- Home
- Skills
- APIs & Backend
- commit push
commit push
Automate structured Git commits and pushes with mandatory type-prefixed subjects and descriptive bodies.
Free
Works with the AI Agents you already use
commit push
Example session with this skill installed
Commit my staged changes using the refactor type and push it to the remote.
- Read your context and instructions
- Compiled the commit push
I have analyzed your staged changes, which involve separating the validation logic from the request orchestration in the billing service. I have committed these changes using git-cz and pushed the branch to the remote.
Git Workflow Execution
| Action | Detail | Result |
|---|---|---|
| Branch | feature/billing-update | Verified |
| Commit Type | refactor | Applied |
| Tool Used | git-cz --non-interactive | Success |
| Commit Subject | refactor: split billing service validation logic | Validated |
| Push Status | origin feature/billing-update | Pushed |
Commit Message Detail:
refactor: split billing service validation logic
Separates billing validation from request orchestration so the rules are easier to reuse and maintain. This change moves the logic into a dedicated validator class to improve testability.
Next steps
- Verify the new commit appears in your remote repository history.
- Continue with the next task now that the billing service is refactored.
- Open a Pull Request if the feature is ready for review.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop wrestling with inconsistent Git histories and missing context in commit logs. This skill enforces a strict, structured commit and push workflow that ensures every change is documented with both a mandatory type-prefixed subject and a detailed body. It automates the verification of staged changes, checks for advanced tooling like git-cz, and handles upstream tracking during the push process.
What it does
- Enforces commit structure by requiring a lowercase type, a specific colon format, and a mandatory descriptive body paragraph.
- Validates staged changes by inspecting the active diff before committing to ensure the intent matches the generated message.
- Selects optimal tools by checking for
git-czpresence and defaulting to non-interactive mode for automation-friendly commits. - Handles remote synchronization by pushing the active branch and automatically setting upstream tracking if it is missing.
- Prevents empty bodies by verifying the final commit message contains a description before allowing the push to execute.
How it works
- Inspection: The agent verifies the Git environment, identifies the current branch, and confirms changes are staged.
- Analysis: It reviews the staged diff to categorize the work into allowed types like
feat,fix, orrefactor. - Execution: It generates the structured message and commits using
git-cz(preferred) orgit commitwith multiple-mflags. - Verification: It performs a final check on the commit log to ensure the body was not dropped before pushing to the remote.
Frameworks & tools
This skill works with standard Git environments and is optimized for repositories using git-cz (Commitizen).
Why this beats prompting it yourself
Generic prompts often produce one-line commits or inconsistent prefixes. This skill strictly enforces a two-part message structure and performs a pre-push safety check to ensure your repository history remains clean, searchable, and compliant with professional standards.
Use cases
- Enforcing structured commit messages across a distributed development team.
- Automating the commit-and-push flow during rapid development cycles.
- Ensuring every production
hotfixhas a mandatory explanation in the Git log. - Standardizing branch upstream configuration for new local branches.
Known limitations
Does not support automatic file staging; changes must be staged before invocation. Only supports five specific commit types and forbids scope usage.
Requires changes to be staged manually first. Limited to five specific commit types: feat, fix, hotfix, test, refactor. No support for commit scopes.
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
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 16 days ago
- Free with an Agensi account
Requires