agentleFS
refpathrefpath/chatgpt-team/.agents/skills/package-readiness/SKILL.md

package-readiness

Skill0 starsChanged 2 months agoMITView on GitHub

Validate a local library package candidate and a generic consumer when packaging, public interfaces, or release readiness changes. Does not authorize publishing or apply to ordinary app deployment.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 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.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Avoid sibling-only paths, private application fixtures, or untracked developer state.

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Package readiness

Inspect the project's manifest, package policy, tool versions, release scripts, and required checks. Identify the exact candidate revision and which packaging or consumer assumptions changed. Use native tools; apply Hex checks only to an Elixir package.

  • Build a local candidate and inspect its file list, dependencies, metadata, license, and required generated assets. Look for missing runtime files and unintended private or development-only content.
  • Exercise the affected public interface from a disposable generic consumer using the built candidate where the toolchain supports it. Record when a path checkout or Git dependency was used instead; it does not prove the archive is complete.
  • Avoid sibling-only paths, private application fixtures, or untracked developer state. Check optional dependency absence and supported compatibility directions when the contract requires them.
  • Align documentation and source links with the candidate. Record exact artifact identity, commands, results, consumer setup, and combinations not tested.

Integrator owns package validation with the implementation and documentation owners. A local validation task does not authorize registry publication, a release tag, deployment, or a visibility change. Follow existing user authorization and repository release policy for separate release actions; repository visibility is always user-managed in this project.

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.