agentleFS
WescholmWescholm/ghostty-fleet/.agents/skills/writing-commit-messages/SKILL.md

writing-commit-messages

Skill1 starsChanged 8 months agoMITView on GitHub

Writes Git commit messages. Activates when the user asks to write a commit message, draft a commit message, or similar.

15 other projects use a version of this, 4 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 7 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 7

    Distinctive

    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:

    Write commit messages that follow commit style guidelines for the project.

    line 10
  2. Very specific:

    Subsystem prefix: Use a short, lowercase identifier for the area of code changed (e.g., terminal, vt, lib, config, font).

    line 26
  3. Very specific:

    If the change relates to a GitHub issue, PR, or discussion, list the relevant numbers on their own lines after the subject, separated by a …

    line 38
  4. Distinctive:

    If there are no references, omit this section entirely (no blank line).

    line 41
  5. Distinctive:

    Use plain prose, not bullet points.

    line 48
  6. Distinctive:

    Keep the tone direct and technical without no filler phrases.

    line 50
  7. Distinctive:

    Don't exceed a handful of paragraphs.

    line 51
  8. Very specific:

    If .jj is present, use jj instead of git for all commands.

    line 55
  9. Distinctive:

    Run a diff to see what changes are present since the last commit.

    line 56
  10. Distinctive:

    Don't push the commit; leave that to the user.

    line 62

“Common” is measured: kept by at least 6 in 10 of the 15 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

Writing Commit Messages

Write commit messages that follow commit style guidelines for the project.

Format

<subsystem>: <summary>

<reference issues/PRs/etc.>

<long form description>

Rules

Subject line

  • Subsystem prefix: Use a short, lowercase identifier for the area of code changed (e.g., terminal, vt, lib, config, font). Determine this from the file paths in the diff. If changes span the macOS app, use macos. For GTK, use gtk. For build system, use build. Use nested subsystems with / when helpful and exclusive (e.g., terminal/osc).
  • Summary: Lowercase start (not capitalized), imperative mood, no trailing period. Keep it concise—ideally under 60 characters total for the whole subject line.

References

  • If the change relates to a GitHub issue, PR, or discussion, list the relevant numbers on their own lines after the subject, separated by a blank line. E.g. #1234
  • If there are no references, omit this section entirely (no blank line).

Long form description

  • Describe what changed, what the previous behavior was, and how the new behavior works at a high level.
  • Use plain prose, not bullet points. Wrap lines at ~72 characters.
  • Focus on the why and how rather than restating the diff.
  • Keep the tone direct and technical without no filler phrases.
  • Don't exceed a handful of paragraphs; less is more.

Workflow

  • If .jj is present, use jj instead of git for all commands.
  • Run a diff to see what changes are present since the last commit.
  • Identify the subsystem from the changed file paths.
  • Identify any referenced issues/PRs from the diff context or branch name.
  • Draft the commit message following the format above.
  • Apply the commit
  • Don't push the commit; leave that to the user.

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.