Agent skill

Atomui Commit Msg

by AtomUI in AtomUI/AtomUI

Generate a single-line commit message for AtomUI by reading the project's git staged area and recent commit style.

LGPL-3.0Auto-check passedDevelopment

Install Atomui Commit Msg

skills CLI
$ npx skills add AtomUI/AtomUI --skill atomui-commit-msg -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AtomUI/AtomUI atomui-commit-msg --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AtomUI/AtomUI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/commit-msg .claude/skills/atomui-commit-msg && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
atomui-commit-msg
GitHub stars
842
Token cost
~2.6k tokens
SKILL.md length
1,265 words
Files
2 (incl. references)
Skills in repo
15
Repo updated
First seen
Licence
LGPL-3.0

At a glance

Generate a single-line commit message for AtomUI by reading the project's git staged area and recent commit style.

  • Works in 8 steps: Default to staged changes only → Always check recent commit style first → Default to a single line of output → …
  • The user asks for a commit message
  • SKILL.md covers Goals, Core Principle, IMPORTANT: Trigger Conditions and Fundamental Rules, plus 7 more sections
  • Calls git

What it does

Atomui Commit Msg is an agent skill from AtomUI/AtomUI. Generate a single-line commit message for AtomUI by reading the project's git staged area and recent commit style. Use when the user asks for a commit message, says "msg", "commit msg", "写提交信息", "创建 commit", "创建commit", or wants one-line text that covers all staged changes. Output should match the repository's existing commit style and summarize all staged changes in one line.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/commit-message-convention.md`).

It sits in Development, covering Commit messages and Git workflow. It works with Git. The repository describes itself as: An enhancement and extension library for Avalonia, bringing the Ant Design design language, modern controls, theming, native integrations, and cross-platform UI capabilities to… The licence is LGPL-3.0.

When your agent uses it

  • The user asks for a commit message
  • Wants one-line text that covers all staged changes

Example prompts

  • “commit msg”
  • “创建 commit”
  • “创建commit”
  • “/atomui-commit-msg”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Default to staged changes only
  2. Always check recent commit style first
  3. Default to a single line of output
  4. Read git status, staging area, and recent commits
  5. Check if generation is possible
  6. Identify the primary semantic intent
  7. Align with AtomUI repository style
  8. Generate one line

What it can do on your machine

Read from SKILL.md and the folder at commit d234fe0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Atomui Commit Msg loads about 2.6k tokens when it runs, and up to ~5.7k if it reads all its reference files. Until then it costs about 99 tokens; SKILL.md has 1,265 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~99
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from AtomUI/AtomUI at commit d234fe0, republished under its LGPL-3.0 licence (© AtomUI). 1,265 words, ~2,559 tokens.

Download SKILL.mdSave it as .claude/skills/atomui-commit-msg/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
atomui-commit-msg
description
Generate a single-line commit message for AtomUI by reading the project's git staged area and recent commit style. Use when the user asks for a commit message, says "msg", "commit msg", "写提交信息", "创建 commit", "创建commit", or wants one-line text that covers all staged changes. Output should match the repository's existing commit style and summarize all staged changes in one line.

AtomUI Commit Message Generation Skill

Goals

1. Accurately summarize the commit — Generate a one-line commit message based on the current git staging area, covering all staged changes.

2. Stay consistent with repository style — Match the repository's existing commit conventions rather than mechanically applying a template.

Core Principle

A commit message is not a per-file listing of the diff — it is a compressed expression of the commit's intent. Read the staging area first, then summarize, then output one line.

IMPORTANT: Trigger Conditions

This skill MUST be invoked when the user's message matches ANY of the following patterns. Do NOT skip this skill and handle the request manually.

Trigger phraseExample
创建 commit / 创建commit"创建 commit"
commit msg / msg"msg", "commit msg"
提交信息 / 写提交信息"帮我写提交信息"
Asks for a commit message"generate a commit message"
Asks to summarize staged changes into a commit title"summarize my staged changes"

When triggered, this skill handles the entire commit workflow: reading staged changes, generating the message, creating the commit, and verifying the result. The caller should NOT add extra trailers (e.g., Co-Authored-By) or wrap the message in additional formatting.

Fundamental Rules

1. Default to staged changes only

Generate the message based on staged changes only, because that is what will actually be committed.

Only include unstaged changes if the user explicitly requests it (e.g., "include unstaged" or "cover all changes").

2. Always check recent commit style first

Before generating a message, review recent commits to avoid producing a format inconsistent with the repository's conventions.

3. Default to a single line of output

Unless the user explicitly asks for an explanation or a body, the final response should be one line of commit message only — no analysis, bullet points, code blocks, or quotes.

Execution Steps

Step 1: Read git status, staging area, and recent commits

Gather the following information before generating. Do not guess or rely on filenames alone.

Recommended commands:

bash
git status --short
git diff --cached --stat
git diff --cached
git log --oneline -10 --no-merges
  • git status --short — Confirm which files are staged and whether unstaged changes exist.
  • git diff --cached --stat — Quickly assess the scope of changes.
  • git diff --cached — Read the actual content being committed. This is the primary basis for the message.
  • git log --oneline -10 --no-merges — Check the repository's recent commit style, language, and type/scope conventions. When reviewing commit style, ignore any Co-Authored-By: trailers — they are not part of the project's commit convention and must not be reproduced.
Step 2: Check if generation is possible

If the staging area is empty:

  • Do NOT fabricate a message.
  • Clearly inform the user that there are no staged changes and an accurate commit message cannot be generated.
Step 3: Identify the primary semantic intent

Based on the git diff --cached output:

  1. Determine the primary purpose — new feature, bug fix, documentation, refactoring, performance optimization, test, Gallery ShowCase, script/dependency update, etc.
  2. Identify the primary affected scope — specific control name, infrastructure module (TokenSystem / Theme / Motion, etc.), Gallery, scripts, docs, etc.
  3. If the diff contains multiple files or mixed small changes, use a higher-level summary that covers everything. Do not concatenate per-file descriptions into one long sentence.
Step 4: Align with AtomUI repository style

Prefer to mimic the repository's recent conventions. Common patterns in AtomUI:

  • feat(Component): ...
  • fix(Component): ...
  • refactor(Component): ...
  • docs: ... / docs(Core): ...
  • chore(deps): ...
  • gallery: ... / gallery(Component): ...
  • build(ci): ...
  • perf(TokenSystem): ...

Notes:

  • type and scope MUST be in English.
  • subject defaults to English; Chinese is acceptable if the user is conversing in Chinese or explicitly requests it.
  • If the repository already uses a more natural phrasing, prefer matching the existing style.
  • gallery is used as a type prefix in AtomUI (analogous to site in ant-design) for ShowCase / Gallery app changes.
Step 5: Generate one line

The output must be:

  • One line
  • Covering all staged changes
  • Concise
  • Consistent with repository style
  • Ready to use as-is for the commit

Writing Rules

Header format

Use one of the following:

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

or (when scope cannot be determined):

text
<type>: <subject>

Examples:

  • feat(Button): add danger style variant for ghost button
  • fix(Select): prevent dropdown from closing on multi-select click
  • refactor(Avatar): extract AbstractAvatar to AtomUI.Controls
  • docs(Core): add three-tier architecture documentation
  • gallery: add QRCode showcase with comprehensive examples
  • chore(deps): bump Avalonia from 11.3.1 to 11.3.2
  • fix(Select): 修复多选模式下点击后下拉框意外关闭
Header rules
  • Use imperative mood — add / fix / update, not added / fixed / updated. For Chinese subjects, start with a verb: "修复" / "添加" / "调整".
  • Do NOT capitalize the first letter of an English subject.
  • Do NOT end with a period (. or 。).
  • Keep the header line to 72 characters or fewer.
  • Avoid vague terms like WIP, misc, update files.
Show full SKILL.md (531 more words)Show less
Type selection

All types are lowercase:

  • feat — New feature, control, property, or API
  • fix — Bug fix — incorrect behavior, crash, memory leak, rendering issue
  • refactor — Code restructuring with no behavior change — moving code between layers, renaming, splitting classes
  • docs — Documentation only — README, XML doc comments, architecture docs, copilot-instructions
  • style — Code formatting only (no logic change) — whitespace, indentation, code style
  • perf — Performance improvement — rendering optimization, reduced allocations, caching
  • test — Adding or updating tests
  • build — Build system or dependency changes — MSBuild props, Directory.Packages.props, scripts
  • chore — Maintenance that doesn't modify src/test — tooling config, .editorconfig, IDE settings
  • ci — CI/CD configuration changes
  • gallery — Gallery / ShowCase changes — demo pages, gallery navigation, gallery assets
  • release — Version bumps, changelog updates, release preparation
  • revert — Reverting a previous commit (must reference the reverted commit hash in the body)

When uncertain:

  • User-visible behavior correction → prefer fix
  • Only text, examples, or descriptions updated → prefer docs
  • Only tooling, dependencies, or scripts adjusted → prefer chore
  • ShowCase / Gallery demo changes → prefer gallery
  • Code structure changed but behavior unchanged → prefer refactor
Scope selection
  • For changes to a single control, use the control name in PascalCase: Button, Select, DatePicker, TreeView, Cascader, FloatButton
  • For infrastructure modules, use the module name: TokenSystem, Theme, Motion, WaveSpirit, Core, Icons, Fonts, Generator, Native, i18n, MediaQuery
  • For cross-cutting maintenance, use a summary scope: deps, scripts, Packaging, Bindings, MemoryLeak
  • For multiple closely related controls, use comma-separated names: Select,AutoComplete
  • If no clear scope exists, it may be omitted

Language Rules

  • type and scope MUST be English (they are fixed keywords / identifiers)
  • subject and body default to English; Chinese is also acceptable
  • Use Chinese for the subject when the user is conversing in Chinese or explicitly requests it

Layer Awareness

AtomUI uses a three-tier architecture: Foundation → Base Control (AtomUI.Controls) → Platform Control (AtomUI.Desktop.Controls).

When changes span layers:

  • If each layer's changes can be understood independently, suggest splitting into multiple commits
  • If tightly coupled and inseparable, use a single commit with the control name as the scope

Edge Cases

Mixed change types

If staged changes include a mix of docs, styles, types, and small fixes:

  • Identify the primary purpose first
  • If there is no single primary purpose, use a higher-level summary
  • The goal is to "honestly cover all changes", not to cram every detail into the title
Scattered / unrelated changes

If the staging area contains clearly unrelated groups of changes:

  • Still produce an honest one-line message
  • Do not pretend these changes share a single specific purpose
  • Use a broad summary, e.g., chore(controls): clean up styles, types and docs
Breaking Changes

If the changes include a breaking API change:

  • Append ! after type/scope, e.g., refactor(TokenSystem)!: rename ControlDesignToken to AbstractControlDesignToken
  • If the user requests a body, include a BREAKING CHANGE: footer

Prohibited

  • Generating a message without reading git diff --cached
  • Guessing content based only on filenames
  • Describing only some files/changes while ignoring other staged content
  • Outputting multi-line explanations as the commit message
  • Breaking from established repository style just to fit a template
  • Writing headers longer than 72 characters unless truly unavoidable
  • Wrapping the final output in backticks, quotes, or code blocks
  • Do not push to the remote end unless explicitly requested
  • Do not add "Co-Authored-By: xxx" or information regarding other agents.

Reference

For detailed type/scope definitions, style examples, and input→output samples, see references/commit-message-convention.md.

© AtomUI, LGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .agents/skills/commit-msg of AtomUI/AtomUI.

  • SKILL.md
  • references/commit-message-convention.md

Open the folder on GitHubat commit d234fe0

Compare with similar skills

Atomui Commit Msg next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Atomui Commit Msg compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Atomui Commit Msg this skillAtomUI/AtomUI842—~2.6kAutomated safety check: PassLGPL-3.0
ToolJet Multi-Repo CommitToolJet/ToolJet41k—~1.3kAutomated safety check: PassAGPL-3.0
Git Workflow and Versioningaddyosmani/agent-skills102k2 repos~3.5kAutomated safety check: NotesMIT
React Router Pull Request Creatorremix-run/react-router57k—~2.5kAutomated safety check: PassMIT
Saleor Commit Workflowsaleor/saleor23k—~575Automated safety check: PassBSD-3-Clause
Emoji Commit ConventionsbaptisteArno/typebot.io11k—~424Automated safety check: PassCustom licence

Similar skills

  • Commits changes across ToolJet's root repo and its server/ee and frontend/ee submodules, writing messages from the diffs and updating submodule pointers in order.

    41k GitHub stars~1.3k tokensUpdated today
    DevelopmentAuto-check passed
  • Git Workflow and Versioning

    addyosmani/agent-skills

    Sets git habits for every change: short-lived branches, atomic commits with descriptive messages, clean pull requests, plus versioning, tagging and changelogs for releases.

    102k GitHub starsUsed in 2 repos~3.5k tokens
    DevelopmentAuto-check: notes
  • React Router Pull Request Creator

    remix-run/react-router

    Packages finished React Router work into a draft pull request: branch, commit, push, a written PR body and the right GitHub labels.

    57k GitHub stars~2.5k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Commits changes in the Saleor codebase and works through pre-commit hook failures from ruff, mypy, the GraphQL schema check and the migrations check.

    23k GitHub stars~575 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Emoji Commit Conventions

    baptisteArno/typebot.io

    Sets the repository's convention for commit messages and pull request titles: one emoji prefix for the main intent, a concise title and clean follow-up commits.

    11k GitHub stars~424 tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Draft Pull Request Creator

    wordpress-mobile/WordPress-Android

    Commits and pushes current changes, writes a pull request title and body from the branch history and template, and opens a draft PR on GitHub after you approve it.

    3.2k GitHub stars~881 tokensUpdated today
    DevelopmentAuto-check: notes

More from AtomUI/AtomUI

All 15 skills in this repo
  • A skill your agent uses when building, launching, debugging, or visually inspecting AtomUIGallery.Desktop from an AtomUI checkout where installed or mounted Gallery apps may share its name or bundle…

    842 GitHub stars~983 tokensUpdated today
    Auto-check passed
  • A skill your agent uses when optimizing, refactoring, reviewing, or fixing AtomUI controls, including control API contracts, member layout, file splitting, lifecycle, AXAML structure, correctness…

    842 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • A skill your agent uses when creating, completing, splitting, reviewing, or synchronizing AtomUI control documentation under docs/controls, including overview.md, implementation.md, token.md…

    842 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • A skill your agent uses when changing AtomUI or Avalonia resource bindings, DynamicResource, TokenResourceBinder, non-Visual AvaloniaObject lifecycle, IResourceHost/IThemeVariantHost…

    842 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • A skill your agent uses when upgrading AtomUI NuGet dependencies, source dependency projects, ReactiveUI, Avalonia, Splat, or any third-party version where compatibility must be evaluated before…

    842 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Version Release

    AtomUI/AtomUI

    A skill your agent uses when preparing or validating an AtomUI release, including version-scope confirmation, AtomUIVersion consistency, README version sync, CHANGELOG and Chinese release sections…

    842 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Atomui Commit Msg

What does Atomui Commit Msg do?

Generate a single-line commit message for AtomUI by reading the project's git staged area and recent commit style. Atomui Commit Msg is an agent skill from AtomUI/AtomUI. Generate a single-line commit message for AtomUI by reading the project's git staged area and recent commit style.

When should I use Atomui Commit Msg?

Atomui Commit Msg fits situations like: the user asks for a commit message; wants one-line text that covers all staged changes.

How do I install Atomui Commit Msg in Claude Code?

Run `npx skills add AtomUI/AtomUI --skill atomui-commit-msg -a claude-code`. Or copy the skill folder (.agents/skills/commit-msg in AtomUI/AtomUI) into .claude/skills/atomui-commit-msg in your project. Claude Code loads it when a task matches its description.

How do I install Atomui Commit Msg in Codex?

Run `npx skills add AtomUI/AtomUI --skill atomui-commit-msg -a codex`. Or copy the skill folder (.agents/skills/commit-msg in AtomUI/AtomUI) into .agents/skills/atomui-commit-msg in your project. Codex loads it when a task matches its description.

Can I use Atomui Commit Msg in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AtomUI/AtomUI --skill atomui-commit-msg -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/atomui-commit-msg, .gemini/skills/atomui-commit-msg, .github/skills/atomui-commit-msg and .opencode/skills/atomui-commit-msg in your project.

What does Atomui Commit Msg need to run?

Going by SKILL.md and its folder, Atomui Commit Msg needs the command-line tools its instructions call (git).

Does Atomui Commit Msg access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Atomui Commit Msg safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Atomui Commit Msg use?

Atomui Commit Msg is published under the LGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Atomui Commit Msg use?

About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.1k tokens, read only when the agent opens those files.

What are the alternatives to Atomui Commit Msg?

Skills that share tags, products or a category with Atomui Commit Msg: ToolJet Multi-Repo Commit (ToolJet/ToolJet, 41k stars), Git Workflow and Versioning (addyosmani/agent-skills, 102k stars), React Router Pull Request Creator (remix-run/react-router, 57k stars) and Saleor Commit Workflow (saleor/saleor, 23k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Atomui Commit Msg?

AtomUI (a GitHub organization) maintains it in AtomUI/AtomUI, which has 842 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 7, 2026.

Source: AtomUI/AtomUI on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.