agentsclimarketplace

Loopify bootstrap

Skill AndreRatzenberger/loopify/plugins/loopify/skills/loopify-bootstrap

Loop yes. Prompt no. Agent skills that turn specs into checked agent loops with receipts.

Install
npx -y skills add AndreRatzenberger/loopify --skill loopify-bootstrap

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when seeding a repository with loop materials such as a goal prompt, Loop Contract, quality gate, trace template, acceptance checklist, and test skeletons.

SKILL.md

2.5 KB, as published. Nobody here has run it

loopify-bootstrap

Seed a repository with the files needed to run a goal loop.

When To Use

  • A project has a spec or Loop Contract but no loop harness.
  • A demo repo needs a prepared material pack.
  • A future /goal should run from repo-relative files.

Do Not Use

  • Do not overwrite existing tests, scripts, or docs without preserving intent.
  • Do not install dependencies unless the user authorized implementation work.
  • Do not make the quality gate pass by deleting meaningful checks.

Workflow

  1. Read the Loop Contract or source spec.
  2. Inspect the repo stack using references/repo-stack-detection.md.
  3. Pick the next loop directory: .loopify/loops/NNN-slug/.
    • Note in the loop README that verdict.md will be written by the independent verifier at the end — the maker must not create it.
  4. Create or update .loopify/index.md with the new loop entry.
  5. Copy the source spec to source.md when available.
  6. Create or copy the Loop Contract to loop-contract.md.
  7. Add quality-gate.sh, trace.md, acceptance-checklist.md, final-report.md, retro.md, and artifacts/.
  8. Add a repo-relative goal prompt when the target agent needs one.
  9. Make shell scripts executable.
  10. Run the lightest validation that should pass before implementation.

Output

Default outputs:

  • .loopify/index.md
  • .loopify/loops/NNN-slug/source.md
  • .loopify/loops/NNN-slug/loop-contract.md
  • .loopify/loops/NNN-slug/quality-gate.sh
  • .loopify/loops/NNN-slug/acceptance-checklist.md
  • .loopify/loops/NNN-slug/trace.md
  • .loopify/loops/NNN-slug/final-report.md
  • .loopify/loops/NNN-slug/retro.md
  • .loopify/loops/NNN-slug/artifacts/

Legacy flat paths such as docs/loop-contract.md, scripts/quality-gate.sh, and runs/trace.md are supported when the user names them, but new loops should use loop directories.

Validation

  • Repo-relative paths work from the project root.
  • The loop directory is self-contained enough for loopify-run.
  • .loopify/index.md lists the loop number, slug, source, status, and stop reason when known.
  • Existing checks are preserved.
  • If implementation has not happened, the first failing check is intentional and documented.

Example

Use loopify-bootstrap with .loopify/loops/001-papertrail/loop-contract.md.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.