agentleFS
RandyRawgustRandyRawgust/ai-knowledge-base-template/.claude/skills/commit-message-writer/SKILL.md

commit-message-writer

Skill1 starsChanged 6 months agoMITView on GitHub

Draft a conventional commit message from the staged git diff. Use before any commit when the user asks you to write the message or generate one. Triggers: commit message, write a commit msg, generate commit, what should I commit this as.

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

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run git diff --staged --stat to see scope

    line 12
  2. Distinctive:

    Run git diff --staged to see actual changes

    line 13
  3. Very specific:

    Write a one-liner: <type>(<scope>): <imperative present-tense summary>

    line 24
  4. Distinctive:

    Don't write "Updated X" - use imperative present: "update X"

    line 34
  5. Distinctive:

    Don't add a period at the end of the subject line

    line 35
  6. Distinctive:

    Don't reference internal session details Andy wouldn't want public

    line 36
  7. Very specific:

    Don't lie about scope if changes span multiple areas - use misc or split commits

    line 37

“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

When to use

User about to commit, asks for a message. Or you're about to commit on their behalf and need to draft one.

Process

  1. Run git diff --staged --stat to see scope
  2. Run git diff --staged to see actual changes
  3. Identify the type:
    • feat - new feature
    • fix - bug fix
    • docs - documentation only
    • refactor - code change, no behavior change
    • style - formatting, whitespace
    • test - test additions or fixes
    • chore - build, deps, config
    • perf - performance
  4. Identify the scope (e.g. cc, vault, snake, hooks, agents)
  5. Write a one-liner: <type>(<scope>): <imperative present-tense summary>
  6. First line max 72 chars. If more context needed, blank line + body.

Examples

  • feat(cc): add script output dialog with stdout/stderr capture
  • fix(snake): revert sprite-sheet to static PNG after animation glitches
  • docs(roadmap): mark phase 10 complete, refresh status header
  • chore(vault): propagate <YOUR-GH-HANDLE> GitHub handle to 5 dept-head memories

Don't

  • Don't write "Updated X" - use imperative present: "update X"
  • Don't add a period at the end of the subject line
  • Don't reference internal session details Andy wouldn't want public
  • Don't lie about scope if changes span multiple areas - use misc or split commits

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.