conventional-git

A naming rule-book for a project's history: write every branch name and commit message the same way, and release notes and version numbers can be generated instead of typed.

WHEN TO USE

SCOPE

USE FOR

Name a new branch or worktree so its purpose is clear at a glance in git history.
Write a commit message that a changelog tool can parse and turn into a version bump.
Close a GitHub or GitLab issue automatically by referencing it in a commit footer.
Fix a squash-merged pull request title so the changelog doesn't break silently.

This is a saved copy of the skill's SKILL.md instructions. It may differ from the upstream file or the version you install.

In this document (7)

Conventional Commits & Branch Naming

Follow Conventional Commits v1.0.0 for both branch names and commit messages — consistent naming lets tools auto-generate changelogs, enforce SemVer bumps, and filter history by concern.

Branch Naming

Format: <type>/[issue-]<description> — lowercase, hyphens only, no special chars except /.

feat/user-authentication
feat/42-user-authentication
fix/login-race-condition
fix/87-login-race-condition
docs/api-reference-update
refactor/payment-module

Prefix with the issue number when one exists — GitHub and GitLab auto-link it and it makes git log immediately traceable to the tracker. Keep the description under 50 characters — most git UIs truncate branch names in lists around that length. Match the type to the work you're doing — this is the contract readers use to understand the branch purpose at a glance.

NEVER include worktree in a branch name — git worktrees are a local checkout mechanism, not a branch concept; the name would leak implementation details into the remote and confuse other contributors.

Worktree Naming

Worktrees are local checkout directories — they never appear in the remote. Place them under .claude/worktrees/ and name them by replacing the branch / separator with -.

git worktree add .claude/worktrees/feat-user-authentication feat/user-authentication
git worktree add .claude/worktrees/fix-87-login-race-condition fix/87-login-race-condition

The directory name mirrors the branch name so git worktree list stays readable and each worktree is immediately traceable to its branch without inspecting the checkout. Run git worktree list before creating a new one — reuse an existing worktree if it already covers the same branch.

Keep worktrees scoped to a single branch. Doing unrelated work inside someone else's worktree obscures which changes belong where and makes cleanup error-prone.

Remove the worktree once its branch is merged — either after a local merge or after the pull/merge request is closed on the remote. Stale worktrees accumulate and make git worktree list unreadable.

git worktree remove .claude/worktrees/feat-user-authentication   # branch merged locally
git worktree prune                                                # remove refs to already-deleted directories

Commit Message Format

<type>[optional scope]: <description>
[optional body]
[optional footer(s)]

Types:

Type	SemVer	When
`feat`	MINOR	New feature
`fix`	PATCH	Bug fix
`docs`	—	Docs only
`style`	—	Formatting, no logic change
`refactor`	—	Restructure, no feature/fix
`perf`	—	Performance improvement
`test`	—	Add/fix tests
`build`	—	Build system, deps
`ci`	—	CI config
`chore`	—	Anything else (not src/test)
`revert`	—	Reverts a previous commit

Rules:

Subject line ≤ 72 characters — git log and GitHub/GitLab UIs silently truncate longer subjects
Imperative mood: "add" not "added" — reads as an instruction, not a history log
No capital letter, no trailing period — enforces uniform parsing by changelog tools
Body separated by blank line — parsers split header/body at the first blank line
Breaking changes: use ! after type/scope, or add BREAKING CHANGE: footer (triggers MAJOR bump) — body-only descriptions are invisible to changelog tools
revert commits SHOULD include This reverts commit <hash>. in the body — git revert generates this automatically; don't strip it
NEVER add a Claude signature, AI agent attribution, or Co-authored-by trailer for Claude or any other AI agent to commits

Examples:

feat(auth): add JWT token refresh

fix: prevent race condition on concurrent requests

Introduce request ID and reference to latest request.
Dismiss responses from stale requests.

refactor!: drop support for Go 1.18

BREAKING CHANGE: Go 1.18 no longer supported; uses stdlib APIs from 1.21+

Closing Issues via Commit Messages

Both GitHub and GitLab detect keywords in commit messages and automatically close the referenced issue when the commit lands on the default branch. Place the reference in the footer (preferred — keeps the subject line clean).

Keywords: close, closes, closed, fix, fixes, fixed, resolve, resolves, resolved — case-insensitive.

GitHub:

fix(auth): prevent token expiry race condition

Closes #42
Closes owner/repo#99

Triggers when merged into the default branch (usually main)
Cross-repo: Closes owner/repo#42
Close multiple: Closes #42, closes #43
Works in PR descriptions too

GitLab:

feat: add dark mode support

Resolves #101
Closes group/project#42

Triggers when merged into the default branch (configurable per project)
Cross-project: Closes group/project#42
Close multiple: Closes #101, closes #102
Works in MR descriptions too

Tip: Pair with the commit type — fix: closing a bug issue, feat: closing a feature request — keeps the changelog semantically coherent.

Common Mistakes

Mistake	Fix
`feat: Added login page`	`feat: add login page` — imperative, no capital
`fix: fix bug.`	`fix: fix bug` — no trailing period
Subject over 72 chars	Shorten; move detail to body
Breaking change only in body	Add `!` or `BREAKING CHANGE:` footer — tools won't detect body-only
`feat(adding-auth): ...`	`feat(auth): ...` — scope is a noun, not a verb
Closes #42 in subject line	Move to footer — keeps subject clean and parseable

Best Practices

Align branch type and commit type — feat/auth-* branch → feat(auth): commits
One concern per branch — mixing fixes into feature branches obscures the changelog
Use scope consistently within a branch — feat(auth): throughout, not feat(user): mid-way
Squash merge: when squash-merging a PR/MR, the branch commits are collapsed into one — the PR/MR title becomes the commit message. If the title doesn't follow conventional commits format, changelog generation breaks silently. Always set the PR title before squashing.

Local tool required

1 FOR YOU

01
Have git installed
Install git, since the skill's branch naming, worktree naming, and commit conventions are applied through git worktree add, git worktree list, and git commit commands, and the frontmatter itself declares git as required.

Listed as free: Connected services may require an account or charge fees.
Installation: One command — usually under 2 minutes.

This skill ships inside the Samber Marketing & Engineering Skills plugin.

Run this outside your AI tool, using Node.js 22.20.0 or newer. Skills CLI 1.7.2 skips skill selection; prompts cancel installation without an interactive terminal. If choosing Project when asked about installation scope, open your project's folder before running this.

Install checklist

Check selected tools if a picker appears; Claude Code may be unchecked under Additional agents. ↑/↓ moves, Space toggles selections, Enter confirms.
Without a tool picker, check Installing to: for your intended tool. Stop if it names a different tool.
If asked, choose Symlink (Recommended) for shared files or Copy to all agents for separate copies; review the summary before confirming installation.
Install the find-skills skill? defaults to Yes, adding another skill for all projects. Choose No if you don't want that extra installation.

Skills CLI 1.7.2 sends install data to skills.sh by default, including the source, skill names, target tools and file details; GitHub sources are reported only when GitHub confirms the repository is public, while other remote sources can also be reported. Confirmed-public GitHub sources also trigger a security-audit request. Before installing, set the environment variable DO_NOT_TRACK=1 or DISABLE_TELEMETRY=1 to disable both.

npx skills add samber/cc-skills --skill "conventional-git" --full-depth

After installing for Claude Code, open it in the installation project if you chose Project; Global makes the skill available across projects on this computer. Once Claude Code loads the skill, its description helps Claude decide when to use it.

If installation created a top-level skills folder that did not exist when your Claude Code session started, run /reload-skills in that session. Run it again after later changes in that folder.

What's inside

Files included with this skill.

View on GitHub

Same repository

chrome-extension
Build Chrome extensions with Manifest V3. Use this skill whenever the user mentions Chrome extension, browser extension, manifest.json, content script, service worker (in extension context), popup, side panel, chrome.runtime, chrome.tabs, chrome.storage, chrome.scripting, or any Chrome extension API. Also trigger when the user wants to inject scripts into web pages, communicate between page and background, bypass CSP from a content script, build an RPC layer over chrome messaging, or publish to the Chrome Web Store. Covers both new extension projects and adding features to existing ones. Do NOT use for CRXJS/Vite-based builds with HMR — use samber/cc-skills@crxjs instead.Read full description
copywriting-cta
Designs end-of-article CTAs — copy, layout, placement, A/B test plan, accessibility — for blog posts, newsletters, and essays. Use whenever the user asks to write, review, or improve a CTA at the bottom of an article; mentions "end-of-post CTA", "call-to-action", "signup box", "newsletter CTA", "subscribe block", or "what should I put at the bottom"; or asks how to turn readers into subscribers, leads, customers, or paying supporters. Covers personal blogs, paid newsletters (Substack, beehiiv, Ghost), and brand content-marketing blogs. Do NOT use for opening hooks, ledes, or post titles — use samber/cc-skills@copywriting-hooks instead. Not for landing-page, ad, or email copy.Read full description
copywriting-hooks
Writes opening hooks and post titles for long-form articles in EN or FR — blog posts, Substack/Medium/dev.to, LinkedIn long-form, newsletters, essays. Trigger whenever the user asks for a hook, opening, lede, intro, first sentence/paragraph, opener, accroche, attaque, phrase d'accroche, or première phrase — including punching up a flat intro or draft opening — or for a post title, titre d'article, or headline. Do NOT trigger for social posts (LinkedIn feed, Twitter/X, TikTok, Bluesky), READMEs, taglines, email subjects, ad copy, landing-page headlines, press releases, SEO meta, or body rewrites. Do NOT use for end-of-article CTAs — use samber/cc-skills@copywriting-cta instead.Read full description
copywriting-prose-creator
Codifies how a person or brand writes — lexicon, syntax, rhythm, structure, signature moves — into a PROSE.md guide, independent of emotional tone. Builds from SOUL.md and TONE.md, ports a guide to another channel, or reverse-engineers prose patterns from a corpus. Trigger on PROSE.md, writing style guide, prose guide, house style, ghostwriter style, writing playbook, banned words, sentence-length targets, or multi-writer consistency in a content factory. Do NOT use for writing actual content — use samber/cc-skills@linkedin-ghostwriting or samber/cc-skills@technical-article-writer instead. Not for tone decisions (samber/cc-skills@copywriting-tone-of-voice-creator), hooks, or CTAs.Read full description
copywriting-tone-of-voice-creator
Builds a brand tone of voice guide (TONE.md) — voice attributes with do's/don'ts, NN/g positioning, tone modulation matrix, lexicon, channel rules — for downstream content skills to consume. Also ports an existing TONE.md to a new channel (blog → LinkedIn, web → Twitter/X, in-product UI). Covers B2B SaaS, B2C/D2C, NGO, public sector, consulting, industrial, product-led, personal, and volunteering brands. Apply when the user wants to define or refresh a brand voice, port it to a new channel, or set up a content factory. Not for writing individual posts, articles, emails, or UI strings — use the dedicated writing skills. Not for SOUL.md, PROSE.md (samber/cc-skills@copywriting-prose-creator), or DESIGN.md.Read full description
crxjs
CRXJS Chrome extension development — true HMR for popup, options, content scripts, side panels, manifest-driven builds, dynamic content script imports (?script, ?script&module), and defineManifest for type-safe manifests. Uses Vite as its build tool. Use when the user mentions CRXJS, crxjs, @crxjs/vite-plugin, 'extension with hot reload', 'HMR for chrome extension', or wants to set up a CRXJS-based Chrome extension project with any framework (React, Vue, Svelte, Solid, Vanilla). Also trigger when the user has an existing CRXJS project and wants to add features, fix HMR issues, or configure content scripts with CRXJS. For general Chrome extension architecture (messaging, CSP, storage, permissions) -> See samber/cc-skills@chrome-extension skill.Read full description