agentleFS
denniemokdenniemok/simple-skills/simple-release/SKILL.md

simple-release

Skill1 starsChanged 43 days agoMITView on GitHub

Cut a release with a semantic version bump, a changelog from commit history, and a git tag. Use only when the user asks to release, bump the version, or write a changelog.

  • Commits and pushes

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check state: clean working tree, on the release branch, up to date.

    line 17
  2. Very specific:

    Only fix, perf, and others: patch

    line 22
  3. Distinctive:

    Before 1.0.0, breaking changes bump minor

    line 23
  4. Distinctive:

    Never push commits or tags unless asked.

    line 60
  5. Distinctive:

    Never move or delete an existing tag.

    line 61
  6. Very specific:

    Do not add Co-Authored-By or any AI attribution to the release commit.

    line 62
  7. Distinctive:

    If the commits do not follow a convention, read the diffs and group the changes yourself, and say that you did.

    line 63
  8. Very specific:

    Create a GitHub release with gh release create only when asked.

    line 64

≈ “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

Simple Release

Prepare a release from the commit history. Propose first, then apply only after the user confirms the version.

Workflow

  1. Check state: clean working tree, on the release branch, up to date. Stop and say so if not.
  2. Find the last tag (git describe --tags --abbrev=0) and read the commits since it (git log <tag>..HEAD --oneline). With no tag, use the full history.
  3. Pick the bump from the commits:
    • Breaking change (! after the prefix, or BREAKING CHANGE): major
    • Any feat: minor
    • Only fix, perf, and others: patch
    • Before 1.0.0, breaking changes bump minor
  4. Show the proposed version and changelog entry, and wait for confirmation.
  5. Apply: update the version file (package.json, pyproject.toml, or the one the project uses), add the entry to CHANGELOG.md, and commit as chore(release): vX.Y.Z.
  6. Tag the commit vX.Y.Z.
  7. Report the version, the tag, and the next command to push. Push only when the user asks.

Changelog entry

Newest first, one section per version, grouped by type. Write for users, not for the commit author.

## [1.4.0] - 2026-09-30

### Added
- Avatar upload on the profile page

### Fixed
- Login redirect loop on expired sessions

### Changed
- Faster chapter loading
Commit prefixSection
featAdded
fixFixed
perf, refactorChanged
revertRemoved or Reverted
docs, style, test, build, ci, choreLeave out, unless users would care
  • Rewrite commit subjects into plain sentences, and merge duplicates.
  • Flag breaking changes at the top of the entry with what to do about them.
  • Link the compare URL at the bottom if the repo has a remote.

Rules

  • Never push commits or tags unless asked.
  • Never move or delete an existing tag.
  • Do not add Co-Authored-By or any AI attribution to the release commit.
  • If the commits do not follow a convention, read the diffs and group the changes yourself, and say that you did.
  • Create a GitHub release with gh release create only when asked.

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.