Git Commit logo

Git Commit

Community
decebals
git-commit

Generate conventional commit messages for Java projects. Use when user says "commit", "create commit", "commit changes", or after completing code changes that need to be committed.

Overview

Publisherdecebals
Repositoryclaude-code-java
Skill namegit-commit
Stars
751
Forks
151
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by decebals on GitHub. Read the source before you install it.

Installation

Install the Git Commit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/decebals/claude-code-java/tree/main/skills/git-commit
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/decebals/claude-code-java.git /tmp/claude-code-java
mkdir -p .claude/skills
cp -r /tmp/claude-code-java/skills/git-commit .claude/skills/git-commit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Git Commit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Git Commit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Git Commit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Git Commit Message Skill

Generate conventional, informative commit messages for Java projects.

When to Use

  • After making code changes
  • User says "commit this" / "commit changes" / "create commit"
  • Before creating PRs

Format Standard

Use Conventional Commits format:

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

<body>

<footer>

Types (Java context)

  • feat: New feature (new API, new functionality)
  • fix: Bug fix
  • refactor: Code refactoring (no functional change)
  • test: Add/update tests
  • docs: Documentation only
  • perf: Performance improvement
  • build: Maven/Gradle changes
  • chore: Maintenance (dependency updates, etc)

Scope Examples (Java specific)

  • Module name: core, api, plugin-loader
  • Component: PluginManager, ExtensionFactory
  • Area: lifecycle, dependencies, security

Subject Rules

  • Imperative mood: "Add support" not "Added support"
  • No period at end
  • Max 50 chars
  • Lowercase after type

Body (optional but recommended)

  • Explain WHAT and WHY, not HOW
  • Wrap at 72 chars
  • Reference issues: "Fixes #123" / "Relates to #456"

Examples

Simple fix

fix(plugin-loader): prevent NPE when plugin directory is missing

Check for null before accessing plugin directory to avoid
NullPointerException during initialization.

Fixes #234

Feature with breaking change

feat(api): add support for plugin dependencies versioning

BREAKING CHANGE: PluginDescriptor now requires semantic versioning
format (x.y.z) instead of free-form version strings.

Closes #567

Refactoring

refactor(core): extract plugin validation logic

Move validation logic from PluginManager to separate
PluginValidator class for better testability and separation
of concerns.

Test addition

test(plugin-loader): add integration tests for plugin loading

Add comprehensive integration tests covering:
- Loading from directory
- Loading from JAR
- Error handling for invalid plugins

Build/dependency update

build(deps): upgrade Spring Boot to 3.2.1

Update Spring Boot from 3.1.0 to 3.2.1 for security patches
and performance improvements.

Workflow

  1. Analyze changes using git diff --staged
  2. Identify scope from modified files
  3. Determine type based on change nature
  4. Generate message following format
  5. Execute commit: git commit -m "message"

Token Optimization

  • Read staged changes ONCE: git diff --staged --stat + targeted file diffs
  • Don't read entire files unless necessary
  • Use concise body - aim for 2-3 lines max
  • Batch multiple small changes into logical commits

Anti-patterns

❌ Avoid:

  • "fix stuff" / "update code" / "changes"
  • "WIP" commits (unless explicitly requested)
  • Mixing unrelated changes (use separate commits)
  • Over-detailed technical implementation in message

✅ Good commits:

  • Single logical change
  • Clear, searchable subject
  • References issues when applicable
  • Explains business value

Integration with GitHub

After commit, suggest next steps:

  • "Push changes?"
  • "Create PR for issue #X?"
  • "Continue with next task?"

Common Patterns for Java Projects

Adding new functionality

feat(extension): add support for prioritized extensions

Allow extensions to specify priority order for execution.
Extensions with higher priority run first.

Closes #123

Fixing bugs

fix(classloader): resolve resource lookup in nested JARs

ClassLoader.getResource() was failing for resources in
JARs loaded from plugin JARs (nested JARs). Fixed by
implementing proper resource resolution chain.

Fixes #456

Dependency updates

build(deps): bump slf4j from 1.7.30 to 2.0.9

Updates SLF4J to latest stable version. No API changes
required as we use only stable APIs.

Documentation improvements

docs(readme): add plugin development quickstart guide

Add step-by-step guide for creating first plugin:
- Project setup
- Implementing Plugin interface
- Building and testing

Performance optimizations

perf(plugin-loader): cache plugin descriptors

Cache parsed plugin descriptors to avoid repeated I/O
and parsing. Reduces plugin loading time by ~40%.

Related to #789

Multi-file Changes

When changes span multiple components:

refactor(core): reorganize plugin lifecycle management

- Extract lifecycle state machine to separate class
- Move validation logic to validators package
- Update tests to reflect new structure

This refactoring improves testability and separation
of concerns without changing external APIs.

Related to #111, #222

Breaking Changes

Always use BREAKING CHANGE footer:

feat(api)!: replace Plugin.start() with Plugin.initialize()

BREAKING CHANGE: The Plugin.start() method has been renamed
to Plugin.initialize() for better semantic clarity. All
plugin implementations must update their code.

Migration guide: Replace @Override start() with @Override
initialize() in all Plugin implementations.

Closes #999

Quick Reference Card

Change TypeTypeExample Scope
New featurefeatapi, core, loader
Bug fixfixplugin-loader, lifecycle
Refactoringrefactorcore, utils
Teststestintegration, unit
Docsdocsreadme, javadoc
Buildbuildmaven, deps
Performanceperfclassloader, cache
Maintenancechoreci, tooling

References

Frequently asked questions

What does the Git Commit AI skill do?

Generate conventional commit messages for Java projects. Use when user says "commit", "create commit", "commit changes", or after completing code changes that need to be committed.

Why use Git Commit on TypingMind?

Because you install it once and use it with any model. Git Commit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Git Commit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/decebals/claude-code-java/tree/main/skills/git-commit. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Git Commit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Git Commit?

As many as you like. As long as a model supports skills, you can use Git Commit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Git Commit AI skill free?

Yes. It is published on GitHub by decebals under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇