agentleFS
claude-worldclaude-world/director-mode-lite/skills/smart-commit/SKILL.md

smart-commit

Skill80 starsChanged 8 months agoMITView on GitHub

Create clean Conventional Commits: inspect the diff, group related changes, run quality checks, and write type(scope) messages. Use when committing work, or when the user runs /smart-commit or asks to commit changes.

  • Reads credentials

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 14 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:

    Create a high-quality commit for current changes.

    line 9
  2. Distinctive:

    Run available quality gates (test suite, linter, formatter) if the project configures them, and fix failures before committing.

    line 15
  3. Distinctive:

    Commit the staged group.

    line 18
  4. Distinctive:

    No period at end

    line 71

“Common” is measured: kept by at least 6 in 10 of the 14 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

Smart Commit

Create a high-quality commit for current changes.

Execution

  1. Inventory changes: run git status and git diff (plus git diff --staged for already-staged work) to see everything that changed.
  2. Group related changes into logical commits — list the files that belong to each group so one commit maps to one concern.
  3. Run available quality gates (test suite, linter, formatter) if the project configures them, and fix failures before committing.
  4. Stage each group in turn with git add <files>.
  5. Craft a Conventional Commits message — type(scope): description, with a body that explains why the change was made.
  6. Commit the staged group.
  7. Confirm the result with git log --oneline -n (choose n to cover the commits you just made).

Repeat steps 4-6 for each group so unrelated changes land in separate commits. The format and type reference below is your guide for steps 5-6.

Pre-Commit Checklist

Scope Check

  • Solves one problem only
  • No unrelated changes
  • No debug code
  • No temporary files

Quality Check

  • All tests pass
  • Code is formatted
  • No linting errors
  • Documentation updated

Commit Message Format

<type>(<scope>): <description>

<body>

<footer>

Type (Required)

TypeUse When
featNew feature (user-visible)
fixBug fix
docsDocumentation only
testAdding/updating tests
refactorCode restructure (no behavior change)
styleFormatting (no logic change)
choreMaintenance, dependencies
perfPerformance improvement

Scope (Optional)

Module, component, or file affected:

  • feat(auth): add login endpoint
  • fix(api): handle null response
  • docs(readme): update installation steps

Description (Required)

  • 50 characters or less
  • Present tense, imperative mood
  • Lowercase first letter
  • No period at end
  • Describe WHAT, not HOW

Examples

Feature

feat(user): add email verification

Implement email verification flow for new user registration.
Users must verify email before accessing protected features.

Closes #42

Bug Fix

fix(api): handle null response in user endpoint

Previously threw uncaught exception when user not found.
Now returns 404 with proper error message.

Fixes #67

Commit Checklist

Before committing:

  • Follows Conventional Commits format
  • Subject clearly describes the change
  • One commit = one logical change
  • No sensitive information (.env, credentials)
  • All tests pass

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.

Reviews can't be read right now.

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.