Write a Magic Resume commit message that passes the gitmoji + conventional-type lint.

MITAuto-check passedDevelopment

Install Commit

skills CLI
$ npx skills add Magic-Resume/Magic-Resume --skill commit -a claude-code

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

GitHub CLI
$ gh skill install Magic-Resume/Magic-Resume commit --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/Magic-Resume/Magic-Resume.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/commit .claude/skills/commit && 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
commit
GitHub stars
101
Token cost
~1.2k tokens
SKILL.md length
455 words
Files
1
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Write a Magic Resume commit message that passes the gitmoji + conventional-type lint.

  • Works in 7 steps: Inspect the staged diff (git diff… → Pick the emoji that matches the intent… → Pick the matching type (lowercase). → …
  • The user asks Claude to commit
  • SKILL.md covers Format, Emoji → intent map, Examples (these pass) and Examples (these fail), plus 3 more sections
  • Calls git and npx

What it does

Commit is an agent skill from Magic-Resume/Magic-Resume. Write a Magic Resume commit message that passes the gitmoji + conventional-type lint. Use whenever the user asks Claude to commit, draft a commit message, or open a PR in this repo.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Commit messages, Pull requests and Building AI agents. It works with LangChain, LangGraph, React and TypeScript. The repository describes itself as: Open-source AI career platform that helps users build, optimize, analyze, and tailor resumes with intelligent job matching, ATS optimization, and career guidance. The licence is MIT.

When your agent uses it

  • The user asks Claude to commit
  • Draft a commit message
  • Open a PR in this repo

Example prompts

  • “/commit”

Requirements

  • Node.js

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Inspect the staged diff (git diff --cached) to understand intent.
  2. Pick the emoji that matches the intent (single, leading position).
  3. Pick the matching type (lowercase).
  4. Add a scope when the change is workspace-local. Skip it for cross-workspace or repo-wide changes.
  5. Write the subject in present-imperative voice, no period.
  6. If extra context is genuinely useful, add a body (blank line, then prose).
  7. Commit. The hook will run commitlint --edit "$1".

What it can do on your machine

Read from SKILL.md and the folder at commit 7c67be7. 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
    • npx

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

  • Network

    Links to these hosts (documentation or services it may open):

    • gitmoji.dev

    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

Commit loads about 1.2k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 455 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 Magic-Resume/Magic-Resume at commit 7c67be7, republished under its MIT licence (© Magic-Resume). 455 words, ~1,238 tokens.

Download SKILL.mdSave it as .claude/skills/commit/SKILL.md (or your agent's skills folder).
name
commit
description
Write a Magic Resume commit message that passes the gitmoji + conventional-type lint. Use whenever the user asks Claude to commit, draft a commit message, or open a PR in this repo.

Commit (gitmoji + conventional)

This repo enforces a gitmoji + conventional-type commit format via Husky commit-msg → commitlint (commitlint-config-gitmoji). Any commit that does not match this format is rejected.

Use this skill every time you write a commit message in this repo. Do not skip the hook with --no-verify.

Format

<emoji> <type>(<scope>?): <subject>
  • emoji — a gitmoji shortcode (:sparkles:) or unicode character (✨). Either works. Pick one that matches the intent of the change.
  • type — exactly one of: build, ci, chore, docs, feat, fix, perf, refactor, revert, style, test, wip. Lowercase.
  • scope — optional, lowercase, no whitespace. Use a workspace name when the change is scoped to one (web, docs, mcp, resume-schema, resume-templates).
  • subject — imperative ("add", not "added" / "adds"). No trailing period. Whole header ≤ 100 chars.

Body and footer are optional. If present, both must be preceded by a blank line.

Emoji → intent map

Pick the emoji from intent first, then choose the type that fits. The two should agree.

Only codes in the official gitmoji list are accepted by the validator. The plugin rejects anything else — including common-looking ones like :books:. Pick from this list.

IntentEmojiCommon type
New feature:sparkles: ✨feat
Bug fix:bug: 🐛fix
Critical hotfix:ambulance: 🚑️fix
Docs:memo: 📝docs
Refactor:recycle: ♻️refactor
Architectural change:building_construction: 🏗️refactor
Perf:zap: ⚡️perf
Format / code structure:art: 🎨style
UI / styling:lipstick: 💄style
Tests:white_check_mark: ✅test
Add a failing test:test_tube: 🧪test
CI:construction_worker: 👷 / :green_heart: 💚ci
Dev scripts (husky, makefiles):hammer: 🔨build, chore
Config files:wrench: 🔧chore
Add a dep:heavy_plus_sign: ➕chore
Remove a dep:heavy_minus_sign: ➖chore
Upgrade deps:arrow_up: ⬆️chore
Downgrade deps:arrow_down: ⬇️chore
Pin deps:pushpin: 📌chore
Remove code / files:fire: 🔥chore, refactor
Move / rename:truck: 🚚refactor
Types:label: 🏷️feat, refactor
i18n:globe_with_meridians: 🌐feat
.gitignore:see_no_evil: 🙈chore
Revert:rewind: ⏪️revert
WIP:construction: 🚧wip
Breaking change:boom: 💥any
Show full SKILL.md (164 more words)Show less

Examples (these pass)

:sparkles: feat(web): add resume share link generator
:bug: fix(mcp): handle empty patch in update_resume_content
:memo: docs: rewrite intro page with multi-repo architecture
:recycle: refactor(web): centralize API route paths in lib/api/routes.ts
:zap: perf(resume-templates): memoize template registry lookup
:white_check_mark: test(mcp): add cases for preview_resume_patch errors
:arrow_up: chore(deps): bump nextra to 4.3.0

Examples (these fail)

feat: add dark mode                       # no emoji
✨ Add dark mode                          # no type
:sparkles: Feat: add dark mode            # type must be lowercase
:sparkles: feat: add dark mode.           # trailing period
sparkles feat add dark mode               # not a gitmoji
:sparkles: feat: this subject is way too long and pushes the whole header past one hundred characters which is the cap

Workflow

  1. Inspect the staged diff (git diff --cached) to understand intent.
  2. Pick the emoji that matches the intent (single, leading position).
  3. Pick the matching type (lowercase).
  4. Add a scope when the change is workspace-local. Skip it for cross-workspace or repo-wide changes.
  5. Write the subject in present-imperative voice, no period.
  6. If extra context is genuinely useful, add a body (blank line, then prose).
  7. Commit. The hook will run commitlint --edit "$1".

If the hook rejects, read the printed rule names (e.g. [start-with-gitmoji], [type-empty]) and rewrite. Do not pass --no-verify.

Quick check before committing

Pipe a candidate message through commitlint without actually committing:

bash
echo ":sparkles: feat(web): add resume share link generator" | npx --no -- commitlint

Exit 0 = good. Non-zero = the printed rule tells you what to fix.

Out of scope for this skill

  • Choosing what to stage (git add decisions) — that's a separate judgment.
  • Branch names, PR titles, PR body formatting — not enforced by commitlint here.
  • Merge commits and revert auto-messages — exempted by parser preset.

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

Files

Just SKILL.md in .claude/skills/commit of Magic-Resume/Magic-Resume.

Open the folder on GitHubat commit 7c67be7

Compare with similar skills

Commit 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.

Commit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Commit this skillMagic-Resume/Magic-Resume101—~1.2kAutomated safety check: PassMIT
Chat Gun Backend ContractHsienW/chat-gun143—~2.1kAutomated safety check: PassCustom licence
Add Example AgentGetBindu/Bindu10k—~1.1kAutomated safety check: NotesCustom licence
Failproof AI SDK IntegrationFailproofAI/failproofai5.3k—~6kAutomated safety check: PassCustom licence
Agent Inspectrajudandigam/agent-inspect165—~424Automated safety check: PassMIT
Deep Agents Corelangchain-ai/langchain-skills1.3k1 repos~3.1kAutomated safety check: PassMIT

Similar skills

  • Apply when creating, modifying, refactoring, debugging, testing, or reviewing TypeScript, LangGraph JS, LangChain, provider adapter, tool, MCP, prompt, state, checkpoint, runtime event, or backend…

    143 GitHub stars~2.1k tokensUpdated 3 days ago
    AI & LLM EngineeringAuto-check passed
  • Add Example Agent

    GetBindu/Bindu

    Add a new self-contained example agent under examples/. An agent skill from GetBindu/Bindu.

    10k GitHub stars~1.1k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check: notes
  • Failproof AI SDK Integration

    FailproofAI/failproofai

    Helps instrument a custom Python or TypeScript agent to record events for Failproof AI, verify what gets written, and run an evaluator worker that scores the runs.

    5.3k GitHub stars~6k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Agent Inspect

    rajudandigam/agent-inspect

    Local evidence debugger and trajectory-test toolkit for TypeScript AI agents.

    165 GitHub stars~424 tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Deep Agents Core

    langchain-ai/langchain-skills

    Official

    Explains how to build agents with the Deep Agents framework: create_deep_agent, the built-in middleware, the harness, SKILL.md format and configuration options.

    1.3k GitHub starsUsed in 1 repo~3.1k tokens
    AI & LLM EngineeringAuto-check passed
  • Tool Design

    agentailor/fullstack-langgraph-nextjs-agent

    Design and verify tools that AI agents can actually use — for any framework or language (MCP servers, LangChain/LangGraph, function-calling, raw JSON schema; TypeScript, Python, or otherwise).

    132 GitHub stars~3.2k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed

More from Magic-Resume/Magic-Resume

  • Magic Resume

    Magic-Resume/Magic-Resume

    How AI agents integrate with Magic Resume — read and safely edit a user's resumes through the native MCP server (@magic-resume/mcp).

    101 GitHub stars~663 tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Commit

What does Commit do?

Write a Magic Resume commit message that passes the gitmoji + conventional-type lint. Commit is an agent skill from Magic-Resume/Magic-Resume. Write a Magic Resume commit message that passes the gitmoji + conventional-type lint.

When should I use Commit?

Commit fits situations like: the user asks Claude to commit; draft a commit message; open a PR in this repo.

How do I install Commit in Claude Code?

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

How do I install Commit in Codex?

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

Can I use Commit 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 Magic-Resume/Magic-Resume --skill commit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/commit, .gemini/skills/commit, .github/skills/commit and .opencode/skills/commit in your project.

What does Commit need to run?

Going by SKILL.md and its folder, Commit needs the command-line tools its instructions call (git and npx). Our summary lists: Node.js.

Does Commit access the network?

SKILL.md names 1 domain. As links in the text: gitmoji.dev. This is read from the text; nothing was executed.

Is Commit 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 Commit use?

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

How many tokens does Commit use?

About 1.2k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Commit?

Skills that share tags, products or a category with Commit: Chat Gun Backend Contract (HsienW/chat-gun, 143 stars), Add Example Agent (GetBindu/Bindu, 10k stars), Failproof AI SDK Integration (FailproofAI/failproofai, 5.3k stars) and Agent Inspect (rajudandigam/agent-inspect, 165 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Commit?

Magic-Resume (a GitHub organization) maintains it in Magic-Resume/Magic-Resume, which has 101 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 5, 2026.

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