DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to split your changes into clean Conventional Commits with Better Claude

Use /commit to group pending edits into Conventional Commits and push, commit only, or branch.

Who it is forA developer with a messy working tree of several unrelated edits who wants clear commit history without writing each message by hand.

The problemWriting separate, well-labeled commits for a batch of mixed changes takes time and is easy to skip.

The outcomeYour pending changes are split into Conventional Commits, and you choose whether to push, commit only, or create a new branch.

What you need first

  • Claude Code installed and running
  • Access to the /plugin command inside Claude Code
  • A git repository with changes to commit, for the Commit plugin
  • A system voice available on your computer, for the Narrator plugin

Steps

  1. Run /plugin marketplace add midudev/better-claude in Claude Code.
  2. Run /plugin install commit@better-claude.
  3. Make some changes in a git repository, then run /commit in Claude Code.
  4. Choose commit and push, commit only, or a new branch when asked.
  5. Review the split commits and messages that Claude proposes before you accept them.

Prompt for your agent

In the git repository at <repo-path>, with the better-claude commit plugin installed, run /commit and choose commit only. Expected output: one or more Conventional Commits covering the pending changes. Verify with git log that each commit message starts with a Conventional Commits type such as feat, fix or docs.

Caveat. The README does not describe how the commit split decides grouping, so review the proposed commits before accepting them.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page