Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From Git
Creates a conventional git commit using git-agent. This skill should be used when the user requests "commit", "git commit", "create commit", or wants to commit staged and unstaged changes following the conventional commits format. The executing AI auto-derives its own co-author string from its runtime model identity (e.g., `Claude Opus 4.7 <[email protected]>`) and passes it to `--co-author`. `$ARGUMENTS`, if provided, overrides the auto-derived value.
How this skill is triggered — by the user, by Claude, or both
Slash command
/git:commit <co-author><co-author>This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
CRITICAL:
CRITICAL:
git status, git diff, git log, or any other commands before git-agent commit.--co-author to git-agent commit. If $ARGUMENTS is non-empty, use it verbatim. Otherwise self-derive from your own runtime model identity (the model named in your own system prompt) plus <[email protected]> — e.g., Claude Opus 4.7 <[email protected]>. Never run a commit without --co-author.<co-author>: if $ARGUMENTS is non-empty use it verbatim; otherwise build <your-running-model> <[email protected]> from your own runtime identity.git-agent commit --intent "<intent>" --co-author "<co-author>"--free appended; keep the --co-author flag.git commit with Conventional Commits format via HEREDOC, including a Co-Authored-By: <co-author> trailer in the message body.CLI reference: ${CLAUDE_PLUGIN_ROOT}/references/cli.md
npx claudepluginhub est7/dotclaude --plugin gitCreates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.