git-commit-helper

Generate standardized git commit messages following Conventional Commits format. Use this skill when the user asks to commit code, write a commit message, or create a git commit. Enforces team conventions for type prefixes, scope naming, message length, and breaking change documentation.

3,891 stars
Complexity: easy

About this skill

This AI agent skill provides a comprehensive guide for generating Git commit messages that strictly adhere to the Conventional Commits specification. It outlines the required structure including `type`, `scope`, and `subject`, along with optional `body` and `footer` sections for detailed explanations or breaking change notifications. The skill defines specific rules for each component, such as allowed commit types (e.g., `feat`, `fix`, `docs`), how to determine the `scope` based on project modules, and formatting rules for the `subject` line (imperative mood, character limit). An AI agent can leverage this skill when tasked with committing code, drafting a commit message, or needing to enforce project-specific commit message standards. It serves as a robust internal guideline, enabling the agent to consistently produce high-quality, professional commit messages that facilitate automated tooling like changelog generation and semantic versioning. The primary benefit of using this skill is to maintain a clean, readable, and machine-parseable Git history, which is crucial for project maintainability, effective team collaboration, and automated release processes.

Best use case

The primary use case is automating the creation of professional, standardized Git commit messages whenever code changes are made. It helps developers, teams, and CI/CD systems maintain a consistent and meaningful project history, which is vital for changelog generation, version control, and streamlined code reviews.

Generate standardized git commit messages following Conventional Commits format. Use this skill when the user asks to commit code, write a commit message, or create a git commit. Enforces team conventions for type prefixes, scope naming, message length, and breaking change documentation.

A well-structured, conventional Git commit message is generated, ready for immediate use, fully compliant with predefined project standards.

Practical example

Example input

Generate a commit message for a new feature: added a user profile page with editable fields. It fixed a display bug on the homepage where user avatars weren't loading. No breaking changes.

Example output

feat(profile): add user profile page with editable fields

fix(homepage): resolve user avatar loading issue

When to use this skill

  • When the user asks to commit code or draft a new git commit message.
  • To ensure all commit messages strictly follow the Conventional Commits standard.
  • When enforcing consistent `type`, `scope`, and `subject` rules across a development team.
  • For projects that rely on commit messages for automated changelog generation or semantic versioning.

When not to use this skill

  • When a project explicitly does not follow the Conventional Commits specification.
  • When the user requires a free-form, informal commit message without specific formatting.
  • For non-code-related Git operations where a formal commit message isn't relevant.
  • If the AI agent lacks context about the project's modules (for `scope` determination).

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/git-cmt-helper/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/0xtresser/git-cmt-helper/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/git-cmt-helper/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How git-commit-helper Compares

Feature / Agentgit-commit-helperStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityeasyN/A

Frequently Asked Questions

What does this skill do?

Generate standardized git commit messages following Conventional Commits format. Use this skill when the user asks to commit code, write a commit message, or create a git commit. Enforces team conventions for type prefixes, scope naming, message length, and breaking change documentation.

How difficult is it to install?

The installation complexity is rated as easy. You can find the installation instructions above.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Git Commit Message Guide

## Format

Every commit message MUST follow this structure:

```
<type>(<scope>): <subject>

[optional body]

[optional footer]
```

## Type (required)

| Type | When to use |
|------|-------------|
| feat | New feature or capability |
| fix | Bug fix |
| docs | Documentation only |
| refactor | Code change that neither fixes nor adds |
| test | Adding or updating tests |
| chore | Build, CI, tooling changes |

## Scope (required)

Scope MUST be a real module name from this project.
See [references/modules.md](references/modules.md) for the full list.

If unsure of the scope, check the file paths being changed — the top-level directory is usually the correct scope.

## Subject (required)

- Imperative mood: "add feature" not "added feature"
- No period at the end
- Max 72 characters total (including type and scope prefix)
- Lowercase first letter

## Body (optional)

- Explain WHY, not WHAT (the diff shows what changed)
- Wrap at 72 characters
- Separate from subject with blank line

## Breaking Changes

If the commit introduces a breaking change, add footer:

```
BREAKING CHANGE: <description of what breaks and migration path>
```

## Examples

**Good:**

```
feat(auth): add JWT token refresh endpoint

Tokens now auto-refresh 5 minutes before expiry.
Previously users had to re-login after token expiration.
```

```
fix(parser): handle empty input without crashing
```

```
refactor(db): extract connection pooling to separate module

BREAKING CHANGE: DatabaseClient constructor no longer accepts
pool config. Use PoolConfig.create() instead.
```

**Bad:**

```
updated some stuff          ← no type, no scope, vague
feat: Add new Feature.      ← capitalized, period, missing scope
fix(misc): various fixes    ← "misc" is not a real module
```

Related Skills

Go Production Engineering

3891
from openclaw/skills

You are a Go production engineering expert. Follow this system for every Go project — from architecture decisions through production deployment. Apply phases sequentially for new projects; use individual phases as needed for existing codebases.

Coding & Development

Database Engineering Mastery

3891
from openclaw/skills

> Complete database design, optimization, migration, and operations system. From schema design to production monitoring — covers PostgreSQL, MySQL, SQLite, and general SQL patterns.

Coding & Development

afrexai-code-reviewer

3891
from openclaw/skills

Enterprise-grade code review agent. Reviews PRs, diffs, or code files for security vulnerabilities, performance issues, error handling gaps, architecture smells, and test coverage. Works with any language, any repo, no dependencies required.

Coding & Development

API Documentation Generator

3891
from openclaw/skills

Generate production-ready API documentation from endpoint descriptions. Outputs OpenAPI 3.0, markdown reference docs, and SDK quickstart guides.

Coding & Development

bili-rs

3891
from openclaw/skills

Development skill for bili-rs, a Rust CLI tool for Bilibili (B站). Use when implementing features, fixing bugs, or extending the bilibili-cli-rust codebase. Provides architecture conventions, API endpoints, coding patterns, and project-specific constraints. Triggers on tasks involving adding CLI commands, calling Bilibili APIs, handling authentication, implementing output formatting, or working with the layered cli/commands/client/payloads architecture.

Coding & Development

Puppeteer

3891
from openclaw/skills

Automate Chrome and Chromium with Puppeteer for scraping, testing, screenshots, and browser workflows.

Coding & Development

pharaoh

3891
from openclaw/skills

Codebase knowledge graph with 23 development workflow skills. Query architecture, dependencies, blast radius, dead code, and test coverage via MCP. Requires GitHub App installation (read-only repo access) and OAuth authentication. Connects to external MCP server at mcp.pharaoh.so.

Coding & Development

ask-claude

3891
from openclaw/skills

Delegate a task to Claude Code CLI and immediately report the result back in chat. Supports persistent sessions with full context memory. Safe execution: no data exfiltration, no external calls, file operations confined to workspace. Use when the user asks to run Claude, delegate a coding task, continue a previous Claude session, or any task benefiting from Claude Code's tools (file editing, code analysis, bash, etc.).

Coding & Development

bnbchain-mcp

3891
from openclaw/skills

Interact with the BNB Chain Model Context Protocol (MCP) server. Blocks, contracts, tokens, NFTs, wallet, Greenfield, and ERC-8004 agent tools. Use npx @bnb-chain/mcp@latest or read the official skill page.

Coding & Development

helius-phantom

3891
from openclaw/skills

Build frontend Solana applications with Phantom Connect SDK and Helius infrastructure. Covers React, React Native, and browser SDK integration, transaction signing via Helius Sender, API key proxying, token gating, NFT minting, crypto payments, real-time updates, and secure frontend architecture.

Coding & Development

micropython-skills/sensor

3891
from openclaw/skills

MicroPython sensor reading — DHT11/22, BME280, MPU6050, ADC, ultrasonic HC-SR04, photoresistor, generic I2C sensors.

Coding & Development

micropython-skills/network

3891
from openclaw/skills

MicroPython networking — WiFi STA/AP, HTTP requests, MQTT pub/sub, BLE, NTP time sync, WebSocket.

Coding & Development