agentleFS
kevinxo328kevinxo328/agent-skills/skills/commit-message/SKILL.md

commit-message

Skill0 starsChanged 3 months agoMITView on GitHub

Write Conventional Commit messages. Use when the user asks to draft or revise a commit message, asks to commit changes, or supplies a diff or change description specifically for creating a commit message.

62 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use pr-description, changelog and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    pr-description

    Draft Nacelle PR titles, pull request descriptions, commit titles, commit descriptions, and squash commit messages. Use when asked for PR or commit wording, a branch summary, or a PR description that can be used in a commit. Omit validation sections from commit bodies and remove filler.

    Also in 9 projects that use this

  • HashiCorpSkill

    changelog

    Add a `.changelog/<PR_NUMBER>.txt` entry for a GitHub Pull Request, commit, and push.

    Also in 3 projects that use this

  • GitHubSkill

    refactor

    Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.

    Also in 3 projects that use this

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 7 projects that use this

  • GoogleSkill

    grilling

    Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

    Also in 3 projects that use this

  • OpenAISkill

    brainstorming

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

    Also in 3 projects that use this

  • +2 more from google

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 51 edited versions we read keep these.

  • 1

    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. Distinctive:

    Write a Conventional Commit message from verified change context.

    line 13
  2. Very specific:

    When cleaning an existing message or running a commit hook, strip recognized AI signatures with strip-ai-signature.sh:

    line 64

“Common” is measured: kept by at least 6 in 10 of the 51 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 Skill

Write a Conventional Commit message from verified change context. The description states What changed. Add a body when the motivation, previous behavior, or trade-off is not evident from the description.

Workflow

  1. Establish the intended change set from the user's request, supplied diff, or repository state. When a repository is available, inspect the relevant diff and recent commit subjects before choosing wording.
  2. Classify the primary intent, scope, breaking change, and supported footers. Account for every changed concern; flag unrelated concerns and suggest separate commits.
  3. Draft only claims supported by the request or inspected changes. If missing information would change the type, breaking-change status, or rationale, ask one focused question. Otherwise state the assumption and keep the draft conservative.
  4. Validate the result against the format, the project's recent conventions, and the style rules below.

Completion criterion: every claim is evidence-backed, the type matches the primary intent, every changed concern is accounted for, and the output is a ready-to-copy message.

Format

<type>[optional scope]: <description>

[optional body]

[optional footer(s)]

type (required). The following are common defaults, not an exhaustive Conventional Commits list:

TypeDescription
featNew feature
fixBug fix
docsDocumentation only
styleFormatting, no logic change
refactorRestructure, not a feat or fix
perfPerformance improvement
testAdding or updating tests
choreBuild process or tooling
revertReverting a previous commit
ciCI/CD pipeline changes
buildBuild system changes

scope (optional) — area affected, e.g. auth, api, db, or package name in a monorepo. Prefer the repository's established scope names.

description (required) — short, specific summary. As the repository default style, keep it under 50 characters, use imperative mood (add not added), and omit a trailing period unless the repository uses another convention.

body (optional) — begin after one blank line. As the repository default style, wrap at 72 characters and explain motivation or context rather than repeating the description.

footer (optional) — issue refs (Closes #123), or breaking changes:

  • BREAKING CHANGE: <description> in footer, or
  • append ! to type/scope: feat!: / feat(api)!:

Output Rules

  1. Present the message in a code block.
  2. When cleaning an existing message or running a commit hook, strip recognized AI signatures with strip-ai-signature.sh:
    echo "$MSG" | ./skills/commit-message/strip-ai-signature.sh
    This removes Co-Authored-By: trailer lines naming Claude, Copilot, GPT, Gemini, or Anthropic. Newly drafted messages should contain only relevant trailers supported by the request.

Examples

fix(auth): redirect to login when session token expires

Previously crashed with an unhandled promise rejection. Now
gracefully redirects and clears the stale session data.

Closes #234
feat(api): add pagination to GET /users endpoint

Refs #189
feat(db)!: replace Prisma with Drizzle ORM

BREAKING CHANGE: All database query APIs have changed.
See docs/migration-drizzle.md for the migration guide.

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.