OpenParable
Skip to content
← Back to skills

Clean Commits

Development
clean-commits

Clean Commits is an Agent Skill for development published in the Archive228/loopkit repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Turn messy WIP into clean, atomic commits with messages that explain why. Use before opening a PR.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/Archive228/loopkit/blob/HEAD/skills/clean-commits/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/clean-commits, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Clean Commits

  • Atomic — one logical change per commit. Refactor and behavior change go in separate commits.
  • Message — subject says WHAT in imperative ("Fix null pointer in user lookup"), body says WHY. "Fix bug" is useless.
  • Specific — "Fix login failing when email has uppercase chars" tells the next person exactly what happened.
  • Reorder/squash WIP and "fix typo" commits into the real changes (git rebase -i).
  • Never mix an unrelated fix into a feature commit. A good history is a debugging tool: git bisect and git blame only work if commits are atomic and messages explain intent.