agentleFS
Sign inStart free
freemtyfreemty/labmate/skills/update-project-skill/SKILL.md

update-project-skill

Skill25 starsChanged 2 months agoMITView on GitHub

Use when durable project architecture, experiment findings, pitfalls, or active interfaces have materially changed. Triggers on "refresh project knowledge", "更新项目知识", project-skill drift, or after major findings.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Keep project-skill as a compact map of stable facts and gotchas, not a session diary or repository duplicate.

    line 9
  2. Very specific:

    Keep .agents/ and .claude/ mirrors identical when both exist, run the parity checker, append the changelog, and update skill_updated_at.

    line 25
  3. Distinctive:

    Do not copy file trees, skill catalogs, command tutorials, or transient tasks into project-skill.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Update Project Skill

Keep project-skill as a compact map of stable facts and gotchas, not a session diary or repository duplicate.

  1. Resolve <plugin-root> and collect bounded facts:

    python3 <plugin-root>/scripts/project_snapshot.py
  2. A bounded read-only scan may use a suitable subagent for high-reasoning analysis when available; otherwise scan directly. Read only files needed to validate architecture, findings, active versions, and durable pitfalls.
  3. Propose a focused diff. Preserve append-only lessons unless evidence shows they are false.
  4. Apply the requested knowledge update within the user's authorization. Ask only when conflicting evidence or a new scope choice would change the result.
  5. Keep .agents/ and .claude/ mirrors identical when both exist, run the parity checker, append the changelog, and update skill_updated_at.

Do not copy file trees, skill catalogs, command tutorials, or transient tasks into project-skill.

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