ReddRadar
Agent skill
git-conventional-commits
Apply when writing commit messages to maintain consistent, readable git history that enables automated changelog generation.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/git-conventional-commits
SKILL.md
When to Use
Apply when writing commit messages to maintain consistent, readable git history that enables automated changelog generation.
Patterns
Pattern 1: Commit Format
<type>(<scope>): <subject>
[optional body]
[optional footer(s)]
Source: https://www.conventionalcommits.org/en/v1.0.0/
Pattern 2: Types
feat: New feature (MINOR version bump)
fix: Bug fix (PATCH version bump)
docs: Documentation only
style: Formatting, no code change
refactor: Code change, no feature/fix
perf: Performance improvement
test: Adding/fixing tests
chore: Build, tooling, deps
ci: CI/CD changes
Pattern 3: Examples
# Feature
feat(auth): add OAuth2 login with Google
# Bug fix
fix(cart): prevent negative quantity values
# Breaking change (triggers MAJOR version)
feat(api)!: change response format to JSON:API
BREAKING CHANGE: All endpoints now return JSON:API format.
Migration guide: docs/migration-v2.md
# With scope
fix(ui/button): correct hover state color
# Multi-line body
feat(search): add full-text search
Implements Elasticsearch integration for product search.
Includes fuzzy matching and relevance scoring.
Closes #123
Pattern 4: Scope Guidelines
Scope = module, component, or area affected
Good scopes:
- auth, cart, api, db
- ui/button, api/users
- deps, config, ci
No scope when change is broad:
- docs: update README
- chore: update dependencies
Anti-Patterns
- Vague messages - "fix bug", "update code", "WIP"
- Missing type - Always prefix with type
- Too long subject - Keep under 72 chars
- Multiple changes - One logical change per commit
Verification Checklist
- Type prefix present (feat/fix/docs/etc.)
- Subject is imperative ("add" not "added")
- Subject under 72 characters
- Breaking changes marked with
!or footer - One logical change per commit
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
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.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
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?