agentleFS
SoftBlack42SoftBlack42/StarPie/.agents/skills/release-review/SKILL.md

release-review

Skill1.4k starsChanged 14 days agoMITView on GitHub

Review a StarPie release candidate for version consistency, package boundaries, plugin distribution rules, evidence completeness, upgrade behavior, and authorization before merge, tags, installers, or GitHub Release publication.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 2

    Distinctive

    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 the root AGENTS.md, docs/release.md, docs/testing.md, and any domain document touched by the candidate.

    line 8
  2. Distinctive:

    All version synchronization points agree.

    line 21
  3. Distinctive:

    No unrelated dirty files or worktree artifacts enter the candidate.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “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

StarPie Release Review

Read the root AGENTS.md, docs/release.md, docs/testing.md, and any domain document touched by the candidate.

Review inputs

  • exact candidate commit and target branch;
  • diff and commit trail;
  • version target and changelog entry;
  • build/test receipts tied to the candidate;
  • human acceptance status;
  • intended artifacts and external operations.

Checks

  • All version synchronization points agree.
  • No unrelated dirty files or worktree artifacts enter the candidate.
  • Main packages do not contain official plugin DLLs or the legacy plugin source directory.
  • Clean data startup performs no silent network/install; installed plugins still work offline.
  • Lightweight, Standalone and Setup outputs match naming and content rules.
  • SHA-256 values are generated from final artifacts, not pre-final files.
  • Upgrade/install paths preserve user configuration and do not silently enable plugins.
  • Required independent review and human gates are complete.

Authorization boundary

Review and preparation do not authorize commit, push, merge, Tag, installer publication or GitHub Release. Identify the next external action and obtain explicit authorization for it. If the requested version is wrong or an artifact is already public, stop and propose recovery; never silently overwrite release history.

Return a verdict of approve, request changes, or blocked, with concrete evidence and unverified items.

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.