Agent skill

Conventional Commits

by Xe in Xe/site

A skill your agent uses when creating git commits, writing commit messages, or following version control workflows

ZlibAuto-check passedDevelopment

Install Conventional Commits

skills CLI
$ npx skills add Xe/site --skill conventional-commits -a claude-code

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

GitHub CLI
$ gh skill install Xe/site conventional-commits --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/Xe/site.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/conventional-commits .claude/skills/conventional-commits && 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
conventional-commits
GitHub stars
732
Token cost
~1.3k tokens
SKILL.md length
421 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
Zlib

At a glance

A skill your agent uses when creating git commits, writing commit messages, or following version control workflows

  • Works in 8 steps: [ ] Type is from allowed list → [ ] Description is imperative mood (add,… → [ ] Description is lowercase → …
  • Creating git commits
  • SKILL.md covers Overview, Quick Reference, Format and Examples, plus 7 more sections
  • Calls git

What it does

Conventional Commits is an agent skill from Xe/site. Use when creating git commits, writing commit messages, or following version control workflows

Its SKILL.md is about 1.3k 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. The repository describes itself as: The new frontend/backend code for https://xeiaso.net. The licence is Zlib.

When your agent uses it

  • Creating git commits
  • Writing commit messages
  • Following version control workflows

Example prompts

  • “/conventional-commits”

Workflow steps

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

  1. [ ] Type is from allowed list
  2. [ ] Description is imperative mood (add, fix, update)
  3. [ ] Description is lowercase
  4. [ ] No trailing period on description
  5. [ ] Breaking changes marked with ! or footer
  6. [ ] AI attribution included (if applicable)
  7. [ ] Body explains WHY not HOW
  8. [ ] Using --signoff flag

What it can do on your machine

Read from SKILL.md and the folder at commit 45c532e. 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

Conventional Commits loads about 1.3k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 421 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 Xe/site at commit 45c532e, republished under its Zlib licence (© Xe). 421 words, ~1,315 tokens.

Download SKILL.mdSave it as .claude/skills/conventional-commits/SKILL.md (or your agent's skills folder).
name
conventional-commits
description
Use when creating git commits, writing commit messages, or following version control workflows

Conventional Commits

Structured commit message format for version control that provides clear, readable project history.

Overview

The Conventional Commits specification provides:

  • Automated changelog generation - Tools can parse commits to generate CHANGELOG.md
  • Semantic versioning - Commit types map to version bumps (feat → minor, breaking → major)
  • Clear project history - Standardized format makes git log readable
  • Automated releases - CI/CD can trigger releases based on commit types

Quick Reference

TypeUse ForVersion Bump
featNew featureMINOR
fixBug fixPATCH
docsDocumentation onlyPATCH
styleFormatting, no logic changePATCH
refactorCode restructuring, no behavior changePATCH
perfPerformance improvementPATCH
testAdding or updating testsPATCH
buildBuild system or dependenciesPATCH
ciCI/CD configurationPATCH
choreMaintenance, no user-facing changePATCH
revertRevert a previous commitPATCH

Format

text
<type>[optional scope]: <description>

[optional body]

[optional footer(s)]

Rules:

  • Type is required
  • Scope is optional - use parenthesized section affected: (api), auth), parser)
  • Description is required
  • Keep description concise, imperative mood, lowercase, no trailing period
  • Body and footer are optional
  • Separate subject from body with blank line
  • Wrap body at 72 characters

Examples

text
feat: add user authentication

Implement JWT-based authentication with login/logout endpoints.
Includes password hashing and session management.

Closes: #123
text
fix(api): handle null response from server

Previous implementation crashed when server returned null.
Now returns empty result set.

Assisted-by: GLM 4.6 via Claude Code
text
feat(storage)!: change bucket listing API

BREAKING CHANGE: bucket list now returns async iterator
instead of array. Update all callers to use for-await.
text
refactor(core): simplify error handling

Consolidate duplicate error handlers into single utility.
No behavior changes - internal cleanup only.
text
revert: feat(auth): add OAuth support

This reverts commit 8b5a1c2. OAuth provider changed
their API and we need to redesign integration.

Breaking Changes

Indicate breaking changes in two ways:

Option 1: Add ! after type/scope

text
feat(api)!: remove deprecated endpoint

Option 2: Add BREAKING CHANGE: footer

text
feat(api): remove deprecated endpoint

BREAKING CHANGE: endpoint no longer exists. Use newEndpoint instead.

AI Attribution

AI agents must disclose their assistance in the commit footer:

text
Assisted-by: [Model Name] via [Tool Name]

Examples:

  • Assisted-by: GLM 4.6 via Claude Code
  • Assisted-by: Claude Opus 4.5 via claude.ai

Common Mistakes

MistakeWhy WrongCorrect
Added login featurePast tense, capitalizedfeat: add login feature
fix bug.Trailing periodfix: resolve login error
updateMissing typechore: update dependencies
feature:add-authMissing space after colonfeat: add authentication
FEAT: big changeUppercase typefeat: add authentication
Multi-line description no blank lineNo separationAdd blank line after subject
Show full SKILL.md (148 more words)Show less

Body Guidelines

  • What: Motivation for the change (vs. code comments describe HOW)
  • Contrast: Explain the WHY and WHAT, not code details
  • Wrap at 72 characters for readability in git log
text
feat(summarization): add support for nested bullet points

Previous implementation only flattened all content. Now preserves
hierarchy by respecting indentation levels. Users can now create
structured summaries with parent-child relationships.

Closes: #456

Use footers for:

  • Breaking changes: BREAKING CHANGE: detailed explanation
  • Issue references: Closes: #123, Fixes: #456, Refs: #789
  • AI attribution: Assisted-by: Model via Tool

Multiple footers separated by blank lines:

text
feat: add batch upload

Implements multipart upload for large files.

BREAKING CHANGE: upload() signature changed - now requires options object
Closes: #123
Assisted-by: GLM 4.6 via Claude Code

Git Commit Flags

Required flag: Always use --signoff when committing:

bash
git commit --signoff -m "feat: add user authentication"

The --signoff flag adds a Signed-off-by trailer to the commit message, indicating the committer has certified the commit follows developer certificate of origin (DCO).

Testing Your Commit

Before committing, verify:

  1. Type is from allowed list
  2. Description is imperative mood (add, fix, update)
  3. Description is lowercase
  4. No trailing period on description
  5. Breaking changes marked with ! or footer
  6. AI attribution included (if applicable)
  7. Body explains WHY not HOW
  8. Using --signoff flag

© Xe, Zlib. 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 .agents/skills/conventional-commits of Xe/site.

Open the folder on GitHubat commit 45c532e

Compare with similar skills

Conventional Commits 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.

Conventional Commits compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Conventional Commits this skillXe/site732—~1.3kAutomated safety check: PassZlib
Contextual Commit Messagesyamadashy/repomix29k1 repos~2.7kAutomated safety check: PassMIT
React Router Release Notes Prepremix-run/react-router57k—~1.1kAutomated safety check: PassMIT
Caveman Commitvishiri/fantasia-archive40913 repos~642Automated safety check: PassGPL-3.0
PR Finalize Reviewmicrosoft/garnet12k—~3.1kAutomated safety check: PassMIT
ToolJet Multi-Repo CommitToolJet/ToolJet41k—~1.3kAutomated safety check: PassAGPL-3.0

Similar skills

  • Writes Conventional Commits whose bodies carry action lines recording the intent, decisions and constraints behind a change, not only what changed.

    29k GitHub starsUsed in 1 repo~2.7k tokens
    DevelopmentAuto-check passed
  • React Router Release Notes Prep

    remix-run/react-router

    Polishes pending React Router change files before the versioning scripts run, and decides whether a long-form What's Changed section is warranted.

    57k GitHub stars~1.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Caveman Commit

    vishiri/fantasia-archive

    Ultra-compressed commit message generator. An agent skill from vishiri/fantasia-archive.

    409 GitHub starsUsed in 13 repos~642 tokens
    DevelopmentAuto-check passed
  • PR Finalize Review

    microsoft/garnet

    Official

    Checks that a pull request's title and description match its implementation and reviews the code for Garnet best practices, reporting findings without posting them.

    12k GitHub stars~3.1k tokensUpdated today
    DevelopmentAuto-check passed
  • 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.

    103k GitHub starsUsed in 2 repos~3.5k tokens
    DevelopmentAuto-check: notes
  • Stop Slop

    Xe/site

    Remove AI writing patterns from prose. An agent skill from Xe/site.

    732 GitHub starsUsed in 8 repos~423 tokens
    Auto-check passed
  • Choose and create the right Neon branch type for testing and development.

    732 GitHub starsUsed in 3 repos~2.4k tokens
    Auto-check: notes
  • Guides and best practices for working with Neon Serverless Postgres.

    732 GitHub starsUsed in 2 repos~1.8k tokens
    Auto-check passed
  • A skill your agent uses when asked to generate a "no way to prevent this" / no-way-to-prevent-this satire post for a memory-safety CVE (out-of-bounds write/read, buffer/heap overflow…

    732 GitHub stars~816 tokensUpdated 3 days ago
    Auto-check passed
  • Create reusable templ UI components with props, children, and composition patterns.

    732 GitHub stars~552 tokensUpdated 3 days ago
    Auto-check passed
  • Templ HTTP

    Xe/site

    Integrate templ components with Go HTTP server using net/http.

    732 GitHub stars~591 tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Conventional Commits

What does Conventional Commits do?

A skill your agent uses when creating git commits, writing commit messages, or following version control workflows. Conventional Commits is an agent skill from Xe/site.

When should I use Conventional Commits?

Conventional Commits fits situations like: creating git commits; writing commit messages; following version control workflows.

How do I install Conventional Commits in Claude Code?

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

How do I install Conventional Commits in Codex?

Run `npx skills add Xe/site --skill conventional-commits -a codex`. Or copy the skill folder (.agents/skills/conventional-commits in Xe/site) into .agents/skills/conventional-commits in your project. Codex loads it when a task matches its description.

Can I use Conventional Commits 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 Xe/site --skill conventional-commits -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/conventional-commits, .gemini/skills/conventional-commits, .github/skills/conventional-commits and .opencode/skills/conventional-commits in your project.

What does Conventional Commits need to run?

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

Does Conventional Commits 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 Conventional Commits 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 Conventional Commits use?

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

How many tokens does Conventional Commits use?

About 1.3k tokens (SKILL.md is roughly 5.3k 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 Conventional Commits?

Skills that share tags, products or a category with Conventional Commits: Contextual Commit Messages (yamadashy/repomix, 29k stars), React Router Release Notes Prep (remix-run/react-router, 57k stars), Caveman Commit (vishiri/fantasia-archive, 409 stars) and PR Finalize Review (microsoft/garnet, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Conventional Commits?

Xe (a GitHub user) maintains it in Xe/site, which has 732 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 5, 2026.

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