conventional-commits
Writes and reviews Conventional Commits commit messages (v1.0.0) to support semantic versioning and automated changelogs. Use when drafting git commit messages, PR titles, release notes, or when enforcing a conventional commit format (type(scope): subject, BREAKING CHANGE, footers, revert).
Best use case
conventional-commits is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Writes and reviews Conventional Commits commit messages (v1.0.0) to support semantic versioning and automated changelogs. Use when drafting git commit messages, PR titles, release notes, or when enforcing a conventional commit format (type(scope): subject, BREAKING CHANGE, footers, revert).
Teams using conventional-commits should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/conventional-commits/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How conventional-commits Compares
| Feature / Agent | conventional-commits | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Writes and reviews Conventional Commits commit messages (v1.0.0) to support semantic versioning and automated changelogs. Use when drafting git commit messages, PR titles, release notes, or when enforcing a conventional commit format (type(scope): subject, BREAKING CHANGE, footers, revert).
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Conventional Commits (v1.0.0) Use the Conventional Commits spec to produce consistent commit messages that are easy to parse for changelogs and semantic versioning. ## Commit message format (canonical) ```text <type>[optional scope][!]: <description> [optional body] [optional footer(s)] ``` Rules: - Separate **header**, **body**, **footers** with a blank line. - Keep the **header** on one line. - Put `!` immediately before `:` to mark a breaking change (e.g. `feat!: ...`, `refactor(api)!: ...`). ## Choose a type The spec allows any type, but these are common and widely supported by tooling: - `feat`: introduce a new feature (user-facing) - `fix`: bug fix (user-facing) - `docs`: documentation-only changes - `refactor`: refactor that neither fixes a bug nor adds a feature - `perf`: performance improvement - `test`: add or adjust tests - `build`: build system/dependencies - `ci`: CI configuration/scripts - `chore`: maintenance tasks - `style`: formatting (whitespace, missing semicolons, etc.) - `revert`: revert a previous commit Default choice when unsure: - If users see new behavior → `feat` - If users see corrected behavior → `fix` - Otherwise → `chore` or a more specific maintenance type (`refactor`, `build`, `ci`) ## Optional scope Use scope to clarify the area impacted. Format: ```text type(scope): description ``` Guidelines: - Use a short noun: `api`, `auth`, `ui`, `db`, `cli`, `deps`, `docs`. - Use repo/module/package name when working in a monorepo. - If scope adds no clarity, omit it. ## Description (subject) Write the description as a short summary of what the change does. Guidelines: - Use **imperative** mood: “add”, “fix”, “remove”, “update”. - Avoid ending punctuation. - Be specific; avoid “stuff”, “changes”, “update things”. Examples: ```text feat(auth): add passwordless login fix(api): handle empty pagination cursor chore(deps): bump react to 18.3.0 ``` ## Body (optional) Use the body to explain motivation, constraints, or high-level implementation notes. Guidelines: - Prefer complete sentences. - If helpful, include: - why the change was needed - what approach was chosen - notable trade-offs Example: ```text refactor(parser): simplify tokenization Replace the regex pipeline with a small state machine to reduce backtracking. ``` ## Footers (optional) Footers are key/value-like lines at the end. Use them for: - breaking change details - issue references - metadata used by tooling Examples: ```text Refs: #123 Closes: #456 Co-authored-by: Name <email@example.com> ``` ## Breaking changes Mark breaking changes in one (or both) of these ways: 1. Add `!` in the header: ```text feat(api)!: remove deprecated v1 endpoints ``` 2. Add a `BREAKING CHANGE:` footer (recommended when you need an explanation): ```text feat(api): remove deprecated v1 endpoints BREAKING CHANGE: /v1/* endpoints are removed; migrate to /v2/*. ``` ## Reverts Use the `revert` type when undoing a previous change. Example: ```text revert: feat(auth): add passwordless login This reverts commit 1a2b3c4. ``` ## Semantic versioning mapping (typical) Common mapping for automated version bumps: - `fix` → patch - `feat` → minor - any breaking change (`!` or `BREAKING CHANGE:`) → major ## When asked to “write a commit message” Collect missing inputs quickly: - What changed? (1–2 sentences) - Scope/module? (optional) - User-facing? (feature vs fix vs chore) - Breaking? (yes/no; migration note if yes) - Any issue IDs to reference? Then produce: 1. A conventional header 2. Optional body (only if it adds clarity) 3. Optional footers (`Refs:`, `Closes:`, `BREAKING CHANGE:`) ## Ready-to-use templates Minimal: ```text <type>: <description> ``` With scope: ```text <type>(<scope>): <description> ``` Breaking change with explanation: ```text <type>(<scope>): <description> BREAKING CHANGE: <what breaks and how to migrate> ```
Related Skills
Conventional Commit Generator
This skill should be used when the user asks to "create a conventional commit", "generate conventional commits", "commit with conventional format", "group my changes for commits", "make a conventional commit message", or mentions "semantic commits", "commitizen", "commit conventions". Analyzes staged and unstaged changes, groups related modifications, and generates properly formatted conventional commit messages with interactive commit grouping options.
bgo
Automated Blender build-go workflow. Automatically builds, removes old version, installs, enables, and launches Blender with your extension/add-on. Use when you want to quickly test changes, execute complete build-to-launch cycle, or run custom packaging scripts with automatic Blender launch.
deleting-op-secrets
Deletes or archives secrets in 1Password using the op CLI. Use when the user needs to permanently remove items, archive deprecated credentials, or clean up unused secrets from 1Password vaults. Supports both permanent deletion and archiving for later recovery.
definition.tech_spike
Scope and prioritize technical spikes that de-risk architecture or implementation questions.
defi-protocol-templates
Implement DeFi protocols with production-ready templates for staking, AMMs, governance, and lending systems. Use when building decentralized finance applications or smart contract protocols.
deepgram-automation
Automate Deepgram tasks via Rube MCP (Composio). Always search tools first for current schemas.
deel-automation
Automate Deel tasks via Rube MCP (Composio). Always search tools first for current schemas.
declarative-agents-microsoft365
Comprehensive development guidelines for Microsoft 365 Copilot declarative agents with schema v1.5, TypeSpec integration, and Microsoft 365 Agents Toolkit workflows Triggers on: **.json, **.ts, **.tsp, **manifest.json, **agent.json, **declarative-agent.json
deck-cli
Manage Kong Gateway and Konnect declaratively using decK CLI. Use when working with Kong Gateway configurations, syncing state, converting OpenAPI specs to Kong config, validating configurations, or automating Kong deployments. Handles declarative configuration files, API lifecycle automation, and Kong entity management.
debugging-memory
This skill should be used when the user asks to "debug this", "fix this bug", "why is this failing", "investigate error", "getting an error", "exception thrown", "crash", "not working", "what's causing this", "root cause", "diagnose this issue", or describes any software bug or error. Also activates when spawning subagents for debugging tasks, using Task tool for bug investigation, or coordinating multiple agents on a debugging problem. Provides memory-first debugging workflow that checks past incidents before investigating.
debug
Systematic debugging with hypothesis testing. Persistent across sessions.
debate-persona-generator
Generates three distinct expert challenger personas for multi-perspective debate. Each persona critiques from a different angle.