agentleFS
Sign inStart free
Atiqul-IslamAtiqul-Islam/graphcrew/.claude/skills/docs-update/SKILL.md

docs-update

Skill0 starsChanged 8 months agoMITView on GitHub

Scan docs for staleness against source code and CLAUDE.md

17 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 16 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    NEVER regenerate or overwrite existing doc files

    line 41
  2. Distinctive:

    Only FLAG staleness — human decides what to update

    line 42
  3. Distinctive:

    Read-only analysis except for ARCHITECTURE.md header timestamp updates

    line 43

“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “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

docs-update

Scan documentation for staleness. Does NOT regenerate existing docs.

Usage

/docs-update

Process

  1. Scan folder structure — compare docs/ARCHITECTURE.md folder structure section against actual src/graphcrew/ layout
    • Flag any new files/directories not listed
    • Flag any listed files/directories that no longer exist
  2. Scan CLAUDE.md decisions — check if any new architectural decisions in CLAUDE.md are not yet reflected in docs/graphcrew_docs.html section 2.4
    • Count decisions in CLAUDE.md vs what's documented
    • Flag discrepancies
  3. Report — output a summary:
    • What's current and up-to-date
    • What's stale and needs manual attention
    • Timestamp of last check

Existing Doc Files (DO NOT modify these):

  • docs/ARCHITECTURE.md — 8-layer diagram, 53 decisions
  • docs/graphcrew_docs.html — Full doc site with all ADRs
  • docs/user-guide.md — Installation → production
  • docs/extending.md — Extension point decision tree
  • docs/deployment.md — Docker, lifecycle
  • docs/common-patterns.md — Production skeletons
  • docs/performance-tuning.md — Optimization tips
  • docs/troubleshooting.md — Common issues
  • docs/knowledge-schema.md — react_config.yaml reference
  • docs/PROJECT_DISCUSSION.md — Design conversation

Rules

  • NEVER regenerate or overwrite existing doc files
  • Only FLAG staleness — human decides what to update
  • Read-only analysis except for ARCHITECTURE.md header timestamp updates

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