generate-changelog

Generate changelog entries from git commits, plan files, or structured data. Use for version releases, creating CHANGELOG.md sections, or documenting changes between versions.

164 stars

Best use case

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

Generate changelog entries from git commits, plan files, or structured data. Use for version releases, creating CHANGELOG.md sections, or documenting changes between versions.

Teams using generate-changelog 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/generate-changelog/SKILL.md --create-dirs "https://raw.githubusercontent.com/maslennikov-ig/claude-code-orchestrator-kit/main/.claude/skills/generate-changelog/SKILL.md"

Manual Installation

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

How generate-changelog Compares

Feature / Agentgenerate-changelogStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Generate changelog entries from git commits, plan files, or structured data. Use for version releases, creating CHANGELOG.md sections, or documenting changes between versions.

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

# Generate Changelog

Automatically generate changelog entries following Keep a Changelog format.

## When to Use

- Version release workflows
- Creating CHANGELOG.md sections
- Documenting changes between versions
- Generating release notes
- Summarizing work completed

## Instructions

### Step 1: Gather Change Data

Accept change information from various sources.

**Expected Input**:
- `version`: String (e.g., "0.8.0")
- `date`: String (ISO-8601 or YYYY-MM-DD)
- `source`: String (git|plan-file|manual)
- `sourceData`: Object (git range, plan file path, or manual entries)

**Source Types**:
- **git**: Parse git log between two refs
- **plan-file**: Extract from plan file metadata
- **manual**: User-provided entries

### Step 2: Parse Changes

Extract and categorize changes.

**Categories** (Keep a Changelog standard):
- **Added**: New features
- **Changed**: Changes to existing functionality
- **Deprecated**: Soon-to-be removed features
- **Removed**: Removed features
- **Fixed**: Bug fixes
- **Security**: Security vulnerability fixes

**Git Commit Parsing**:
- Parse conventional commit format (feat:, fix:, etc.)
- Extract scope and description
- Map commit type to changelog category

### Step 3: Group and Deduplicate

Group changes by category and remove duplicates.

**Grouping Rules**:
- feat → Added
- fix → Fixed
- security → Security
- refactor, perf → Changed
- docs → Changed (if significant)
- chore → Omit (unless breaking change)

### Step 4: Format Changelog Section

Create formatted changelog section.

**Format**:
```markdown
## [Version] - Date

### Added
- New feature 1
- New feature 2

### Fixed
- Bug fix 1
- Bug fix 2

### Changed
- Change 1
```

### Step 5: Return Formatted Changelog

Return complete changelog section ready for insertion.

**Expected Output**:
```markdown
## [0.8.0] - 2025-10-17

### Added
- Dark mode toggle for user preferences
- OAuth2 authentication support

### Fixed
- Memory leak in connection pool
- CORS configuration error

### Changed
- Migrated to v2 authentication API
- Optimized query performance
```

## Error Handling

- **No Changes Found**: Return empty changelog with note
- **Invalid Git Range**: Return error with git command output
- **Invalid Plan File**: Return error describing issue
- **Unparseable Commits**: Include as "Changed" with raw message

## Examples

### Example 1: Generate from Git Range

**Input**:
```json
{
  "version": "0.8.0",
  "date": "2025-10-17",
  "source": "git",
  "sourceData": {
    "fromRef": "v0.7.0",
    "toRef": "HEAD"
  }
}
```

**Git Commits**:
```
feat(auth): add OAuth2 support
fix(api): resolve memory leak
docs: update API documentation
chore(deps): bump dependencies
```

**Output**:
```markdown
## [0.8.0] - 2025-10-17

### Added
- Add OAuth2 support (auth)

### Fixed
- Resolve memory leak (api)

### Changed
- Update API documentation
```

### Example 2: Generate from Plan File

**Input**:
```json
{
  "version": "0.8.0",
  "date": "2025-10-17",
  "source": "plan-file",
  "sourceData": {
    "planFile": ".version-update-plan.json"
  }
}
```

**Plan File Content**:
```json
{
  "changes": {
    "added": ["Dark mode toggle", "User profiles"],
    "fixed": ["Login redirect bug", "Dashboard crash"],
    "changed": ["Improved performance"]
  }
}
```

**Output**:
```markdown
## [0.8.0] - 2025-10-17

### Added
- Dark mode toggle
- User profiles

### Fixed
- Login redirect bug
- Dashboard crash

### Changed
- Improved performance
```

### Example 3: Manual Entries

**Input**:
```json
{
  "version": "0.8.0",
  "date": "2025-10-17",
  "source": "manual",
  "sourceData": {
    "added": ["New payment gateway integration"],
    "fixed": ["Cart calculation error"],
    "security": ["Fixed XSS vulnerability in search"]
  }
}
```

**Output**:
```markdown
## [0.8.0] - 2025-10-17

### Added
- New payment gateway integration

### Fixed
- Cart calculation error

### Security
- Fixed XSS vulnerability in search
```

### Example 4: Empty Changelog

**Input**:
```json
{
  "version": "0.8.0",
  "date": "2025-10-17",
  "source": "git",
  "sourceData": {
    "fromRef": "v0.7.0",
    "toRef": "v0.7.0"
  }
}
```

**Output**:
```markdown
## [0.8.0] - 2025-10-17

No changes in this release.
```

## Validation

- [ ] Parses conventional commits correctly
- [ ] Maps commit types to changelog categories
- [ ] Groups changes by category
- [ ] Formats according to Keep a Changelog
- [ ] Handles empty changelogs
- [ ] Deduplicates entries
- [ ] Includes scope in entries when present
- [ ] Handles manual entries

## Supporting Files

- `commit-mapping.json`: Conventional commit to changelog category mapping

Related Skills

generate-report-header

164
from maslennikov-ig/claude-code-orchestrator-kit

Create standardized report headers with metadata for all agent-generated reports. Use when generating bug reports, security audits, dependency reports, or any worker output requiring consistent formatting.

changelog-generator

164
from maslennikov-ig/claude-code-orchestrator-kit

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

Beads Issue Tracking Skill

164
from maslennikov-ig/claude-code-orchestrator-kit

> **Attribution**: [Beads](https://github.com/steveyegge/beads) by [Steve Yegge](https://github.com/steveyegge)

Workflow & ProductivityClaude

webapp-testing

164
from maslennikov-ig/claude-code-orchestrator-kit

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

validate-report-file

164
from maslennikov-ig/claude-code-orchestrator-kit

Validate that worker-generated reports have all required sections and proper formatting. Use in quality gates, for report completeness checking, or when debugging missing report sections.

validate-plan-file

164
from maslennikov-ig/claude-code-orchestrator-kit

Validate that orchestrator plan files conform to expected JSON schema. Use before workers read plan files or after orchestrators create them to ensure proper structure and required fields.

ux-researcher-designer

164
from maslennikov-ig/claude-code-orchestrator-kit

UX research and design toolkit for Senior UX Designer/Researcher including data-driven persona generation, journey mapping, usability testing frameworks, and research synthesis. Use for user research, persona creation, journey mapping, and design validation.

ui-design-system

164
from maslennikov-ig/claude-code-orchestrator-kit

UI design system toolkit for Senior UI Designer including design token generation, component documentation, responsive design calculations, and developer handoff tools. Use for creating design systems, maintaining visual consistency, and facilitating design-dev collaboration.

theme-factory

164
from maslennikov-ig/claude-code-orchestrator-kit

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

systematic-debugging

164
from maslennikov-ig/claude-code-orchestrator-kit

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

setup-knip

164
from maslennikov-ig/claude-code-orchestrator-kit

Install and configure Knip for dead code detection. Use before running dead-code-hunter or dependency-auditor to ensure Knip is available. Handles installation, configuration creation, and validation.

senior-prompt-engineer

164
from maslennikov-ig/claude-code-orchestrator-kit

World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.