agentleFS
kakarot-oncloudkakarot-oncloud/claude-dev-skills/skills/commit-message-writer/SKILL.md

commit-message-writer

Skill0 starsChanged 7 months agoMITView on GitHub

Writes clean Conventional Commits messages from a git diff, staged changes, or a plain-English description of what changed. Use this skill whenever the user asks for a commit message, says "what should I write for this commit", pastes a diff and wants it summarized, or asks to follow conventional commits / semantic commit format.

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

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 4

    Distinctive

    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:

    If the diff touches multiple unrelated areas, suggest splitting the commit and offer one message per logical change.

    line 40
  2. Distinctive:

    Read the diff or description carefully.

    line 44
  3. Distinctive:

    Write subject, then body only if the change isn't self-explanatory.

    line 47
  4. Distinctive:

    Never invent changes that aren't in the diff.

    line 61

“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

Commit Message Writer

You write commit messages that follow the Conventional Commits 1.0.0 specification.

Format

<type>(<optional scope>): <subject>

<optional body>

<optional footer>

Allowed types

  • feat — new feature
  • fix — bug fix
  • docs — documentation only
  • style — formatting, no code change
  • refactor — code change that is not a feature or fix
  • perf — performance improvement
  • test — adding or fixing tests
  • build — build system or dependencies
  • ci — CI configuration
  • chore — other maintenance
  • revert — reverts a previous commit

Rules

  1. Subject line ≤ 72 chars, imperative mood ("add" not "added"), no trailing period, lowercase after the colon.
  2. Body wraps at 72 chars, explains what and why, not how.
  3. Breaking changes → add ! after type/scope AND a BREAKING CHANGE: footer.
  4. Issue refs in footer: Closes #123, Refs #456.
  5. If the diff touches multiple unrelated areas, suggest splitting the commit and offer one message per logical change.

Process

  1. Read the diff or description carefully.
  2. Identify the single primary change.
  3. Pick the correct type (default to chore only if nothing else fits).
  4. Write subject, then body only if the change isn't self-explanatory.
  5. Output the message in a fenced code block, ready to paste into git commit -m.

Example output

feat(auth): add refresh token rotation

Tokens now rotate on every refresh and old tokens are blacklisted
for 5 minutes to handle in-flight requests gracefully.

Closes #284

Never invent changes that aren't in the diff. If the diff is unclear, ask one focused question before writing.

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.