commit-prepare
About
This Claude skill helps developers prepare conventional commit messages by analyzing git changes. It activates on commit-related phrases and automatically determines the appropriate commit type (feat, fix, docs, etc.) and scope. The skill examines staged/unstaged changes via git commands to generate properly formatted commit messages.
Quick Install
Claude Code
Recommended/plugin add https://github.com/majiayu000/claude-skill-registrygit clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/commit-prepareCopy and paste this command in Claude Code to install this skill
Documentation
Commit Preparation Skill
Automatically prepare commit messages following conventional commits standard.
Activation
This skill activates on keywords:
- "commit", "prepare commit", "commit this"
- "commit message", "write commit"
- "stage and commit", "commit changes"
- "what should I commit", "ready to commit"
Workflow
When activated, follow these steps:
1. Gather Context
Run these commands to understand what's being committed:
# See all changes
git status
# Staged changes (what will be committed)
git diff --cached --stat
git diff --cached
# Unstaged changes (won't be committed yet)
git diff --stat
2. Analyze Changes
Determine:
- Type: feat, fix, docs, refactor, test, chore, perf, ci
- Scope: Which component/module is affected (optional)
- Breaking: Are there breaking changes?
- What: What was changed
- Why: Why was it changed (if not obvious)
3. Generate Commit Message
Follow conventional commits format:
<type>(<scope>): <subject>
<body>
<footer>
Type Reference
| Type | When to Use | Example |
|---|---|---|
feat | New feature | feat: add user authentication |
fix | Bug fix | fix: resolve null pointer in parser |
docs | Documentation only | docs: update API reference |
refactor | Code restructuring | refactor: extract validation logic |
test | Adding/fixing tests | test: add unit tests for auth |
perf | Performance improvement | perf: optimize database queries |
chore | Maintenance, deps | chore: update dependencies |
ci | CI/CD changes | ci: add caching to workflow |
style | Formatting only | style: fix indentation |
Rules
- Subject: Imperative mood ("add" not "added"), no period, max 50 chars
- Body: Wrap at 72 chars, explain what and why (not how)
- Footer: Breaking changes, issue references
4. Handle Staging
If there are unstaged changes, ask:
- "Stage all changes?" (
git add .) - "Stage specific files?" (list them)
- "Review changes first?" (show diff)
5. Execute Commit
After user confirms the message:
git add <files>
git commit -m "<message>"
Important: Always use HEREDOC for multi-line commits:
git commit -m "$(cat <<'EOF'
feat: add user authentication
Implement OAuth2 flow with Google and GitHub providers.
Includes session management with secure cookies.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <[email protected]>
EOF
)"
6. Post-Commit
After successful commit:
- Show
git log -1to confirm - Suggest
git pushif ready - Mention if more changes remain unstaged
Example Interactions
Simple Commit
User: "commit these changes"
Claude:
git status
git diff --cached
Looking at your staged changes:
- Modified
src/auth/oauth.py- added token refresh logic - Modified
tests/test_auth.py- added refresh tests
Suggested commit:
feat(auth): add OAuth token refresh
Implement automatic token refresh when access token expires.
Includes retry logic with exponential backoff.
Shall I commit with this message?
Breaking Change
User: "ready to commit"
Claude: I see you've changed the API response format. This is a breaking change.
Suggested commit:
feat(api)!: change response envelope format
BREAKING CHANGE: API responses now use { data, meta, errors }
envelope instead of flat response. Clients must update parsing.
Migration: Update response handlers to access .data property.
This marks it as a breaking change with !. Proceed?
Multiple Logical Changes
User: "commit this"
Claude: I see changes to multiple unrelated areas:
- Bug fix in
parser.py - New feature in
export.py - Updated docs
Recommend splitting into separate commits:
fix(parser): handle empty input gracefullyfeat(export): add CSV export optiondocs: update export documentation
Want me to help stage and commit each separately?
Attribution
Always include Claude attribution for AI-assisted commits:
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <[email protected]>
Safety Rules
- Never use
git commit --amendon pushed commits - Never skip hooks with
--no-verifyunless explicitly asked - Always show the commit message before executing
- Check for secrets/credentials in staged files
- Warn about large binary files
GitHub Repository
Related Skills
algorithmic-art
MetaThis Claude Skill creates original algorithmic art using p5.js with seeded randomness and interactive parameters. It generates .md files for algorithmic philosophies, plus .html and .js files for interactive generative art implementations. Use it when developers need to create flow fields, particle systems, or other computational art while avoiding copyright issues.
subagent-driven-development
DevelopmentThis skill executes implementation plans by dispatching a fresh subagent for each independent task, with code review between tasks. It enables fast iteration while maintaining quality gates through this review process. Use it when working on mostly independent tasks within the same session to ensure continuous progress with built-in quality checks.
executing-plans
DesignUse the executing-plans skill when you have a complete implementation plan to execute in controlled batches with review checkpoints. It loads and critically reviews the plan, then executes tasks in small batches (default 3 tasks) while reporting progress between each batch for architect review. This ensures systematic implementation with built-in quality control checkpoints.
cost-optimization
OtherThis Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.
