agentleFS
SkillkeelSkillkeel/skillkeel-starter/skills/commit-message/SKILL.md

commit-message

Skill3 starsChanged 57 days agoMITView on GitHub

Use when the user asks to commit, write a commit message, or stage-and-commit changes. Produces a Conventional Commits message derived from the actual staged diff, never from memory of what was edited.

62 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use refactor, code-review and 7 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.
  • 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

  • MicrosoftSkill

    grill-with-docs

    Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

    Also in 3 projects that use this

  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 4 projects that use this

  • +2 more from google

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 51 edited versions we read keep these.

  • 6

    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
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Write commit messages from evidence (the diff), not from recollection.

    line 8
  2. Distinctive:

    Run git status --porcelain and git diff --cached --stat.

    line 11
  3. Very specific:

    Read the staged diff: git diff --cached.

    line 12
  4. Distinctive:

    Never describe changes that are not in the staged diff.

    line 30
  5. Distinctive:

    Never include secrets, tokens, or internal URLs in the message.

    line 31
  6. Distinctive:

    Do not add "Co-Authored-By" or tool attribution unless the repo's CONTRIBUTING or the user asks for it.

    line 32
  7. Distinctive:

    If tests were not run, do not claim they pass in the message.

    line 33

“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

Write commit messages from evidence (the diff), not from recollection.

Procedure

  1. Run git status --porcelain and git diff --cached --stat. If nothing is staged, ask whether to stage all tracked changes (git add -u) or specific paths. Never git add -A silently (untracked junk, secrets).
  2. Read the staged diff: git diff --cached. If it exceeds ~400 lines, read --stat plus the hunks of the 5 largest files.
  3. Classify the change: feat, fix, refactor, perf, docs, test, build, ci, chore. Pick ONE. If the diff mixes types, say so and offer to split into two commits.
  4. Scope = the top-level directory or module most touched (auth, api, cli). Omit when the change is cross-cutting.
  5. Subject: imperative, ≤ 50 chars, no trailing period. fix(auth): reject expired refresh tokens.
  6. Body only when the why is not obvious from the diff: 1 to 3 lines, wrap at 72. Reference issues as Refs #123 / Closes #123 on their own line.
  7. Show the message, then commit with a heredoc so newlines survive:
    git commit -m "$(cat <<'MSG'
    fix(auth): reject expired refresh tokens
    
    Tokens past `exp` were accepted because the check used `<` instead of `<=`.
    Closes #412
    MSG
    )"
  8. Print git log -1 --stat as proof.

Rules

  • Never describe changes that are not in the staged diff.
  • Never include secrets, tokens, or internal URLs in the message.
  • Do not add "Co-Authored-By" or tool attribution unless the repo's CONTRIBUTING or the user asks for it.
  • If tests were not run, do not claim they pass in the message.

Verify

Maintainers: bash evals/run.sh /tmp/skillkeel-evals commit-message from the plugin root runs this case and grades it; records and transcripts sit in evals/commit-message/. evals/commit-message/: fixture repo with two new staged Python files; expected: feat subject ≤ 50 chars, imperative, describes only the staged files, no tool trailer, git log -1 --stat shown after the commit.

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.