agentleFS
Sign inStart free
glebisglebis/claude-skills/cull-release-recover/SKILL.md

cull-release-recover

Skill400 starsChanged 4 months agoMITView on GitHub

Use when a Cull release is stuck, inconsistent, failed in a workflow or artifact gate, missing Homebrew promotion, failed after publication, or needs a safe recovery or patch plan.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Never erase immutable release history to make local state look consistent.

    line 11
  2. Very specific:

    Run npm run release:cull -- resume --version "$VERSION" --json and parse exactly one JSON envelope.

    line 16
  3. Very specific:

    Never delete or move a tag or release.

    line 31

≈ “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

Cull Release Recover

Principle

Derive truth from external evidence, then resume the first incomplete safe phase. Never erase immutable release history to make local state look consistent.

Diagnose

  1. Resolve the Cull checkout.
  2. Run npm run release:cull -- resume --version "$VERSION" --json and parse exactly one JSON envelope. Treat local release state as a cache.
  3. Authenticate and compare the prepared commit, remote annotated tag and peeled commit, Actions run, exact asset inventory, public release, updater metadata, provenance, and Homebrew cask/evidence.
  4. Classify the next action exactly as rerun-check, prepare-new-version, watch-build, verify-artifact, publish-verified-artifacts, promote-homebrew, or prepare-patch-plan.
  5. Execute only the safe resumable phase the user already authorized. Do not repeat a completed signed build or replace verified artifacts.

A post-publish verification failure creates or updates the stable P0 bd incident, blocks later release checks, and returns prepare-patch-plan. Prepare the patch plan but never publish that patch implicitly.

Never delete or move a tag or release. Never force-push, clobber assets, reset unrelated work, bypass a gate, clean cull.db, or treat missing evidence as success.

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.

Reviews can't be read right now.

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