agentleFS
metagit-aimetagit-ai/metagit-cli/skills/metagit-stamp/SKILL.md

metagit-stamp

Skill4 starsChanged 12 days agoMITView on GitHub

Stamp or refresh a non-umbrella .metagit.yml for a target folder (git or local) using detection-first, idempotent updates. Use when users ask to create/update a local project manifest quickly.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Use this skill to create or refresh a project-local .metagit.yml for a target folder that should behave like a lightweight atlas.

    line 8
  2. Distinctive:

    Ensure a base manifest exists in that folder:

    line 19
  3. Distinctive:

    if missing: initialize one

    line 20
  4. Distinctive:

    if present: keep it and refresh

    line 21
  5. Distinctive:

    Run repository detection for auto-filled metadata.

    line 22
  6. Distinctive:

    Run from the target folder unless an explicit path is provided.

    line 28
  7. Very specific:

    Do not overwrite unrelated files.

    line 60
  8. Distinctive:

    Prefer idempotent refreshes over destructive resets.

    line 61
  9. Very specific:

    If the user needs multi-repo workspace orchestration, switch to metagit-projects instead.

    line 62

≈ “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

Manifest Stamping (Non-Umbrella)

Use this skill to create or refresh a project-local .metagit.yml for a target folder that should behave like a lightweight atlas.

Use when

  • User asks to create a new local .metagit.yml for an app/repo folder
  • User asks to refresh stale metadata in an existing non-umbrella manifest
  • User wants an idempotent detect-and-update flow rather than hand-editing every field

Workflow

  1. Resolve the target folder and verify it exists.
  2. Ensure a base manifest exists in that folder:
    • if missing: initialize one
    • if present: keep it and refresh
  3. Run repository detection for auto-filled metadata.
  4. Persist the result to .metagit.yml in the target folder.
  5. Validate and report what changed.

Commands

Run from the target folder unless an explicit path is provided.

# initialize only when missing
metagit init

# detect + save (idempotent refresh)
metagit detect repository --path . --save --force --config-path .metagit.yml --output summary

# validate stamped manifest
metagit config validate --config-path .metagit.yml

Path-targeted variant:

metagit detect repository --path /path/to/target --save --force --config-path /path/to/target/.metagit.yml --output summary
metagit config validate --config-path /path/to/target/.metagit.yml

Output contract

Return:

  • target path
  • whether manifest was created or refreshed
  • detection mode used (detect repository --save)
  • validation result
  • key stamped fields (name/kind/language/framework/package manager, if detected)

Safety

  • This skill is for non-umbrella project manifests, not workspace controller manifests.
  • Do not overwrite unrelated files; only update .metagit.yml.
  • Prefer idempotent refreshes over destructive resets.
  • If the user needs multi-repo workspace orchestration, switch to metagit-projects instead.

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.