메뉴
Analyze git changes and generate conventional commit messages. Supports batch commits for multiple unrelated changes. Use when: (1) Creating git commits, (2) Reviewing staged changes, (3) Splitting large changesets into logical commits.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | commit-message |
| description | Analyze git changes and generate conventional commit messages. Supports batch commits for multiple unrelated changes. Use when: (1) Creating git commits, (2) Reviewing staged changes, (3) Splitting large changesets into logical commits. |
Analyze git changes and generate context-aware commit messages following Conventional Commits.
# Analyze all changes
python3 .shared/commit-message/scripts/analyze_changes.py --analyze
# Get batch commit suggestions
python3 .shared/commit-message/scripts/analyze_changes.py --batch
# Generate message for specific files
python3 .shared/commit-message/scripts/analyze_changes.py --generate "src/api/*.py"
| Command | Description |
|---|---|
--analyze | Show all changed files with status and categories |
--batch | Suggest how to split changes into multiple commits |
--generate [pattern] | Generate commit message for matching files |
--staged | Only analyze staged changes (default: all changes) |
| Type | Description | Example |
|---|---|---|
feat | New feature | feat(api): add user authentication |
fix | Bug fix | fix(db): resolve connection timeout |
refactor | Code restructuring | refactor(utils): simplify helper functions |
docs | Documentation | docs: update README |
test | Tests | test(api): add user endpoint tests |
chore | Maintenance | chore: update dependencies |
style | Formatting | style: fix linting errors |
When you have multiple unrelated changes:
--batch to see suggested commit groupsgit add <files>Files are grouped by:
src/api/, tests/, docs/Note: The
analyze_changes.pyscript provides file grouping and basic suggestions. Use its output as a starting point, then readgit diffto understand the actual changes and generate context-aware messages following the examples below.
When generating commit messages, analyze the actual code changes to infer business context. Don't just describe files—describe what the changes accomplish.
The scope should reflect the business module or feature, not just the directory:
| Scope Type | Example | When to Use |
|---|---|---|
| Feature/Module | companion, calendar, inbox | Changes to a specific product feature |
| Platform | ios, android, web | Platform-specific changes |
| Integration | outlook, gmail, slack | Third-party integration changes |
| Component | auth, api, db | Core infrastructure changes |
Example 1: New Feature
Input (code changes):
+ src/companion/pages/AvailabilityDetailPage.tsx
+ src/companion/pages/AvailabilityActionsPage.tsx
+ src/companion/components/AvailabilityCard.tsx
M src/companion/navigation/routes.ts
Output:
feat(companion): add availability detail and actions pages for ios
- New AvailabilityDetailPage showing time slot details
- New AvailabilityActionsPage for booking/canceling
- AvailabilityCard component for list display
- Updated navigation routes
Example 2: Bug Fix
Input (code changes):
M src/integrations/outlook/email_sender.py
M src/integrations/outlook/auth.py
Output:
fix(outlook): resolve email sending failures due to token expiration
Refresh OAuth token before sending when close to expiry
Example 3: Multi-platform Change
Input (code changes):
M ios/Calendar/CalendarView.swift
M android/calendar/CalendarFragment.kt
M web/src/calendar/Calendar.tsx
Output:
feat(calendar): add week view across all platforms
Implement consistent week view UI for iOS, Android, and web
Example 4: Chore/Maintenance
Input (code changes):
M package.json
M yarn.lock
M requirements.txt
Output:
chore(deps): update dependencies to latest versions
| Bad (Generic) | Good (Context-Aware) |
|---|---|
feat: add new file | feat(payments): add Stripe webhook handler |
fix: fix bug | fix(auth): prevent session timeout on mobile |
chore: update code | chore(ci): reduce build time with parallel jobs |
refactor: refactor utils | refactor(api): extract rate limiting to middleware |
Python error handling patterns for FastAPI, Pydantic, and asyncio. Follows "Let it crash" philosophy - raise exceptions, catch at boundaries. Covers HTTPException, global exception handlers, validation errors, background task failures. Use when: (1) Designing API error responses, (2) Handling RequestValidationError, (3) Managing async exceptions, (4) Preventing stack trace leakage, (5) Designing custom exception hierarchies.
Create professional Excalidraw diagrams by generating JSON directly. This skill provides the Excalidraw JSON schema reference and professional icon libraries for AI agents to autonomously create diagrams without templates.
Python backend development expertise for FastAPI, security patterns, database operations, Upstash integrations, and code quality. Use when: (1) Building REST APIs with FastAPI, (2) Implementing JWT/OAuth2 authentication, (3) Setting up SQLAlchemy/async databases, (4) Integrating Redis/Upstash caching, (5) Refactoring AI-generated Python code (deslopification), (6) Designing API patterns, or (7) Optimizing backend performance.
Structured observability with Pydantic Logfire and OpenTelemetry. Use when: (1) Adding traces/logs to Python APIs, (2) Instrumenting FastAPI, HTTPX, SQLAlchemy, or LLMs, (3) Setting up service metadata, (4) Configuring sampling or scrubbing sensitive data, (5) Testing observability code.
Pydantic models and validation. Use when: (1) Defining schemas, (2) Validating input/output, (3) Generating JSON schema.
Python linting with Ruff - an extremely fast linter written in Rust. Use when: (1) Standardizing code quality, (2) Fixing style warnings, (3) Enforcing rules in CI, (4) Replacing flake8/isort/pyupgrade/autoflake, (5) Configuring lint rules and suppressions.