agentleFS
hmj1026hmj1026/dhpk/skills/doc-maintain/SKILL.md

doc-maintain

Skill2 starsChanged 6 days agoMITView on GitHub

Maintain documentation through stale-doc refresh, architecture codemap generation, or a bounded Markdown refactor. Selects update, codemap, or refactor while preserving each output and evidence contract. Not for application source, tests, manifests, route tables, generated projections, or broad policy review.

The file

Files
SKILL.md

Documentation maintenance

  1. Select the mode from the requested output below. A command's fixed mode or explicit mode wins; clarify ambiguous target ownership before editing.
  2. Resolve the remaining normalized arguments as that mode's consumer input. Record the target, existing dirty work, canonical evidence and any locale pair.
  3. Load only the selected mode procedure and apply its local completion gates.
  4. Return its report with the actual PASS, NOT_RUN, BLOCKED or human-decision state. Keep source implementation, installation and release evidence separate.
ModeTask and inputProcedureOutput and authority
updateStale documentation path or workflow keywordupdateDocumentation update report; PASS/NOT_RUN/BLOCKED/Need Human; documentation only
codemapStructural change or architecture refresh of live consumer treecodemapFive CODEMAPS documents and codemap-diff report; PASS/BLOCKED/confirmation-required; preserve the 30% overwrite gate
refactorOne existing, safe Markdown pathrefactorRefactored path, before/after line counts, preserved facts; PASS/NOT_RUN/BLOCKED

Authority is documentation-only: application source, tests, manifests, route tables and generated runtime projections belong to their respective owners. An update does not refresh codemaps or refactor an unrelated file. A refactor retains facts and policy; a codemap refresh keeps its output-path restrictions.

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.