Commit Message logo

Commit Message

Community
Aedelon
commit-message

Ship workflow: review changes, generate conventional commit messages, push, and create PRs. MUST BE USED when user says: "commit", "git commit", "commit this", "save changes", "commit message", "ship", "ship it", "push", "create PR", "pull request", "ready to merge", "deploy this", "stage changes", "what changed", "review my changes", "conventional commit", or after completing a coding task. Reviews changes, generates commit, optionally pushes and creates PR. NOT for git branching/rebasing (use git-workflow), code review (use review command), or deployment configuration (use deployment-assistant).

Overview

PublisherAedelon
Repositoryclaude-code-blueprint
Skill namecommit-message
Stars
119
Forks
34
Bundled files
Instructions only
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 Aedelon on GitHub. Read the source before you install it.

Installation

Install the Commit Message 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/Aedelon/claude-code-blueprint/tree/main/skills/commit-message
  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/Aedelon/claude-code-blueprint.git /tmp/claude-code-blueprint
mkdir -p .claude/skills
cp -r /tmp/claude-code-blueprint/skills/commit-message .claude/skills/commit-message
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Commit Message 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 Commit Message 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 Commit Message 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.

Ship Workflow

Overview

Complete shipping pipeline: review changes -> commit -> push -> PR (each step confirmed).

Process

Phase 1: REVIEW   -> git status + diff, understand all changes
Phase 2: COMMIT   -> Generate conventional commit message, confirm, commit
Phase 3: PUSH     -> Push to remote (if requested)
Phase 4: PR       -> Create PR with summary (if requested)

Phase 1: Review Changes

Before generating a commit message:

bash
# 1. Check what's staged and untracked
git status

# 2. Review changes (staged + unstaged)
git diff --cached
git diff

# 3. Check recent commit style
git log --oneline -5

Review Checklist

  • Are all intended files staged?
  • Are there files that should NOT be committed? (.env, large binaries, etc.)
  • Do changes make sense as a single commit or should they be split?

Format (Conventional Commits)

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

<body>

<footer>

Types

TypeUsageExample
featNew featurefeat(auth): add OAuth2 login
fixBug fixfix(api): handle null response
docsDocumentation onlydocs(readme): update installation
styleFormatting, no logicstyle: format with prettier
refactorCode restructurerefactor(utils): extract helper
perfPerformanceperf(query): add index
testTeststest(auth): add login tests
choreMaintenancechore(deps): update packages
ciCI/CDci: add GitHub Actions
buildBuild systembuild: update webpack config

Rules

Subject Line (First Line)

  • Max 50 characters
  • Imperative mood: "Add" not "Added" or "Adds"
  • No period at end
  • Capitalize first letter
  • Be specific: "fix login button" > "fix bug"

Scope (Optional)

  • Component, module, or feature affected
  • Lowercase, short
  • Examples: auth, api, ui, config, deps

Body (Optional)

  • Wrap at 72 characters
  • Explain "what" and "why", not "how"
  • Separate from subject with blank line
  • Use bullet points for multiple changes

Footer (Required)

  • Always include Claude attribution
  • Reference issues if applicable: Closes #123
  • Note breaking changes: BREAKING CHANGE: ...

Template

<type>(<scope>): <description>

<optional body explaining why this change was made>

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

Git Command Format

Use HEREDOC for proper formatting:

bash
git commit -m "$(cat <<'EOF'
feat(auth): add password reset flow

Implement forgot password functionality with email verification.
Users can now reset their password via a secure token sent by email.

Closes #42

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
EOF
)"

Examples

Simple Fix

fix(button): correct hover state color

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

Feature with Explanation

feat(search): add fuzzy matching

Implement Levenshtein distance for typo-tolerant search.
This improves UX when users mistype search queries.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

Breaking Change

feat(api)!: change response format to JSON:API

BREAKING CHANGE: API responses now follow JSON:API specification.
All clients must update their parsers.

Migration guide: docs/migration-v2.md

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

Anti-Patterns (Avoid)

❌ "fix stuff"
❌ "update code"
❌ "WIP"
❌ "misc changes"
❌ "asdf" (obviously)
❌ "Fixed the thing that was broken"
❌ Subject longer than 50 chars.....................

Post-Commit Verification

After committing:

bash
# Verify commit was created
git log -1

# Check nothing was missed
git status

Phase 3: Push (Optional)

If user confirms push:

bash
# Push to remote
git push origin HEAD

# If no upstream, set it
git push -u origin HEAD

Always confirm before pushing. Show which remote and branch.

Phase 4: Create PR (Optional)

If user wants a PR:

bash
gh pr create --title "<title>" --body "$(cat <<'EOF'
## Summary
- [bullet points of changes]

## Test Plan
- [how to verify changes]

Generated with [Claude Code](https://claude.com/claude-code)
EOF
)"

PR Title Rules

  • Max 70 characters
  • Same format as commit subject: type(scope): description
  • Use the body for details, not the title

PR Body Template

markdown
## Summary
[1-3 bullet points describing what changed and why]

## Test Plan
- [ ] [Steps to verify the changes work]

## Related Issues
Closes #[number] (if applicable)

Always confirm PR title and body before creating. Return the PR URL when done.

Frequently asked questions

What does the Commit Message AI skill do?

Ship workflow: review changes, generate conventional commit messages, push, and create PRs. MUST BE USED when user says: "commit", "git commit", "commit this", "save changes", "commit message", "ship", "ship it", "push", "create PR", "pull request", "ready to merge", "deploy this", "stage changes", "what changed", "review my changes", "conventional commit", or after completing a coding task. Reviews changes, generates commit, optionally pushes and creates PR. NOT for git branching/rebasing (use git-workflow), code review (use review command), or deployment configuration (use deployment-assi...

Why use Commit Message on TypingMind?

Because you install it once and use it with any model. Commit Message 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 Commit Message in TypingMind?

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

Which AI models can use Commit Message?

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 Commit Message?

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

Is the Commit Message AI skill free?

It is published on GitHub by Aedelon. Check the repository for licensing terms. 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 👇