agentleFS
Sign inStart free
satoshikawatosatoshikawato/gbdraw/.claude/skills/gbdraw-promotion/SKILL.md

gbdraw-promotion

Skill162 starsChanged 15 days agoMITView on GitHub

Prepare the evidence for a gbdraw dev-to-main promotion - the promotion checklist, carried CI evidence, deploy-only suites, and version literals. Run only when the Owner asks for promotion preparation.

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Run node tools/ci-impact.mjs classify --base <E> --head <H>.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Prepare a dev-to-main promotion

The Owner decides when to promote and opens or approves the promotion PR. This skill gathers the evidence. The authority is the "Promotion PR checklist" and "Carrying evidence forward" in docs/internal/WEB_PERIODIC_AUDIT.md, and "Carrying evidence to a later commit" in docs/internal/SELECTIVE_CI.md.

  1. Fix the candidate head H (the dev tip) and the newest ancestor E that already has release-tier evidence.
  2. Run node tools/ci-impact.mjs classify --base <E> --head <H>. Redo only the evidence whose verdict (releaseEvidenceCarries, generatedArtifactChecksCarry, localTestEvidenceCarries) is false; link E's evidence and the classify output.
  3. Collect the audit evidence with the release-tier dispatch: gh workflow run test.yml --ref dev -f tier=release. Besides Vibrio full generation, its Promotion audit / ... jobs run every recipe check, the tools/audit/ sweeps (report-only), the user journeys, and the random walk (seeded with the run ID), and Promotion audit / summary tabulates their results, artifacts, findings, and the capabilities no journey covers. Copy that table and the uncovered capabilities into the checklist. Run other suites that run only on main or on deploy by dispatching deploy_web.yml on dev, or locally.
  4. Grep tests/, docs/capture/, docs/recipes/, and tool fixtures for schema or version literals that changed since main.
  5. Fill every item of the checklist with links. Report each item that is not met, and the evidence for it, to the Owner instead of working around 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.

Check your setup, free