Doc Workflow
Documentsdoc-workflowDoc Workflow is an Agent Skill for documents published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Use when user asks about 'documentation workflow', 'how to document', 'doc system', 'what is llmdoc', 'how does llmdoc work', or needs guidance on the documentation system.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/documents/doc-workflow/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/doc-workflow, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
/doc-workflow
This skill provides guidance on the llmdoc documentation system and available documentation workflows.
Pre-fetched Context
- Llmdoc status: !
test -d llmdoc && echo "INITIALIZED" || echo "NOT_INITIALIZED" - Doc count: !
find llmdoc -name "*.md" 2>/dev/null | wc -l - Doc index: !
cat llmdoc/index.md 2>/dev/null | head -30
Workflow Guide
If llmdoc is NOT initialized:
Recommend running /tr:initDoc to initialize the documentation system.
Explain the benefits:
- Documentation-driven development
- LLM-optimized retrieval maps
- Consistent project understanding
If llmdoc IS initialized:
Explain the available workflows:
| Task | Command/Skill | Description |
|---|---|---|
| Read docs | /read-doc | Quick project understanding |
| Update docs | /update-doc | Sync docs after code changes |
| Investigate | /investigate | Doc-first codebase research |
| Initialize | /tr:initDoc | One-time setup (already done) |
llmdoc Structure
llmdoc/
├── index.md # Navigation hub
├── overview/ # "What is this project?"
├── architecture/ # "How does it work?" (LLM Retrieval Map)
├── guides/ # "How do I do X?"
└── reference/ # "What are the specifics?"
Actions
- Check the pre-fetched context to determine llmdoc status.
- Based on user's question, provide relevant guidance.
- If user wants to perform an action, guide them to the appropriate skill/command.