agentleFS
BigHandsDanBigHandsDan/molt/.claude/skills/repo-skills/SKILL.md

repo-skills

Skill1 starsChanged 8 months agoApache-2.0View on GitHub

After cloning a repository, scan for skill definitions and load them on demand. Always use this after cloning any repo.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are 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.

  • 2

    Very specific

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

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

    After cloning any repository, scan for skill definitions.

    line 8
  2. Distinctive:

    If no skill files are found, skip the index output and proceed with the task.

    line 16
  3. Distinctive:

    When a discovered skill is relevant to your current task, read its full file and follow its instructions.

    line 25
  4. Very specific:

    If the <repo-skills> index is missing from your conversation history (e.g.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Repo Skill Discovery

After cloning any repository, scan for skill definitions. Replace <repo-root> below with the absolute path of the cloned repository:

find <repo-root>/.claude/skills -name "SKILL.md" 2>/dev/null
find <repo-root>/.codex/agents \( -name "*.md" -o -name "*.toml" \) 2>/dev/null
find <repo-root>/.skills -name "SKILL.md" 2>/dev/null

If no skill files are found, skip the index output and proceed with the task.

For each skill file found, read only the metadata (YAML frontmatter for .md files, top-level fields for .toml files) to extract the name and description. Output a compact index:

<repo-skills repo="org/repo-name" path="/absolute/path/to/repo"> - skill-name: one-line description - skill-name: one-line description </repo-skills>

When a discovered skill is relevant to your current task, read its full file and follow its instructions.

If the <repo-skills> index is missing from your conversation history (e.g. after context compaction), re-scan the repo using the path from git rev-parse --show-toplevel in the repo's working directory to rebuild it.

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.