- Home
- Skills
- Technical Documentation
- conventional commit rewriter
Works with the AI Agents you already use
conventional commit rewriter
Enforce strict Conventional Commit standards on messy diffs and developer notes without hallucinations.
$5
conventional commit rewriter
Example session with this skill installed
rewrite this: i fixed the login screen crash when the password field is empty and also updated the readme to include the new setup steps.
- Read your context and instructions
- Compiled the conventional commit rewriter
I have analyzed your input and identified two distinct changes. I recommend splitting these into two separate commits.
Recommended Commits
Commit 1
fix(ui): resolve crash on login screen with empty password
Commit 2
docs: update setup instructions in README
Reason
The first change addresses a specific bug in the UI, while the second is a documentation-only update.
Confidence
High
Notes
The scope (ui) was inferred from "login screen". If there is a more specific package name (e.g., auth-web), consider using that instead.
Next steps
- Stage the UI changes and apply the
fixcommit. - Stage the README changes and apply the
docscommit. - Push your changes.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Writing standardized commit messages is tedious, leading to inconsistent logs that break automated changelogs and make history hard to read. Developers often default to vague messages like "fixed bug" or "updates," losing the context of what actually changed.
What it does
- Converts informal developer notes or diff summaries into valid Conventional Commits.
- Identifies the correct commit type (feat, fix, refactor, etc.) based strictly on provided context.
- Formats breaking changes with the "!" indicator and appropriate footers without inventing migration details.
- Detects and suggests splitting multiple unrelated changes into separate commit messages.
- Flags ambiguity when the input lacks sufficient detail to determine a type or scope.
Why this beats prompting it yourself
Generic LLMs often hallucinate technical details, invent issue numbers, or guess commit types to appear helpful. This skill enforces strict anti-hallucination rules, ensuring your git history stays factual and your automated CI pipelines don't break due to malformed headers.
Use cases
- Turning a messy list of "last hour" changes into a structured set of commits.
- Standardizing commit messages across a team with varying levels of discipline.
- Ensuring breaking changes are properly flagged for automated semver tooling.
- Cleaning up a PR summary before merging into the main branch.
Known limitations
This is a text-rewriting utility. It cannot access your local repository, execute git commands, or analyze code unless the diff is explicitly pasted into the chat.
Requires manual copy-pasting of diffs or messages as it cannot access local git history. Does not perform code analysis or verify if the code actually works.
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 any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
Permissions
No special permissions declared or detected