agentleFS
Tngc93Tngc93/repo-onboarding/skills/refresh/SKILL.md

refresh

Skill0 starsChanged 33 days agoMITView on GitHub

Bring a repository's AGENTS.md and CLAUDE.md back in line with the code after commands, folders, dependencies or CI changed. Use when repo-onboarding reports stale guidance, when `repo-onboarding check` fails, or when the user asks to update, refresh or fix the agent docs.

12 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 6 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 10 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run repo-onboarding check and keep its output.

    line 10
  2. Very specific:

    Run repo-onboarding update.

    line 15
  3. Very specific:

    If the + and - lines show new top-level folders, a new framework or a changed workflow, check whether the Architecture, Conventions and …

    line 17
  4. Very specific:

    Run repo-onboarding check again until it reports no errors.

    line 18

“Common” is measured: kept by at least 6 in 10 of the 10 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

Refresh agent guidance

The CLI is at ${CLAUDE_PLUGIN_ROOT}/cli/repo-onboarding.mjs (or ../../cli/repo-onboarding.mjs relative to this file if the variable was not substituted). Run it with node. Below, repo-onboarding means that command.

  1. Run repo-onboarding check and keep its output. It lists:
    • stale: the generated block differs from the repository. The - and + lines show what changed.
    • unknown-command: a command written by hand no longer exists.
    • missing-path: a file or folder written by hand was not found.
    • claude-ignores-agents: CLAUDE.md does not import AGENTS.md.
  2. Run repo-onboarding update. This rewrites only the generated block. For claude-ignores-agents, run repo-onboarding init, which only adds the import line.
  3. For each unknown-command and missing-path, find out what replaced it before editing: look at the manifest scripts, git log --oneline -20 -- <path>, git log -S '<old name>' --oneline, and search the code. Update the line to the new command or path. Delete it only if the thing is really gone.
  4. If the + and - lines show new top-level folders, a new framework or a changed workflow, check whether the Architecture, Conventions and Gotchas sections are still true, and fix them.
  5. Run repo-onboarding check again until it reports no errors.
  6. Tell the user in two or three lines what changed in the docs. Do not commit unless they ask.

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.