Agent skill
conventional-commits
Generate properly formatted Conventional Commits messages with Claude Code footer. Use when creating git commits, writing commit messages, or the user mentions "commit", "git commit", or wants to save changes.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/design/conventional-commits-vm0-ai-vm0
SKILL.md
Conventional Commits for emoji_gen
This Skill helps create commit messages that follow the Conventional Commits specification and include the required Claude Code footer.
Commit Message Format
<type>[optional scope][optional !]: <description>
[optional body]
[required footer]
Types
- feat: New feature for the user or library
- fix: Bug fix for the user
- docs: Documentation changes only
- build: Changes to build system or dependencies (Cargo.toml, Dockerfile, CI)
- test: Adding or updating tests
- refactor: Code changes that neither fix bugs nor add features
- perf: Performance improvements
- chore: Maintenance tasks, tooling changes
Scope Examples
feat(cli):- CLI-related featurefix(parser):- Parser bug fixbuild(docker):- Docker build changesdocs(readme):- README updates
Breaking Changes
Indicate with ! after type/scope:
feat!: drop support for count=0
Or use BREAKING CHANGE: footer:
feat: change default emoji pool
BREAKING CHANGE: removed deprecated emojis from pool
Required Footer
ALWAYS include this footer:
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Instructions for Creating Commits
-
Run git diff to understand changes:
bashgit diff --staged # or git diff -
Analyze the changes to determine:
- Appropriate type (feat, fix, docs, build, etc.)
- Optional scope (cli, docker, ci, etc.)
- Whether it's a breaking change
- Clear, concise description (imperative mood)
-
Draft commit message following the template in
commit-template.txt -
Use heredoc format for multi-line commits:
bashgit commit -m "$(cat <<'EOF' feat: add emoji category support Adds categorization system for emojis (animals, food, symbols). Users can now filter by category using --category flag. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <[email protected]> EOF )"
Best Practices
- Use imperative mood: "add" not "added", "fix" not "fixed"
- Keep summary under 50 characters when possible
- Explain what and why, not how
- Reference issue numbers in body if applicable
- Always include the Claude Code footer
- Use body for context if the change needs explanation
Common Patterns
Simple feature
feat: add emoji pool customization via config file
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Bug fix with details
fix: correct emoji count validation
Previously accepted negative counts, now returns error for count < 0.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Build/CI change
build(docker): optimize dependency caching layer
Remove emoji_gen-specific artifacts to prevent cache conflicts between
dummy and real builds.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Documentation
docs: add Docker development workflow to README
Includes docker-dev.sh helper script usage and examples.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Breaking change
feat(cli)!: replace --count with --num flag
BREAKING CHANGE: --count flag removed, use --num instead
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <[email protected]>
Error Prevention
DO NOT:
- Forget the Claude Code footer
- Use past tense ("added", "fixed")
- Write vague descriptions ("update stuff", "fix bug")
- Skip the body when breaking changes need explanation
- Commit without running git diff first
DO:
- Always check staged changes first
- Use clear, specific descriptions
- Include body for context when needed
- Use appropriate type and scope
- Include the required footer
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?