- Home
- Skills
- Code Quality & Review
- Git Commit Writer
Works with the AI Agents you already use
Git Commit Writer
Generate precise Conventional Commit messages by analyzing staged Git diffs.
$9.99
Git Commit Writer
Example session with this skill installed
Review my staged changes and write a Conventional Commit message: I renamed the 'auth_token' field to 'session_key' in the public API and updated the login logic.
- Read your context and instructions
- Compiled the git commit writer
I have analyzed the change involving the renaming of the public API field. This is a breaking change because it modifies the public interface.
Recommended commit
feat(api)!: rename auth_token to session_key
BREAKING CHANGE: The `auth_token` field has been renamed to `session_key`.
All API consumers must update their request/response handling to use the new field name.
Why
- Type: feat (adds/modifies system functionality).
- Scope: api (inferred from the field location).
- Breaking change: yes, the field rename is a breaking change for public API consumers.
Next steps
- Copy the recommended message.
- Run
git commit -m "feat(api)!: rename auth_token to session_key" -m "BREAKING CHANGE: ..."or paste into your git client. - Verify that all related documentation reflects the field name change.
Connects securely to your tools. The creator never sees your data.
About this skill
Writing meaningful commit messages is a chore that often leads to lazy "update code" summaries. This skill automates the analysis of staged Git changes to generate precise, Conventional Commit compliant messages that actually describe the functional intent of your work.
What it does
- Diff analysis summarizes the functional intent of staged changes based on
git diff --cachedand file structure. - Type selection assigns the correct Conventional Commit type like
feat,fix,refactor, orperfbased on behavioral evidence. - Scope inference extracts relevant component or package names from filenames to provide specific context.
- Breaking change detection identifies API-breaking modifications and adds the
!indicator and footer only when justified. - Message formatting produces concise subjects under 72 characters using imperative mood and proper casing.
How it works
- Provide the output of
git diff --cachedor your repository context to the agent. - The skill analyzes the diff to identify if the change is a feature, bug fix, or maintenance task.
- It generates a recommended commit message along with a brief explanation of the chosen type and scope.
- If the changes are complex, it provides an optional body or footer for extra clarity.
Frameworks & tools
This skill works with any project using Git and follows the Conventional Commits 1.0.0 specification. It integrates well with tools like git status, git diff, and CLI-based agent environments.
Why this beats prompting it yourself
Generic prompts often hallucinate issue numbers or default to chore for everything. This skill uses a strict logic gate to distinguish between refactor, style, and perf while ensuring breaking change flags are only used when evidence supports an incompatible API change.
Use cases
- Generating standardized commit messages for teams following Conventional Commits.
- Drafting breaking change footers that explain migration steps for library consumers.
- Summarizing large diffs into concise, readable subject lines for PR history.
Known limitations
It cannot create, amend, or push commits directly. It requires the user to provide the staged diff or repository access to function.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.
Cannot execute git commands like commit or push. Requires staged diff input. Does not invent issue numbers or credentials.
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
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 23 days ago
- Software
Git