agentleFS
PowerBeefPowerBeef/QwenVoice/.claude/skills/vocello-release-readiness/SKILL.md

vocello-release-readiness

Skill388 starsChanged 21 days agoMITView on GitHub

Read-only assessment of a tag or candidate against exact-source CI, release source authority and quality-promotion evidence; never publishes or dispatches.

The file

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:

    Read docs/reference/quality-promotion.md, docs/reference/macos-release-qa.md, docs/reference/ios-appstore-submission.md and …

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Release readiness (read-only)

Arguments: $ARGUMENTS

Read docs/reference/quality-promotion.md, docs/reference/macos-release-qa.md, docs/reference/ios-appstore-submission.md and tooling-and-evidence.md. Require/infer the exact tag or candidate; inspect existing Git metadata, GitHub checks and release assets through read-only tools. Candidate production and public promotion are separate decisions; this skill authorizes neither. No release.sh, workflow dispatch, signing, upload, metadata change, push, deployment or App Store write. Validate existing source-authority inputs with python3 scripts/release_source_authority.py and quality evidence with python3 scripts/quality_promotion.py validate; consult --help for required arguments. Curated notes use python3 scripts/check_release_notes.py <tag>. Read-only GitHub GETs may save fetched JSON to governed scratch, never into frozen evidence. The source-authority script has no network route: save the tag ref (gh api --method GET repos/<owner>/<repo>/git/ref/tags/<tag>), the annotated tag object, the tagged commit's check runs (.../commits/<sha>/check-runs?filter=all) and its push runs on main (.../actions/runs?head_sha=<sha>&event=push&branch=main) under build/scratch/transient/release-evidence/<tag>/, then pass those files to the script. Check annotated verified tag, origin/main containment, exact tagged-SHA push CI, platform/lane completeness, evidence age and compatible source/build/device identities. Missing evidence is a blocker, never an inferred PASS. Report each check and what would unblock it. Publication requires a specific maintainer request.

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.