Claude
Skills
Sign in
Back

changelog-generator

Included with Lifetime
$97 forever

Generate changelogs and release notes from Conventional Commits. Covers commit parsing, semantic version bump detection, Keep a Changelog formatting, monorepo scoped changelogs, CI integration, and commit message linting. Use when preparing releases, enforcing commit standards, or automating release notes.

Cloud & DevOpsscripts

What this skill does

# Changelog Generator

**Tier:** POWERFUL
**Category:** Engineering / Release Management
**Maintainer:** Claude Skills Team

## Overview

Generate consistent, auditable changelogs and release notes from Conventional Commits. Parses commit messages, detects semantic version bumps (major/minor/patch), renders Keep a Changelog sections, supports monorepo scoped changelogs, integrates with CI for automated release notes, and enforces commit format with linting. Separates commit parsing, bump logic, and rendering so teams can automate releases without losing editorial control.

## Keywords

changelog, release notes, conventional commits, semantic versioning, semver, Keep a Changelog, commit linting, release automation, monorepo changelog

## Core Capabilities

### 1. Commit Parsing
- Parse Conventional Commit messages into structured data
- Extract type, scope, description, body, and footer
- Detect breaking changes from `!` suffix and `BREAKING CHANGE:` footer
- Handle multi-line commit bodies and co-author trailers

### 2. Semantic Version Detection
- Map commit types to version bump levels
- Breaking changes trigger major bumps
- `feat` triggers minor bumps
- All other types trigger patch bumps
- Support for pre-release versions (alpha, beta, rc)

### 3. Changelog Rendering
- Keep a Changelog format with semantic sections
- GitHub release notes format
- Plain markdown for documentation
- JSON output for automation pipelines
- Grouped by type with user-readable descriptions

### 4. Quality Enforcement
- Commit message linter for CI and pre-commit hooks
- Strict mode that blocks non-conforming commits
- Scope validation against allowed values
- Breaking change documentation requirements

## When to Use

- Before publishing a release tag
- During CI to generate release notes automatically
- In PR checks to enforce commit message standards
- In monorepos where package changelogs need scoped filtering
- When converting raw git history into user-facing notes
- As a pre-release checklist step

## Conventional Commit Format

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

[optional body]

[optional footer(s)]
```

### Type to Section Mapping

| Commit Type | Changelog Section | SemVer Bump | User-Facing? |
|-------------|------------------|-------------|-------------|
| `feat` | Added | minor | Yes |
| `fix` | Fixed | patch | Yes |
| `perf` | Performance | patch | Yes |
| `security` | Security | patch | Yes |
| `deprecated` | Deprecated | minor | Yes |
| `remove` | Removed | major | Yes |
| `refactor` | Changed | patch | Sometimes |
| `docs` | — | patch | No |
| `test` | — | — | No |
| `build` | — | — | No |
| `ci` | — | — | No |
| `chore` | — | — | No |

### Breaking Change Rules

Breaking changes always trigger a **major** version bump regardless of type:

```
feat(api)!: remove deprecated v1 endpoints

BREAKING CHANGE: The /api/v1/* endpoints have been removed.
Migrate to /api/v2/* before upgrading. See migration guide at docs/v2-migration.md.
```

## Changelog Rendering

### Keep a Changelog Format

```markdown
# Changelog

All notable changes to this project will be documented in this file.

The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

## [1.4.0] - 2026-03-09

### Added
- User can now export projects as CSV ([#234](https://github.com/org/repo/pull/234))
- Dark mode support for dashboard ([#228](https://github.com/org/repo/pull/228))

### Fixed
- Pagination returning duplicate items on page boundaries ([#231](https://github.com/org/repo/pull/231))
- Login form not showing validation errors on mobile ([#229](https://github.com/org/repo/pull/229))

### Performance
- Reduced dashboard load time by 40% with query optimization ([#232](https://github.com/org/repo/pull/232))

### Security
- Updated jsonwebtoken to 9.0.2 to fix CVE-2024-XXXX ([#233](https://github.com/org/repo/pull/233))

## [1.3.2] - 2026-02-28

### Fixed
- API rate limiter not resetting after window expiry ([#227](https://github.com/org/repo/pull/227))

[1.4.0]: https://github.com/org/repo/compare/v1.3.2...v1.4.0
[1.3.2]: https://github.com/org/repo/compare/v1.3.1...v1.3.2
```

### GitHub Release Notes Format

```markdown
## What's New

- **CSV Export**: Users can now export project data as CSV files (#234)
- **Dark Mode**: Dashboard fully supports dark mode (#228)

## Bug Fixes

- Fixed pagination returning duplicate items on page boundaries (#231)
- Fixed login form validation on mobile devices (#229)

## Performance

- Dashboard load time reduced by 40% through query optimization (#232)

## Security

- Updated jsonwebtoken to patch CVE-2024-XXXX (#233)

**Full Changelog**: https://github.com/org/repo/compare/v1.3.2...v1.4.0
```

## Generation Workflow

### Step 1: Collect Commits

```bash
# Get commits between two tags
git log v1.3.2..HEAD --pretty=format:'%H %s' --no-merges

# Get commits with full body (for breaking change detection)
git log v1.3.2..HEAD --pretty=format:'%H%n%s%n%b%n---COMMIT_END---' --no-merges
```

### Step 2: Parse and Classify

```python
import re
from dataclasses import dataclass
from typing import Optional

@dataclass
class ParsedCommit:
    hash: str
    type: str
    scope: Optional[str]
    description: str
    body: Optional[str]
    breaking: bool
    breaking_description: Optional[str]

COMMIT_PATTERN = re.compile(
    r'^(?P<type>feat|fix|perf|refactor|docs|test|build|ci|chore|security|deprecated|remove)'
    r'(?:\((?P<scope>[^)]+)\))?'
    r'(?P<breaking>!)?'
    r':\s*(?P<description>.+)$'
)

def parse_commit(hash: str, message: str) -> Optional[ParsedCommit]:
    lines = message.strip().split('\n')
    subject = lines[0]
    body = '\n'.join(lines[1:]).strip() if len(lines) > 1 else None

    match = COMMIT_PATTERN.match(subject)
    if not match:
        return None  # Non-conventional commit

    breaking = bool(match.group('breaking'))
    breaking_desc = None

    if body and 'BREAKING CHANGE:' in body:
        breaking = True
        bc_match = re.search(r'BREAKING CHANGE:\s*(.+)', body, re.DOTALL)
        if bc_match:
            breaking_desc = bc_match.group(1).strip()

    return ParsedCommit(
        hash=hash,
        type=match.group('type'),
        scope=match.group('scope'),
        description=match.group('description'),
        body=body,
        breaking=breaking,
        breaking_description=breaking_desc,
    )
```

### Step 3: Determine Version Bump

```python
def determine_bump(commits: list[ParsedCommit]) -> str:
    """Determine semver bump from parsed commits."""
    if any(c.breaking for c in commits):
        return 'major'
    if any(c.type == 'feat' for c in commits):
        return 'minor'
    if any(c.type in ('fix', 'perf', 'security', 'refactor') for c in commits):
        return 'patch'
    return 'none'

def bump_version(current: str, bump: str) -> str:
    """Apply bump to a semver string."""
    major, minor, patch = map(int, current.lstrip('v').split('.'))
    if bump == 'major':
        return f"{major + 1}.0.0"
    elif bump == 'minor':
        return f"{major}.{minor + 1}.0"
    elif bump == 'patch':
        return f"{major}.{minor}.{patch + 1}"
    return current
```

### Step 4: Render Changelog

```python
SECTION_MAP = {
    'feat': 'Added',
    'fix': 'Fixed',
    'perf': 'Performance',
    'security': 'Security',
    'deprecated': 'Deprecated',
    'remove': 'Removed',
    'refactor': 'Changed',
}

def render_changelog(version: str, date: str, commits: list[ParsedCommit], repo_url: str) -> str:
    sections: dict[str, list[str]] = {}

    # Breaking changes get their own section
    breaking = [c for c in commits if c.breaking]
    if breaking:
        sections['BREAKING CHANGES'] = []
        for c in breaking:
            desc = c.breaking_description or c.description
            scope = f"**{c.scope}**: " if c.scope else ""
            sections['BREAKING CHANGES'].append(f"- {scope}{desc}")

 

Related in Cloud & DevOps