MCPInstall

conventional-commits

This skill should be used when creating Git commits to ensure they follow the Conventional Commits specification. It provides guidance on commit message structure, types, scopes, and best practices for writing clear, consistent, and automated-friendly commit messages. Use when committing code changes or reviewing commit history.

Installs
270
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://smithery.ai --skill conventional-commits
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads conventional-commits automatically when relevant.

  3. 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

This skill provides guidance for writing Git commits that follow the Conventional Commits specification (v1.0.0).

Purpose

Conventional Commits is a specification for adding human and machine-readable meaning to commit messages. It provides an easy set of rules for creating an explicit commit history, which makes it easier to understand project changes and improve collaboration.

When to Use This Skill

Use this skill when:

  • Creating Git commits
  • Reviewing commit messages in PRs
  • Writing clear, structured commit messages
  • Collaborating on projects with multiple contributors

Commit Message Structure

Basic Format

<type>[optional scope]: <description>

[optional body]

[optional footer(s)]

Examples

feat: add user authentication
feat(api): add JWT token generation
fix: resolve memory leak in image processor
docs: update README with setup instructions
refactor(database): optimize user query performance

Commit Types

Primary Types

feat - A new feature for the user

feat: add export to PDF functionality
feat(api): add webhook signature verification

fix - A bug fix for the user

fix: resolve login redirect loop
fix(api): handle null response from GitHub webhook

docs - Documentation only changes

docs: update API endpoint documentation
docs(readme): add troubleshooting section

style - Changes that don't affect code meaning (formatting, whitespace)

style: format code with StandardRB
style(css): update button padding

refactor - Code change that neither fixes a bug nor adds a feature

refactor: extract user validation to service object
refactor(models): simplify tenant scoping logic

perf - Performance improvements

perf: add database index for user lookups
perf(queries): reduce N+1 queries in artifacts index

test - Adding or updating tests

test: add specs for user authentication
test(integration): add webhook processing tests

chore - Changes to build process, dependencies, or maintenance

chore: update Rails to 7.2.0
chore(deps): bump sidekiq from 7.1.0 to 7.2.0

Additional Types (Less Common)

build - Changes to build system or dependencies

build: configure Docker for production
build(webpack): update asset compilation settings

ci - Changes to CI configuration

ci: add security scanning to GitHub Actions
ci(tests): run RSpec in parallel

revert - Reverts a previous commit

revert: revert "feat: add export feature"

This reverts commit abc123.

Scope (Optional)

Scope provides additional context about what part of the codebase changed:

feat(auth): add two-factor authentication
fix(api): handle rate limit errors
docs(contributing): update PR guidelines
refactor(services): extract common validation logic

Common scope examples:

  • auth - Authentication/authorization
  • api - API endpoints
  • ui - User interface components
  • database or db - Database models/migrations
  • services - Service objects
  • jobs - Background jobs
  • tests - Test suite
  • deps - Dependencies
  • config - Configuration changes
  • docs - Documentation

Choose scopes that match your project's architecture and domain areas.

Description

The description is a short summary of the code change:

Rules:

  • Use imperative, present tense: "add" not "added" or "adds"
  • Don't capitalize first letter
  • No period (.) at the end
  • Keep under 72 characters (ideally under 50)

Good descriptions:

add user profile page
fix memory leak in file upload
update email templates for notifications
remove deprecated API endpoint

Bad descriptions:

Added user profile page          # Past tense
Fix Memory Leak In File Upload   # Capitalized
Updated email templates.          # Period at end
Lots of changes to the codebase   # Vague

Body (Optional)

The body provides additional context about the change:

When to include a body:

  • Complex changes needing explanation
  • Non-obvious design decisions
  • Breaking changes
  • Migration instructions

Format:

  • Separate from description with blank line
  • Use imperative mood like description
  • Wrap at 72 characters
  • Can include multiple paragraphs

Example:

feat(api): add webhook signature verification

Add HMAC-SHA256 signature verification for all incoming webhooks
to prevent unauthorized access and replay attacks.

The signature is validated using a secret key stored per
installation. Requests with invalid signatures are rejected
with a 401 response.

Footer (Optional)

Footers provide metadata about the commit:

Breaking Changes

Use BREAKING CHANGE: footer for incompatible API changes:

feat(api): change authentication endpoint

BREAKING CHANGE: The /auth endpoint now requires a client_id parameter.
Update all API clients to include client_id in authentication requests.

Or use ! after type/scope:

feat!: change authentication endpoint
feat(api)!: remove deprecated /login endpoint

Issue References

Reference issues and pull requests:

fix(auth): resolve session timeout bug

Fixes #123
Closes #456
Related to #789

Common reference types:

  • Fixes #123 - Closes the issue
  • Closes #123 - Closes the issue
  • Resolves #123 - Closes the issue
  • Related to #123 - References without closing
  • See also #123 - Additional reference

Co-authors

Credit multiple contributors:

feat: add data export feature

Co-authored-by: Jane Doe <jane@example.com>
Co-authored-by: John Smith <john@example.com>

Complete Examples

Simple Feature

feat: add password reset functionality

Feature with Scope

feat(api): add rate limiting for endpoints

Bug Fix with Body

fix(api): handle rate limit errors from GitHub

When GitHub API returns 429 status, retry the request
with exponential backoff up to 3 attempts before failing.

Fixes #234

Breaking Change

feat(api)!: redesign webhook payload structure

BREAKING CHANGE: Webhook payloads now use a nested structure.

Before:
{
  "event": "issue.created",
  "data": {...}
}

After:
{
  "type": "issue",
  "action": "created",
  "payload": {...}
}

Clients must update their webhook handlers to use the new structure.

Refactoring

refactor(services): extract validation to concern

Move common validation logic from multiple services into
a shared ValidationConcern module. No behavior changes.

Multiple Footers

fix(auth): resolve concurrent login race condition

Add database-level locking to prevent race condition when
multiple login attempts occur simultaneously for the same user.

Fixes #567
Related to #432
Reviewed-by: Jane Doe <jane@example.com>

Best Practices

Do:

✅ Use present tense imperative mood ("add" not "added") ✅ Keep first line under 50 characters when possible ✅ Reference issues/PRs in footer ✅ Explain "why" in body, not "what" (code shows what) ✅ Break up large changes into multiple commits ✅ Make commits atomic (one logical change per commit)

Don't:

❌ Use vague descriptions ("fix stuff", "updates") ❌ Combine multiple unrelated changes in one commit ❌ Capitalize first letter of description ❌ End description with period ❌ Use past tense ("added", "fixed") ❌ Commit broken code (each commit should work)

Summary

Conventional Commits provide:

  • ✅ Clear, consistent commit history
  • ✅ Better collaboration through explicit intent
  • ✅ Easier code review and git history navigation
  • ✅ Improved project documentation through structured messages

Key formula:

<type>(<scope>): <description>

[body]

[footer]

For detailed examples and edge cases, see references/commit-examples.md.

FAQ

What does the conventional-commits skill do?

This skill should be used when creating Git commits to ensure they follow the Conventional Commits specification. It provides guidance on commit message structure, types, scopes, and best practices for writing clear, consistent, and automated-friendly commit messages. Use when committing code changes or reviewing commit history.

How do I install conventional-commits?

Run npx skills add https://smithery.ai --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 smithery.ai in smithery.ai. It has 270 recorded installs.

More from smithery.ai

View all →

smithery-ai-cli

smithery.ai

Find, connect, and use MCP tools and skills via the Smithery CLI. Use when the user searches for new tools or skills, wants to discover integrations, connect to an MCP, install a skill, or wants to interact with an external service (email, Slack, Discord, GitHub, Jira, Notion, databases, cloud APIs, monitoring, etc.).

frontend-design

smithery.ai

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

Frontend & Design6.4K installs

skill-creator

smithery.ai

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Gemini CLI's capabilities with specialized knowledge, workflows, or tool integrations.

AI & Agents2.6K installs

ui-ux-pro-max

smithery.ai

UI/UX design intelligence for web, mobile, and desktop. This skill should be used when designing, building, reviewing, or fixing interfaces, including pages, components, design systems, accessibility, interaction, responsive layout, typography, color, charts, and stack-specific UI implementation. Searchable local data: 79 searchable styles (50 active), 192 product palettes and reasoning profiles, 74 font pairings, 119 UX guidelines, 105 icons, 17 GSAP presets, 25 chart types, and 22 stacks.

Frontend & Design1.3K installs

pdf

smithery.ai

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Docs & Writing1.3K installs

xlsx

smithery.ai

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Data & Databases984 installs

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

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.