commit
Stage, commit, and push changes with conventional commit style. Creates meaningful commit messages and clean git history.
Best use case
commit is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Stage, commit, and push changes with conventional commit style. Creates meaningful commit messages and clean git history.
Teams using commit should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/commit/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How commit Compares
| Feature / Agent | commit | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Stage, commit, and push changes with conventional commit style. Creates meaningful commit messages and clean git history.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Commit Skill Professional git workflow with conventional commits. ## When to Activate This skill is relevant when: - Staging and committing code changes - Creating meaningful commit messages - Following conventional commit standards - Maintaining clean git history ## Core Principles ### Clean History - Commits tell a story - Make them meaningful and descriptive - Each commit is a logical unit - Easy to understand in hindsight ### Conventional Commits - Use standard prefixes consistently - `feat:` for new features - `fix:` for bug fixes - `chore:` for maintenance - `docs:` for documentation - `refactor:` for code restructuring - `test:` for test changes ### Atomic Changes - Each commit = single logical change - Don't mix unrelated changes - Makes reverting easier - Simplifies code review ### Pre-Commit Verification - All tests should pass - Code has been reviewed - No broken functionality - Build succeeds ## Quick Checks Before committing, verify: - [ ] All changes are intentional - [ ] Tests pass locally - [ ] Code has been reviewed (or self-reviewed) - [ ] Commit message follows conventional format - [ ] Message describes "why" not just "what" - [ ] No sensitive data included (credentials, keys) - [ ] No debug code or console.logs left behind - [ ] Related changes grouped together - [ ] Unrelated changes separated - [ ] Breaking changes documented
Related Skills
wireframe
Create markdown wireframes with detailed UX descriptions from a product specification. Senior UX Designer perspective inspired by Notion and Linear.
ux_redesign
Redesign a feature or page from a Principal UX Designer's perspective.
tech_review
Senior Principal Engineer performing thorough technical review of implementation plans before development.
tasks
Break down an approved implementation plan into specific, actionable tasks.
specify
Create a product specification that defines what to build and why, without prescribing how.
skeptical_review
Perform a critical, skeptical code review of the project from the perspective of a Principal Engineer.
security_agent
Perform a full security review of the codebase (Node.js & React focus).
review_plan
Review the technical implementation plan against the specification.
review_domain
Perform a thorough architectural review of a domain model.
review_constitution
Review and stress-test the technical constitution after /constitute.
retro
Reflect on the completed feature, document lessons learned, and improve workflows.
release_gate
Final Go/No-Go check and release preparation.