agentleFS
manastalukdarmanastalukdar/ai-devstudio/.claude/skills/project-health/SKILL.md

project-health

Skill1 starsChanged 7 months agoMITView on GitHub

Internal health check skill for AI DevStudio project. Checks skill count consistency across docs, detects stale sessions, and identifies cache files to clean. Not user-facing.

3 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

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify that the skill count (99) is consistent across all documentation files:

    line 16
  2. Very specific:

    Check that docs/ modification dates are recent relative to skills/ changes:

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Project Health Check Skill

Internal skill used by the session-daily command. Checks the health of the AI DevStudio project itself.

Checks

1. Skill Count Consistency

Verify that the skill count (99) is consistent across all documentation files:

Bash: ls skills/ | wc -l

Then check these files reference the correct count:

  • CLAUDE.md: grep for skill count
  • AGENTS.md: grep for skill count
  • README.md: grep for skill count

Report any inconsistencies found.

2. Stale Session Files

Bash: find .claude/sessions/ -name "*.json" -mtime +30 2>/dev/null | wc -l

Report count of session files older than 30 days. Suggest running /cleanproject if count > 5.

3. Cache Size

Bash: du -sh .claude/cache/ 2>/dev/null || echo "No cache directory"

Report cache size. Suggest cleanup if > 50MB.

4. Install Script Sync

Bash: python3 -c "import ast, sys; ast.parse(open('install.py').read()); print('install.py: OK')" 2>&1
Bash: bash -n install.sh 2>&1 && echo "install.sh: OK"

Report any syntax errors.

5. Documentation Currency

Check that docs/ modification dates are recent relative to skills/ changes:

Bash: git log --oneline -1 -- skills/ docs/

Output Format

Project Health: <OK|ISSUES FOUND>

Skill count: N (consistent: yes/no)
Stale sessions: N files
Cache: <size>
Install scripts: OK / <error>
Docs currency: OK / <last updated>

Token Optimization

Expected range: 200-500 tokens

Patterns used: Bash-based queries, early exit if all checks pass

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.