
conventional-commits
Generate and validate commit messages following the Conventional Commits specification. Use when creating git commits, writing commit messages, reviewing commit history, generating changelogs, or when the user mentions commits, commit messages, semantic versioning, or changelog generation.
- Installs
- 73
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/enderpuentes/ai-agent-skills --skill conventional-commits- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads conventional-commits automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Conventional Commits
Overview
Conventional Commits is a specification for commit messages that provides an explicit structure for creating a clear commit history. It enables automated tools for generating changelogs, determining semantic version bumps, and communicating changes effectively.
Core Principle: Every commit message follows a structured format that clearly communicates the type and scope of changes.
Commit Message Structure
<type>[optional scope]: <description>
[optional body]
[optional footer(s)]
Quick Reference
| Element | Required | Format | Purpose |
|---|---|---|---|
| Type | ✅ Yes | feat, fix, or custom | Indicates the nature of the change |
| Scope | ❌ Optional | Parentheses: (parser) | Provides additional context |
| Breaking | ❌ Optional | ! after type/scope | Indicates breaking changes |
| Description | ✅ Yes | Short summary | Brief description of the change |
| Body | ❌ Optional | Free-form paragraphs | Detailed explanation |
| Footer | ❌ Optional | Token: value format | Metadata (e.g., BREAKING CHANGE:) |
Commit Types
Standard Types
feat: A new feature (correlates with MINOR in SemVer)fix: A bug fix (correlates with PATCH in SemVer)
Additional Types (Common)
build: Changes to build system or dependencieschore: Maintenance tasks, no production code changeci: Changes to CI configurationdocs: Documentation only changeshotfix: Emergency bug fix applied directly to production, bypassing normal development workflow (correlates with PATCH in SemVer)perf: Performance improvementsrefactor: Code refactoring without behavior changestyle: Code style changes (formatting, missing semicolons, etc.)test: Adding or updating tests
Breaking Changes
Breaking changes can be indicated in two ways:
-
In the type/scope prefix: Append
!before the colonfeat!: remove deprecated API feat(api)!: change authentication method -
In the footer: Use
BREAKING CHANGE:tokenfeat: add new authentication system BREAKING CHANGE: Old authentication tokens are no longer valid
Examples
Basic Feature Commit
feat: add user authentication endpoint
Implement JWT-based authentication with login and token validation
Feature with Scope
feat(auth): implement password reset flow
Add forgot password endpoint and email notification system
Bug Fix
fix(parser): correct array parsing with multiple spaces
Handle edge case where strings contained multiple consecutive spaces
Breaking Change (Prefix)
feat(api)!: remove deprecated v1 endpoints
BREAKING CHANGE: All v1 API endpoints have been removed. Migrate to v2.
Breaking Change (Footer)
feat: update database schema
BREAKING CHANGE: Environment variables now take precedence over config files
Documentation
docs: update API reference for authentication endpoints
Refactoring
refactor(auth): extract token validation to separate module
Improve code organization and testability
Performance
perf(queries): optimize database query for user lookup
Reduce query time from 500ms to 50ms by adding index
Hotfix
Security Hotfix
hotfix(auth): fix critical security vulnerability in token validation
Immediate fix for CVE-2024-XXXX. Patch token validation to prevent unauthorized access.
Database Hotfix
hotfix(db): fix connection pool exhaustion causing service outage
Emergency patch to increase pool size and add connection timeout. Applied directly to production to restore service.
Payment Hotfix
hotfix(payment): fix incorrect currency conversion in checkout
Critical bug causing incorrect charges. Immediate fix applied to prevent financial impact.
API Hotfix
hotfix(api): fix null pointer exception in user endpoint
Emergency fix for production crash. Bypassed normal deployment process.
Performance Hotfix
hotfix(cache): fix memory leak causing server crashes
Immediate fix for production instability. Applied hotfix to prevent service degradation.
Data Integrity Hotfix
hotfix(data): fix corrupted data migration affecting user accounts
Emergency fix applied directly to production database to prevent data loss.
Common Mistakes
❌ Missing Colon and Space
feat add authentication
✅ Correct:
feat: add authentication
❌ Uppercase Type
FEAT: add authentication
✅ Correct:
feat: add authentication
❌ Description Too Long
feat: add user authentication with JWT tokens, password hashing, session management, and email verification
✅ Correct:
feat(auth): implement JWT-based authentication
Add login endpoint, password hashing, session management, and email verification
❌ Using Wrong Type
fix: add new feature for user dashboard
✅ Correct:
feat: add user dashboard
❌ Breaking Change Not Indicated
feat(api): remove deprecated endpoints
✅ Correct:
feat(api)!: remove deprecated endpoints
BREAKING CHANGE: All v1 endpoints have been removed
❌ Scope Without Parentheses
feat auth: implement login
✅ Correct:
feat(auth): implement login
Workflow Guidelines
When Creating Commits
- Determine the type: Is this a feature, fix, or other type?
- Use
hotfixfor emergency fixes applied directly to production, bypassing normal development workflow - Use
fixfor regular bug fixes in normal development workflow
- Use
- Identify scope (optional): Which part of the codebase is affected?
- Check for breaking changes: Does this change break existing functionality?
- Write concise description: Keep under 72 characters when possible
- Add body if needed: Provide context, motivation, or details
- Include footer if applicable: Add breaking changes, references, etc.
Description Best Practices
- Use imperative mood: "add feature" not "added feature" or "adds feature"
- Don't end with a period
- Keep it concise (50-72 characters ideal)
- Focus on what changed, not why (why goes in body)
Body Best Practices
- Separate from description with blank line
- Explain the "why" behind the change
- Provide context or background
- Reference related issues or PRs
Semantic Versioning Correlation
| Commit Type | SemVer Impact |
|---|---|
fix | PATCH (1.0.0 → 1.0.1) |
hotfix | PATCH (1.0.0 → 1.0.1) |
feat | MINOR (1.0.0 → 1.1.0) |
BREAKING CHANGE | MAJOR (1.0.0 → 2.0.0) |
| Other types | No automatic version bump |
Validation Checklist
Before finalizing a commit message, verify:
- Type is lowercase and valid
- Colon and space follow type/scope
- Description is concise and imperative
- Breaking changes are properly indicated
- Body is separated by blank line (if present)
- Footer tokens use hyphens (e.g.,
BREAKING CHANGE, notBREAKING_CHANGE) - Message doesn't exceed 120 characters in title (if team standard)
Special Cases
Revert Commits
revert: let us never again speak of the noodle incident
Refs: 676104e, a215868
Multiple Commits for One Feature
If a commit conforms to multiple types, split into separate commits when possible:
feat(auth): add login endpoint
test(auth): add login endpoint tests
docs(auth): update API documentation for login
Integration with Tools
Conventional Commits enables:
- Automatic changelog generation: Tools parse commit history
- Semantic versioning: Automated version bumps based on commit types
- Release notes: Extract features and fixes from commits
- Build triggers: Different build processes for different commit types
Additional Resources
- reference.md — Official spec, commit types, SemVer correlation, tooling — indexable
- Official spec: https://www.conventionalcommits.org/en/v1.0.0/
Specification Reference
This skill is based on the official Conventional Commits specification v1.0.0.
All rules, examples, and guidelines in this skill follow the official specification. For the complete specification, examples, and FAQ, refer to the official documentation.
FAQ
What does the conventional-commits skill do?
Generate and validate commit messages following the Conventional Commits specification. Use when creating git commits, writing commit messages, reviewing commit history, generating changelogs, or when the user mentions commits, commit messages, semantic versioning, or changelog generation.
How do I install conventional-commits?
Run npx skills add https://github.com/enderpuentes/ai-agent-skills --skill conventional-commits in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/conventional-commits/ (personal) or .claude/skills/conventional-commits/ (project).
Which AI agents can use conventional-commits?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is conventional-commits safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains conventional-commits?
It is published by enderpuentes in enderpuentes/ai-agent-skills. It has 73 recorded installs.
More from enderpuentes/ai-agent-skills
pagespeed-insights
enderpuentes/ai-agent-skills
Audit web pages for performance optimization following PageSpeed Insights guidelines. Use when analyzing page performance, optimizing web applications, reviewing performance metrics, implementing Core Web Vitals improvements, or when the user mentions page speed, performance optimization, Lighthouse scores, or Core Web Vitals.
tailwind-css
enderpuentes/ai-agent-skills
Open the skill to read its SKILL.md instructions.
typescript
enderpuentes/ai-agent-skills
Open the skill to read its SKILL.md instructions.
zod
enderpuentes/ai-agent-skills
Define and use Zod schemas for TypeScript-first validation: primitives, objects, arrays, unions, refinements, transform, z.infer, parse, safeParse. Use when validating input, parsing API data, form validation with react-hook-form, or when the user mentions Zod, schema validation, or z.infer.
shadcn-ui
enderpuentes/ai-agent-skills
Open the skill to read its SKILL.md instructions.
jsdoc
enderpuentes/ai-agent-skills
Write and maintain JSDoc comments for JavaScript and TypeScript APIs: functions, classes, modules, parameters, returns, examples, and TODO annotations. Use when documenting code, generating API docs, setting JSDoc conventions, or when the user mentions JSDoc tags like @param, @returns, or @todo.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.