OpenCode agent skills for writing Chinese web novels (网文): 扫榜、拆文、写作、去AI味、封面全流程,长篇短篇都支持 | 13 skills for novel writing and long-form fiction with file-based continuity tracking. MIT.
iPolloWork
6.5kEnterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for Codex Harness, DeepSeek Harness, and OpenCode, with unified plugins and Skills, multi-agent projects and tasks, and editable code, documents, presentations, design, and video.
Security Score
Audited on Jun 22, 2026
