- Home
- Skills
- Productivity
- Remove Claude Co-Author: Pro Commits in Your Language
More screenshots
Works with the AI Agents you already use
Remove Claude Co-Author: Pro Commits in Your Language
- **Activates on its own** — just say "commit", "commit my changes", "haz commit" or "save my work in git".
Free
Remove Claude Co-Author: Pro Commits in Your Language
Example session with this skill installed
commit my changes
- Read your context and instructions
- Compiled the remove claude co-author
Made 2 commits (no AI attribution, no push):
feat(auth): validar usuario en login y agregar refresh de token
- login lanza un error si no recibe usuario
- nueva función refresh para renovar el token vía /refresh
docs(readme): agregar instrucciones de instalación
Connects securely to your tools. The creator never sees your data.
About this skill
Your history, your name. Claude Code signs every commit with Co-Authored-By: Claude and every PR with "Generated with Claude Code". This skill makes commits that read like a senior engineer wrote them — and carry no AI attribution.
- Activates on its own — just say "commit", "commit my changes", "haz commit" or "save my work in git". Tested: 10/10 automatic activations across different phrasings in English and Spanish.
- Conventional Commits, done right —
feat,fix,refactor, scopes from your own history, imperative headers ≤72 chars, a body that explains why,BREAKING CHANGEfooters. - Atomic by default — mixed diffs get split into focused commits.
- Your language — messages follow the
languageyou set in Claude Code; spec keywords stay in English so tooling keeps working. - Validated — a bundled script strips AI trailers (Claude, Copilot, ChatGPT, Cursor, Codex, Gemini) and rejects malformed headers before the commit lands. Human co-authors are kept.
- Permanent, if you want — one command installs a
commit-msghook that cleans every commit in the repo, even ones made by hand or other tools. It chains your existing hook and works without the skill. - Safe — never commits secrets, never skips your hooks with
--no-verify, never pushes unless you ask.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Productivity.
Does not push or open PRs unless asked. Does not rewrite commits that were already pushed. Language detection reads Claude Code's language setting only; other agents default to English.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
This skill has been used 1 time.
Trust & safety
Security scan
Security scan passed 7 days ago
- Free with an Agensi account
- Software
GitBash (macOS, Linux or WSL)
- Optional
- jq
Permissions
File Scopes
No network access. Never pushes unless asked.