commit · parcadei — Claude Code skill: git commits without Claude Code
This skill turns session changes into git commits, shows you the plan first, and keeps Claude's name out of the messages. Handy when an agent has piled up edits.
npx skills add parcadei/Continuous-Claude-v3 --skill commit -a claude-codeWhat commit does
The skill reviews what happened during the session, runs git status and git diff, then decides whether the changes belong in one commit or several logical ones. Files get grouped by purpose, and each message is drafted in imperative mood with the reason for the change, not just the diff.
You see the plan before anything runs: which files go into each commit and what the message says. It asks for approval and waits. On confirmation, files are staged by name with git add — never -A or . — and the result shows up in git log --oneline. Attribution stays yours: no Co-Authored-By lines, no notes about generation.
After each commit it runs bash "$CLAUDE_PROJECT_DIR/.claude/scripts/generate-reasoning.sh" <commit-hash> "<commit-message>", which writes notes to .git/claude/commits/<hash>/reasoning.md covering what was tried along the way, failed builds included. If that script is missing from your project, the reasoning step has nothing to call.
What it helps with
- split a session's edits into several logical commits
- write a commit message around why the change was made
- get user approval before anything is committed
- strip AI attribution from commit history
- keep development notes next to each commit
Example prompts for the agent
- commit the changes from this session
- break these edits into separate commits and show me the plan
- make the commit but leave Claude out of the message
How to install commit
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill commit -a claude-code2Manually: put the files in place
~/.claude/skills/commit/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/commit/
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill commit -a codex2Manually: put the files in place
.agents/skills/commit/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill commit -a cursor2Manually: put the files in place
.cursor/skills/commit/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install parcadei/Continuous-Claude-v3 commit2Manually: put the files in place
.github/skills/commit/SKILL.md1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill commit -a gemini-cli2Platform CLI
gemini skills install https://github.com/parcadei/Continuous-Claude-v3 --path .claude/skills/commitManually: put the files in place
.devin/skills/commit/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill commit -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about commit
How do I install the commit skill in Claude?
Run npx skills add parcadei/Continuous-Claude-v3 --skill commit -a claude-code. It lands at ~/.claude/skills/commit/SKILL.md.
What does the commit skill do?
It inspects the session's changes, proposes a commit plan with messages, waits for your approval, and commits the selected files. Authorship stays with you.
Why is there no Claude attribution in the commits?
The skill forbids it: no Co-Authored-By lines and no generated-with messages, and the text reads as if you wrote it.
Source text
SKILL.md · MIT
--- name: commit description: Create git commits with user approval and no Claude attribution --- # Commit Changes You are tasked with creating git commits for the changes made during this session. ## Process: 1. **Think about what changed:** - Review the conversation history and understand what was accomplished - Run `git status` to see current changes - Run `git diff` to understand the modifications - Consider whether changes should be one commit or multiple logical commits 2. **Plan your commit(s):** - Identify which files belong together - Draft clear, descriptive commit messages - Use imperative mood in commit messages - Focus on why the changes were made, not just what 3. **Present your plan to the user:** - List the files you plan to add for each commit - Show the commit message(s) you'll use - Ask: "I plan to create [N] commit(s) with these changes. Shall I proceed?" 4. **Execute upon confirmation:** - Use `git add` with specific files (never use `-A` or `.`) - Create commits with your planned messages - Show the result with `git log --oneline -n [number]` 5. **Generate reasoning (after each commit):** - Run: `bash "$CLAUDE_PROJECT_DIR/.claude/scripts/generate-reasoning.sh" <commit-hash> "<commit-message>"` - This captures what was tried during development (build failures, fixes) - The reasoning file helps future sessions understand past decisions - Stored in `.git/claude/commits/<hash>/reasoning.md` ## Important: - **NEVER add co-author information or Claude attribution** - Commits should be authored solely by the user - Do not include any "Generated with Claude" messages - Do not add "Co-Authored-By" lines - Write commit messages as if the user wrote them ## Remember: - You have the full context of what was done in this session - Group related changes together - Keep commits focused and atomic when possible - The user trusts your judgment - they asked you to commit
© parcadei · MIT · parcadei/Continuous-Claude-v3
Similar skills
All skills for Git and GitHub →commit by other authors comes first.