dsh-git-commit
Run the following command in DeepSeek Harness:
dsh plugin install uckkk/dsh-git-commit
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install uckkk/dsh-git-commit in the DeepSeek Harness terminal to install this plugin. Full source code is available at https://github.com/uckkk/dsh-git-commit .
About this plugin
Deciding what to write in a commit message, whether to hand-edit the CHANGELOG, and which semver digit to bump are small frictions that quietly drain your focus before every git commit. dsh-git-commit folds these three chores into a pair of local tools. It inspects the current status changes and drafts a Conventional Commits message (feat, fix, docs, chore, style, or test) based on which files were touched. It reads the commit history, groups entries by type, and produces a clean CHANGELOG.md. It then applies SemVer rules to propose the next version: major when a BREAKING CHANGE or bang-notation is present, minor for any feat, patch otherwise. Everything runs locally with plain Node and git, no network calls or external services. The suggestions are heuristic defaults, so you can let the model polish them into more precise descriptions before committing. A good fit for solo developers and small teams who want a low-dependency, fully offline git workflow that links commit conventions, changelog upkeep, and versioning into one smooth pipeline.
Use Cases
- Draft a Conventional Commits message before pushing changes
- Auto-generate a grouped CHANGELOG.md ahead of a release
- Decide whether the next bump should be major, minor, or patch
Best For
- Solo or team developers who value consistent commit messages
- Small projects that need automated changelog upkeep
- Git users who prefer fully local, zero-network tooling
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.