Skip to content
Back to skills

Commit

ASecurity

Atomic, semantic-boundary git commit workflow

  • 20 stars
  • 0 votes
  • 0 copies
  • 4 views
  • Added September 12, 2026
securitygitdocumentation

Security analysis

A100/100

Scanned September 12, 2026

npx -y skills add dirien/yet-another-agent-harness --skill commit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Commit?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Commit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/dirien-commit/badge)](https://www.skillsdirectory.com/skills/dirien-commit)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: commit
description: "Atomic, semantic-boundary git commit workflow"
---

# /commit — Atomic Commit Workflow

## When to use
When the user runs /commit or asks to commit changes.

## Steps

1. Run `git status` and `git diff --staged` to understand what's changed
2. If nothing is staged, identify logical change groups and stage them separately
3. Write a commit message following Conventional Commits:
   - feat: new feature
   - fix: bug fix
   - refactor: code restructuring
   - docs: documentation
   - test: tests
   - chore: tooling/build
4. Use the imperative mood in the subject line
5. Keep subject under 72 characters
6. Add body with "why" not "what" if the change isn't self-evident
7. Create the commit using a heredoc for the message
8. Run `git status` to verify

## Rules
- NEVER use --no-verify or --amend unless explicitly asked
- NEVER stage .env, credentials, or secret files
- Prefer multiple small commits over one large commit
- Each commit should compile and pass tests independently

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.