conventional-commits

Format commit messages using the Conventional Commits specification. Use when creating commits, writing commit messages, or when the user mentions commits, git commits, or commit messages. Ensures commits follow the standard format for automated tooling, changelog generation, and semantic versioning.

3,880 stars

Best use case

conventional-commits is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Format commit messages using the Conventional Commits specification. Use when creating commits, writing commit messages, or when the user mentions commits, git commits, or commit messages. Ensures commits follow the standard format for automated tooling, changelog generation, and semantic versioning.

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

$curl -o ~/.claude/skills/conventional-commits/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/bastos/conventional-commits/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/conventional-commits/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How conventional-commits Compares

Feature / Agentconventional-commitsStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Format commit messages using the Conventional Commits specification. Use when creating commits, writing commit messages, or when the user mentions commits, git commits, or commit messages. Ensures commits follow the standard format for automated tooling, changelog generation, and semantic versioning.

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.

Related Guides

SKILL.md Source

# Conventional Commits

Format all commit messages according to the [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/) specification. This enables automated changelog generation, semantic versioning, and better commit history.

## Format Structure

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

[optional body]

[optional footer(s)]
```

## Commit Types

### Required Types

- **`feat:`** - A new feature (correlates with MINOR in Semantic Versioning)
- **`fix:`** - A bug fix (correlates with PATCH in Semantic Versioning)

### Common Additional Types

- **`docs:`** - Documentation only changes
- **`style:`** - Code style changes (formatting, missing semicolons, etc.)
- **`refactor:`** - Code refactoring without bug fixes or new features
- **`perf:`** - Performance improvements
- **`test:`** - Adding or updating tests
- **`build:`** - Build system or external dependencies changes
- **`ci:`** - CI/CD configuration changes
- **`chore:`** - Other changes that don't modify src or test files
- **`revert:`** - Reverts a previous commit

## Scope

An optional scope provides additional contextual information about the section of the codebase:

```
feat(parser): add ability to parse arrays
fix(auth): resolve token expiration issue
docs(readme): update installation instructions
```

## Description

- Must immediately follow the colon and space after the type/scope
- Use imperative mood ("add feature" not "added feature" or "adds feature")
- Don't capitalize the first letter
- No period at the end
- Keep it concise (typically 50-72 characters)

## Body

- Optional longer description providing additional context
- Must begin one blank line after the description
- Can consist of multiple paragraphs
- Explain the "what" and "why" of the change, not the "how"

## Breaking Changes

Breaking changes can be indicated in two ways:

### 1. Using `!` in the type/scope

```
feat!: send an email to the customer when a product is shipped
feat(api)!: send an email to the customer when a product is shipped
```

### 2. Using BREAKING CHANGE footer

```
feat: allow provided config object to extend other configs

BREAKING CHANGE: `extends` key in config file is now used for extending other config files
```

### 3. Both methods

```
chore!: drop support for Node 6

BREAKING CHANGE: use JavaScript features not available in Node 6.
```

## Examples

### Simple feature

```
feat: add user authentication
```

### Feature with scope

```
feat(auth): add OAuth2 support
```

### Bug fix with body

```
fix: prevent racing of requests

Introduce a request id and a reference to latest request. Dismiss
incoming responses other than from latest request.

Remove timeouts which were used to mitigate the racing issue but are
obsolete now.
```

### Breaking change

```
feat!: migrate to new API client

BREAKING CHANGE: The API client interface has changed. All methods now
return Promises instead of using callbacks.
```

### Documentation update

```
docs: correct spelling of CHANGELOG
```

### Multi-paragraph body with footers

```
fix: prevent racing of requests

Introduce a request id and a reference to latest request. Dismiss
incoming responses other than from latest request.

Remove timeouts which were used to mitigate the racing issue but are
obsolete now.

Reviewed-by: Z
Refs: #123
```

## Guidelines

1. **Always use a type** - Every commit must start with a type followed by a colon and space
2. **Use imperative mood** - Write as if completing the sentence "If applied, this commit will..."
3. **Be specific** - The description should clearly communicate what changed
4. **Keep it focused** - One logical change per commit
5. **Use scopes when helpful** - Scopes help categorize changes within a codebase
6. **Document breaking changes** - Always indicate breaking changes clearly

## Semantic Versioning Correlation

- **`fix:`** → PATCH version bump (1.0.0 → 1.0.1)
- **`feat:`** → MINOR version bump (1.0.0 → 1.1.0)
- **BREAKING CHANGE** → MAJOR version bump (1.0.0 → 2.0.0)

## When to Use

Use this format for:
- All git commits
- Commit message generation
- Pull request merge commits
- When the user asks about commit messages or git commits

## Common Mistakes to Avoid

❌ `Added new feature` (past tense, capitalized)
✅ `feat: add new feature` (imperative, lowercase)

❌ `fix: bug` (too vague)
✅ `fix: resolve null pointer exception in user service`

❌ `feat: add feature` (redundant)
✅ `feat: add user profile page`

❌ `feat: Added OAuth support.` (past tense, period)
✅ `feat: add OAuth support`

Related Skills

daily-commits

3891
from openclaw/skills

Summarize a person's git commits for a specific date, grouped by feature points, in English. Use when reviewing daily work output.

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research