agentleFS
MaxGfellerMaxGfeller/open-harness/.agents/skills/release-local/SKILL.md

release-local

Skill611 starsChanged 7 months agoMITView on GitHub

Run the local maintainer release flow for this Changesets-based pnpm monorepo.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run the release workflow from RELEASING.md.

    line 7
  2. Distinctive:

    Only run this on main unless the user explicitly wants a dry run elsewhere.

    line 11
  3. Distinctive:

    Ask for confirmation before creating the release commit.

    line 13
  4. Very specific:

    Ask for confirmation again before starting pnpm release:publish, because it publishes to npm, pushes the branch and tags to GitHub, and may …

    line 14
  5. Very specific:

    Run pnpm release:status and confirm there are pending changesets.

    line 18
  6. Very specific:

    Commit the release files with Release packages unless the user requests a different message.

    line 21
  7. Very specific:

    If npm publish succeeded but GitHub release creation failed, rerun pnpm release:github after fixing the blocker.

    line 24
  8. Distinctive:

    If publish fails because of npm auth, OTP, or missing release notes, stop, report the exact blocker, and do not keep mutating the repo.

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Run the release workflow from RELEASING.md.

Guardrails:

  • Only run this on main unless the user explicitly wants a dry run elsewhere.
  • Require a clean worktree before versioning or publishing.
  • Ask for confirmation before creating the release commit.
  • Ask for confirmation again before starting pnpm release:publish, because it publishes to npm, pushes the branch and tags to GitHub, and may require npm OTP entry.

Workflow:

  1. Run pnpm release:status and confirm there are pending changesets.
  2. Run pnpm version-packages.
  3. Review the generated version bumps and changelog entries with the user.
  4. Commit the release files with Release packages unless the user requests a different message.
  5. Run pnpm release:publish.
  6. Confirm that npm publish succeeded and that GitHub Releases were created or updated for the tags on HEAD.
  7. If npm publish succeeded but GitHub release creation failed, rerun pnpm release:github after fixing the blocker.

If publish fails because of npm auth, OTP, or missing release notes, stop, report the exact blocker, and do not keep mutating the repo.

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.