Agent skill
commit-staged
Generate descriptive commit messages by analyzing git diffs, very fast and context-pollution safe. Use when the user asks to commit staged changes or needs a conventional-commits message generated from the current diff.
Install this agent skill to your Project
npx add-skill https://github.com/Jamie-BitFlight/claude_skills/tree/main/.claude/skills/commit-staged
SKILL.md
Analyze these staged changes and generate commit message, then commit the changes:
!uv run prek run >/dev/null 2>&1 || git add -u
!git --no-pager status || true
!git --no-pager diff --cached || true
!git --no-pager diff --cached --stat || true
<user_notes> $ARGUMENTS </user_notes>
Commit message format
Follow conventional commits format (no footer, except for breaking change footer):
<type>(<scope>): <description>
[optional body]
Types
- feat: New feature
- fix: Bug fix
- docs: Documentation changes
- style: Code style changes (formatting, missing semicolons)
- refactor: Code refactoring
- test: Adding or updating tests
- chore: Maintenance tasks
Examples
Feature commit:
feat(auth): add JWT authentication
Implement JWT-based authentication system with:
- Login endpoint with token generation
- Token validation middleware
- Refresh token support
Bug fix:
fix(api): handle null values in user profile
Prevent crashes when user profile fields are null.
Add null checks before accessing nested properties.
Refactor:
refactor(database): simplify query builder
Extract common query patterns into reusable functions.
Reduce code duplication in database layer.
Commit message guidelines
DO:
- Use imperative mood ("add feature" not "added feature")
- Keep first line under 50 characters
- Capitalize first letter
- No period at end of summary
- Explain WHY not just WHAT in body
DON'T:
- Use vague messages like "update" or "fix stuff"
- Include technical implementation details in summary
- Write paragraphs in summary line
- Use past tense
Multi-file commits
When committing multiple related changes:
refactor(core): restructure authentication module
- Move auth logic from controllers to service layer
- Extract validation into separate validators
- Update tests to use new structure
- Add integration tests for auth flow
Breaking change: Auth service now requires config object
Scope Rules
Scope MUST identify WHERE in the codebase, NOT what type of change.
The scope is a module, component, or directory name - never a description of the change itself.
Determining Scope
-
Single module/directory: Use that module name
- Changes to
src/auth/*.py→auth - Changes to
plugins/gitlab-skill/→gitlab-skill
- Changes to
-
Multiple files in same area: Use the common parent
- Changes to
skills/python3-dev/assets/*.py→assetsorpython3-dev
- Changes to
-
Cross-cutting changes: Use the primary affected area OR omit scope
- Config + code changes → use primary area:
feat(auth): add OAuth support - Truly scattered changes → omit:
chore: update dependencies across modules
- Config + code changes → use primary area:
-
Root config files: Use the config type
pyproject.tomllinting rules →lintorruffpyproject.tomldependencies →deps.github/workflows/→ci
Scope Anti-Patterns
NEVER use these as scopes - they describe WHAT, not WHERE:
| ❌ Wrong | ✅ Correct | Why |
|---|---|---|
docs |
readme, api-docs, skills |
"docs" is a change type, not a location |
tests |
auth-tests, api |
Be specific about what's being tested |
types |
models, api |
Types belong to a module |
refactor |
(use as type, not scope) | "refactor" is a type, not a location |
bugfix |
(use fix as type) |
"bugfix" is a type, not a location |
Scope Examples
By domain:
feat(auth): add JWT authenticationfix(payments): handle currency conversionrefactor(users): extract validation logic
By layer:
feat(api): add user profile endpointfix(db): resolve connection pool leakchore(ci): update Node version to 20
By plugin/skill:
feat(gitlab-skill): add MR approval supportfix(python3-dev): correct shebang detectiondocs(commit-staged): clarify scope selection
Breaking changes
Indicate breaking changes clearly:
feat(api)!: restructure API response format
BREAKING CHANGE: All API responses now follow JSON:API spec
Previous format:
{ "data": {...}, "status": "ok" }
New format:
{ "data": {...}, "meta": {...} }
Migration guide: Update client code to handle new response structure
Template workflow
- Review changes:
git diff --staged - Identify type: Is it feat, fix, refactor, etc.?
- Determine scope: What part of the codebase?
- Write summary: Brief, imperative description
- Add body: Explain why and what impact
- Note breaking changes: If applicable
Interactive commit helper
Use git add -p for selective staging:
# Stage changes interactively
git add -p
# Review what's staged
git diff --staged
# Commit with message
git commit -m "type(scope): description"
Amending commits
Fix the last commit message:
# Amend commit message only
git commit --amend
# Amend and add more changes
git add forgotten-file.js
git commit --amend --no-edit
Best practices
- Atomic commits - One logical change per commit
- Test before commit - Ensure code works
- Reference issues - Include issue numbers if applicable
- Keep it focused - Don't mix unrelated changes
- Write for humans - Future you will read this
Commit message checklist
- Type is appropriate (feat/fix/docs/etc.)
- Scope identifies WHERE (module/directory), NOT what type of change
- Scope is NOT a banned word:
docs,tests,types,refactor,bugfix - Summary is under 50 characters
- Summary uses imperative mood
- Body explains WHY not just WHAT
- Breaking changes are clearly marked
- Related issue numbers are included
Finally, you will commit the changes with the generated commit message, without using --no-verify:
git commit -m "<commit-message>"
If you are blocked by a pre-commit or prek hook, you should stop, and announce your intended commit message, and that it was blocked, and requires a linting-agent to be run against the issues found.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the index', 'ccc', 'cocoindex-code'.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
delegate
Quick delegation template for sub-agent prompts. Use when assigning work to a sub-agent, before invoking the Agent tool, or when preparing prompts for specialized agents. Provides the WHERE-WHAT-WHY framework. For comprehensive delegation guidance, activate the agent-orchestration how-to-delegate skill.
swarm-spawning
Spawn agents and teammates in Claude Code swarms. Use when choosing between subagents vs teammates, selecting agent types (Explore, Plan, general-purpose, plugin agents), configuring spawn backends (in-process, tmux, iterm2), or setting environment variables for spawned agents.
knowledge-explorer
Manage the research/ knowledge base (KB) of tool and library research entries. Use when browsing KB topics, adding new research entries, updating existing entries with dated revisions, fetching GitHub repo metadata into a draft KB entry, or migrating old-format entries to skill-spec frontmatter. Triggers on tasks like "what do we have on X", "add this to the KB", "update the KB entry for Y", "fetch github info for owner/repo", or "migrate old entries".
design-anti-patterns
Enforce anti-AI UI design rules based on the Uncodixfy methodology. Use when generating HTML, CSS, React, Vue, Svelte, or any frontend UI code. Prevents "Codex UI" — the generic AI aesthetic of soft gradients, floating panels, oversized rounded corners, glassmorphism, hero sections in dashboards, and decorative copy. Applies constraints from Linear/Raycast/Stripe/GitHub design philosophy: functional, honest, human-designed interfaces. Triggers on: UI generation, dashboard building, frontend component creation, CSS styling, landing page design, or any task producing visual interface code.
Didn't find tool you were looking for?