Agent skill
commit
Guidelines for writing commit messages and PR descriptions
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/commit
SKILL.md
Commit Messages
Format
type(scope): short message
Types
feat- new featurefix- bug fixrefactor- code refactoringchore- maintenance tasks (deps, config, tooling)
Scopes
Always use the app or package name as scope:
Apps: admin, auth, editor, evals, main
Packages: ai, auth, core, db, e2e, error-reporter, mailer, next, testing, tsconfig, ui, utils
Inferred scopes (when change doesn't fit an app/package):
agents- CLAUDE.md, AGENTS.md,.claude/folderci- GitHub workflows, CI/CD configurationdeps- dependency updates across multiple packagesdata- data layer changes spanning multiple packages
Examples
feat(main): add lesson page
fix(editor): always use custom lesson kind
refactor(db): use enum for step kind
chore(deps): update vercel ai sdk
chore(agents): add commit skill
fix(ci): update node version in workflow
Rules
- Use lowercase for entire message
- No period at the end
- Keep message under 72 characters
- Use imperative mood ("add" not "added")
Author
Always set the AI agent as the commit author:
git commit -m "feat(main): add lesson page" --author="Claude Opus 4.5 <[email protected]>"
PR Descriptions
Keep descriptions brief. Focus on what changed. No need to list verification commands run.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?