Github Awesome Copilot Git Commit logo

Github Awesome Copilot Git Commit

Community
tuanductran
github-awesome-copilot-git-commit

Generate high-quality, atomic Conventional Commits by analyzing Git changes, recommending logical commit boundaries, validating commit messages, and assisting with PRs, changelogs, and releases.

Overview

Publishertuanductran
Repositoryhr-skills
Skill namegithub-awesome-copilot-git-commit
Stars
78
Forks
20
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 tuanductran on GitHub. Read the source before you install it.

Installation

Install the Github Awesome Copilot 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/tuanductran/hr-skills/tree/main/.agents/skills/github-awesome-copilot-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/tuanductran/hr-skills.git /tmp/hr-skills
mkdir -p .claude/skills
cp -r /tmp/hr-skills/.agents/skills/github-awesome-copilot-git-commit .claude/skills/github-awesome-copilot-git-commit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Github Awesome Copilot 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 Github Awesome Copilot 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 Github Awesome Copilot 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.

GitHub Awesome Copilot Git Commit

Supported tasks

Commit generation

  • Generate Conventional Commit messages from Git diffs
  • Analyze the current working tree using git diff
  • Generate commit messages from staged changes using git diff --cached
  • Infer the best commit type from the actual intent of the change
  • Recommend an appropriate scope when it improves clarity
  • Write concise subjects in the imperative mood (≤72 characters)
  • Generate optional commit bodies explaining what changed and why
  • Generate footers for issue references and breaking changes

Commit review

  • Review uncommitted Git changes before creating commits
  • Detect unrelated changes mixed in the same diff
  • Recommend splitting large changes into multiple atomic commits
  • Explain why commits should be separated
  • Generate one Conventional Commit for each logical change
  • Ignore whitespace-only changes unless intentional

Interactive Git workflow

  • Review git diff before staging
  • Review git diff --cached before committing
  • Suggest files that should be committed together
  • Recommend staging strategies using git add -p
  • Help create clean Git history with atomic commits

Validation

  • Validate commit messages against Conventional Commits 1.0.0
  • Detect incorrect types, scopes, formatting, or grammar
  • Suggest improved commit messages
  • Validate subject length
  • Detect non-imperative subjects
  • Detect unnecessary scopes

Pull requests

  • Generate PR titles from commits
  • Generate concise PR descriptions
  • Summarize major changes
  • Highlight breaking changes
  • List testing notes
  • Draft reviewer checklists

Releases

  • Generate changelog entries
  • Group commits into release categories
  • Draft release notes
  • Detect breaking changes
  • Generate migration notes
  • Summarize notable improvements

Key prompts

Generate commit from current changes

  • "Analyze the current Git working tree by running git diff and generate the best Conventional Commit."
  • "Review my current changes and recommend whether they should be split into multiple commits."
  • "Generate a Conventional Commit from the current unstaged changes."
  • "Generate a Conventional Commit from git diff --cached."

Generate commit from provided diff

  • "Generate a Conventional Commit from this Git diff."
  • "Analyze this patch and create the best Conventional Commit."
  • "Determine the intent of this change instead of describing modified files."
  • "Write a complete multi-line Conventional Commit including body and footer."

Improve commit quality

  • "Recommend a better commit scope."
  • "Suggest a shorter commit subject."
  • "Rewrite this commit message following Conventional Commits."
  • "Explain why this commit should be split."

Git workflow

  • "Review my Git changes before I commit."
  • "Suggest a clean staging strategy using git add -p."
  • "Identify unrelated modifications."
  • "Recommend the optimal commit order."

Validation

  • "Validate this Conventional Commit."
  • "Explain why this commit message is invalid."
  • "Rewrite this commit following Conventional Commits 1.0.0."

Pull requests

  • "Generate a PR title from these commits."
  • "Generate a complete PR description."
  • "Summarize these commits for reviewers."

Releases

  • "Generate changelog entries from these commits."
  • "Draft release notes for the next version."
  • "Generate migration notes for breaking changes."

Best practices

  • Always prioritize atomic commits.
  • Focus on the intent of the change rather than modified filenames.
  • Infer the correct commit type from behavior, not keywords.
  • Add a scope only when it provides meaningful context.
  • Keep commit subjects concise, imperative, and under 72 characters.
  • Do not end commit subjects with a period.
  • Include a body only when it adds useful context.
  • Recommend splitting unrelated changes into separate commits.
  • Prefer git add -p over staging everything when unrelated changes exist.
  • Review git diff before staging.
  • Review git diff --cached before committing.
  • Generate release notes from grouped Conventional Commits.
  • Follow Conventional Commits 1.0.0 whenever possible.

Temporary files

  • Never create temporary patch or diff files (for example *.patch or *.diff) unless the user explicitly requests them.
  • Prefer piping output directly to Git or the terminal instead of writing temporary files.
  • If a temporary file is required during execution, treat it as ephemeral:
    • Before creating a temporary file, verify whether it is ignored by Git (.gitignore); if not, avoid creating it or remove it before completing the task.
    • Remove the file before completing the task.
    • Never leave temporary artifacts behind or include them in commits.

Conventional Commit types

  • feat — Introduce a new feature
  • fix — Fix a bug
  • refactor — Improve code without changing behavior
  • perf — Improve performance
  • docs — Documentation only
  • style — Formatting without behavior changes
  • test — Add or update tests
  • build — Build system or dependencies
  • ci — Continuous integration
  • chore — Maintenance tasks
  • revert — Revert previous commits

Output guidelines

When generating commits:

  1. Analyze the complete Git diff.
  2. Identify the primary intent.
  3. Detect unrelated logical changes.
  4. Recommend splitting commits when appropriate.
  5. Produce valid Conventional Commit messages.
  6. Keep the history clean and review-friendly.
  7. Generate bodies only when they improve understanding.
  8. Include breaking-change footers when necessary.

Preferred output format:

text
type(optional-scope): concise imperative subject

Optional body explaining what changed and why.

BREAKING CHANGE: description (if applicable)

Frequently asked questions

What does the Github Awesome Copilot Git Commit AI skill do?

Generate high-quality, atomic Conventional Commits by analyzing Git changes, recommending logical commit boundaries, validating commit messages, and assisting with PRs, changelogs, and releases.

Why use Github Awesome Copilot Git Commit on TypingMind?

Because you install it once and use it with any model. Github Awesome Copilot 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 Github Awesome Copilot Git Commit in TypingMind?

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

Which AI models can use Github Awesome Copilot 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 Github Awesome Copilot Git Commit?

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

Is the Github Awesome Copilot Git Commit AI skill free?

Yes. It is published on GitHub by tuanductran 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 👇