Skip to content
Development
Skill

/commit

Create well-formatted commits with conventional commit messages and emoji

From plugin
context-engineering-kit
1.8k68 skills21 agents1 command

Claude Code

$ npx -y skills add NeoLabHQ/context-engineering-kit --skill commit --agent claude-code

SKILL.md

commit.SKILL.md
name: commit
description: Create well-formatted commits with conventional commit messages and emoji

Claude Command: Commit

Your job is to create well-formatted commits with conventional commit messages and emoji.

Instructions

CRITICAL: Perform the following steps exactly as described:

1. **Branch check**: Checks if current branch is `master` or `main`. If so, asks the user whether to create a separate branch before committing. If user confirms a new branch is needed, creates one using the pattern `<type>/<username>/<description>` (e.g., `feature/leovs09/add-new-command`) 2. Unless specified with `--no-verify`, automatically runs pre-commit checks like `pnpm lint` or simular depending on the project language. 3. Checks which files are staged with `git status` 4. If 0 files are staged, automatically adds all modified and new files with `git add` 5. Performs a `git diff` to understand what changes are being committed 6. Analyzes the diff to determine if multiple distinct logical changes are present 7. If multiple distinct changes are detected, suggests breaking the commit into multiple smaller commits 8. For each commit (or the single commit if not split), creates a commit message using emoji conventional commit format

Best Practices for Commits

  • **Verify before committing**: Ensure code is linted, builds correctly, and documentation is updated
  • **Atomic commits**: Each commit should contain related changes that serve a single purpose
  • **Split large changes**: If changes touch multiple concerns, split them into separate commits
  • **Conventional commit format**: Use the format `<type>: <description>` where type is one of:
  • `feat`: A new feature
  • `fix`: A bug fix
  • `docs`: Documentation changes
  • `style`: Code style changes (formatting, etc)
  • `refactor`: Code changes that neither fix bugs nor add features
  • `perf`: Performance improvements
  • `test`: Adding or fixing tests
  • `chore`: Changes to the build process, tools, etc.
  • **Present tense, imperative mood**: Write commit messages as commands (e.g., "add feature" not "added feature")
  • **Concise first line**: Keep the first line under 72 characters
  • **Emoji**: Each commit type is paired with an appropriate emoji:
  • โœจ `feat`: New feature
  • ๐Ÿ› `fix`: Bug fix
  • ๐Ÿ“ `docs`: Documentation
  • ๐Ÿ’„ `style`: Formatting/style
  • โ™ป๏ธ `refactor`: Code refactoring
  • โšก๏ธ `perf`: Performance improvements
  • โœ… `test`: Tests
  • ๐Ÿ”ง `chore`: Tooling, configuration
  • ๐Ÿš€ `ci`: CI/CD improvements
  • ๐Ÿ—‘๏ธ `revert`: Reverting changes
  • ๐Ÿงช `test`: Add a failing test
  • ๐Ÿšจ `fix`: Fix compiler/linter warnings
  • ๐Ÿ”’๏ธ `fix`: Fix security issues
  • ๐Ÿ‘ฅ `chore`: Add or update contributors
  • ๐Ÿšš `refactor`: Move or rename resources
  • ๐Ÿ—๏ธ `refactor`: Make architectural changes
  • ๐Ÿ”€ `chore`: Merge branches
  • ๐Ÿ“ฆ๏ธ `chore`: Add or update compiled files or packages
  • โž• `chore`: Add a dependency
  • โž– `chore`: Remove a dependency
  • ๐ŸŒฑ `chore`: Add or update seed files
  • ๐Ÿง‘โ€๐Ÿ’ป `chore`: Improve developer experience
  • ๐Ÿงต `feat`: Add or update code related to multithreading or concurrency
  • ๐Ÿ”๏ธ `feat`: Improve SEO
  • ๐Ÿท๏ธ `feat`: Add or update types
  • ๐Ÿ’ฌ `feat`: Add or update text and literals
  • ๐ŸŒ `feat`: Internationalization and localization
  • ๐Ÿ‘” `feat`: Add or update business logic
  • ๐Ÿ“ฑ `feat`: Work on responsive design
  • ๐Ÿšธ `feat`: Improve user experience / usability
  • ๐Ÿฉน `fix`: Simple fix for a non-critical issue
  • ๐Ÿฅ… `fix`: Catch errors
  • ๐Ÿ‘ฝ๏ธ `fix`: Update code due to external API changes
  • ๐Ÿ”ฅ `fix`: Remove code or files
  • ๐ŸŽจ `style`: Improve structure/format of the code
  • ๐Ÿš‘๏ธ `fix`: Critical hotfix
  • ๐ŸŽ‰ `chore`: Begin a project
  • ๐Ÿ”– `chore`: Release/Version tags
  • ๐Ÿšง `wip`: Work in progress
  • ๐Ÿ’š `fix`: Fix CI build
  • ๐Ÿ“Œ `chore`: Pin dependencies to specific versions
  • ๐Ÿ‘ท `ci`: Add or update CI build system
  • ๐Ÿ“ˆ `feat`: Add or update analytics or tracking code
  • โœ๏ธ `fix`: Fix typos
  • โช๏ธ `revert`: Revert changes
  • ๐Ÿ“„ `chore`: Add or update license
  • ๐Ÿ’ฅ `feat`: Introduce breaking changes
  • ๐Ÿฑ `assets`: Add or update assets
  • โ™ฟ๏ธ `feat`: Improve accessibility
  • ๐Ÿ’ก `docs`: Add or update comments in source code
  • ๐Ÿ—ƒ๏ธ `db`: Perform database related changes
  • ๐Ÿ”Š `feat`: Add or update logs
  • ๐Ÿ”‡ `fix`: Remove logs
  • ๐Ÿคก `test`: Mock things
  • ๐Ÿฅš `feat`: Add or update an easter egg
  • ๐Ÿ™ˆ `chore`: Add or update .gitignore file
  • ๐Ÿ“ธ `test`: Add or update snapshots
  • โš—๏ธ `experiment`: Perform experiments
  • ๐Ÿšฉ `feat`: Add, update, or remove feature flags
  • ๐Ÿ’ซ `ui`: Add or update animations and transitions
  • โšฐ๏ธ `refactor`: Remove dead code
  • ๐Ÿฆบ `feat`: Add or update code related to validation
  • โœˆ๏ธ `feat`: Improve offline support

Guidelines for Splitting Commits

When analyzing the diff, consider splitting commits based on these criteria:

1. **Different concerns**: Changes to unrelated parts of the codebase 2. **Different types of changes**: Mixing features, fixes, refactoring, etc. 3. **File patterns**: Changes to different types of files (e.g., source code vs documentation) 4. **Logical grouping**: Changes that would be easier to understand or review separately 5. **Size**: Very large changes that would be clearer if broken down

Examples

Good commit messages:

  • โœจ feat: add user authentication system
  • ๐Ÿ› fix: resolve memory leak in rendering process
  • ๐Ÿ“ docs: update API documentation with new endpoints
  • โ™ป๏ธ refactor: simplify error handling logic in parser
  • ๐Ÿšจ fix: resolve linter warnings in component files
  • ๐Ÿง‘โ€๐Ÿ’ป chore: improve developer tooling setup process
  • ๐Ÿ‘” feat: implement business logic for transaction validation
  • ๐Ÿฉน fix: address minor styling inconsistency in header
  • ๐Ÿš‘๏ธ fix: patch critical security vulnerability in auth flow
  • ๐ŸŽจ style: reorganize component structure for better readability
  • ๐Ÿ”ฅ fix: remove deprecated legacy code
  • ๐Ÿฆบ feat: add input validation for user registration form
  • ๐Ÿ’š fix: resolve failing CI pipe
Read more
@neolabhq
Ships withcontext-engineering-kit

A hand-crafted collection of advanced context engineering techniques and patterns with minimal token footprint, focused on improving agent result quality and predictability.

1.8k68 skills21 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
1.8k
Star history of NeoLabHQ/context-engineering-kit on GitHub, a chart by star-history.com

Other skills on context-engineering-kit.

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, orโ€ฆ

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills2w309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android โ€” semantic ARIA roles and labels,โ€ฆ

ecc2w293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commitsโ€ฆ

react5d252k
@facebook@facebookInstall Skill

Questions about commit.

Which coding agents can use commit?
commit installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.