Skip to main content
ClaudeWave
Skill1.1k estrellas del repoactualizado today

release-prep

The release-prep skill automates documentation generation for MassGen releases by extracting commits and merged pull requests since the last version tag, then creating structured CHANGELOG entries following Keep a Changelog format and archiving previous announcement files. Use this skill after merging a release PR to main but before creating the git tag, running the command with the new version number to validate and prepare release documentation.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/massgen/MassGen /tmp/release-prep && cp -r /tmp/release-prep/massgen/skills/release-prep ~/.claude/skills/release-prep
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# Release Prep Skill

This skill automates release preparation for MassGen, generating CHANGELOG entries, announcement text, and validating documentation.

## When to Use

Run this skill when preparing a new release:
- After merging the release PR to main
- Before creating the git tag

## Usage

```
/release-prep v0.1.34
```

## What This Skill Does

### 1. Gather Changes

Read commits and PRs since the last tag:

```bash
# Get last tag
git describe --tags --abbrev=0

# Get commits since last tag
git log v0.1.33..HEAD --oneline

# Get merged PRs (if using GitHub)
gh pr list --base main --state merged --search "merged:>2024-01-01"
```

### 2. Archive Previous Announcement

If `docs/announcements/current-release.md` exists:

```bash
# Extract version from current-release.md
VERSION=$(grep -m1 "^# MassGen v" docs/announcements/current-release.md | sed 's/# MassGen v\([^ ]*\).*/\1/')

# Archive it
mv docs/announcements/current-release.md docs/announcements/archive/v${VERSION}.md
```

### 3. Generate CHANGELOG Entry

**Update the Recent Releases section** at the top of `CHANGELOG.md`:
- Add the new release summary at the top
- Keep only the **3 newest releases** in this section
- Remove older entries (they remain in the detailed changelog below)

Create a structured entry following Keep a Changelog format:

```markdown
## [0.1.34] - YYYY-MM-DD

### Added
- **Feature Name**: Description
  - Implementation details

### Changed
- **Modified Feature**: What changed

### Fixed
- **Bug #123**: Description of fix

### Documentations, Configurations and Resources
- **Feature Guide**: New `docs/source/user_guide/feature.rst` for feature usage
- **Design Document**: New `docs/dev_notes/feature_design.md` for implementation details
- **Updated Docs**: Updated `docs/source/reference/cli.rst` with new commands
- **Skills**: New `massgen/skills/skill-name/SKILL.md` for automation
```

**Documentation section rules:**
- Reference specific file paths (`.rst`, `.md`, `.yaml` files)
- Use "New" for newly added files, "Updated" for modified files
- Run `git diff <last-tag>..HEAD --name-only -- "*.md" "*.rst" "*.yaml"` to find changed docs

**Categorization rules:**
- `feat:` commits → Added
- `fix:` commits → Fixed
- `docs:` commits → Documentation
- `refactor:`, `perf:` commits → Changed
- Breaking changes → highlight with ⚠️

**Contributors:**
- Run `git shortlog -sn <last-tag>..HEAD` to find all contributors
- List contributors by commit count in the Technical Details section

### 4. Update Sphinx Documentation

Update `docs/source/index.rst` Recent Releases section:

```bash
# Update Recent Releases section (keep latest 3 releases)
# Add new release at top, remove oldest (v0.1.X-3)
```

**Format:**
```rst
Recent Releases
---------------

**v0.1.44 (January 28, 2026)** - Execute Mode for Independent Plan Selection

New Execute mode for cycling through Normal → Planning → Execute modes via ``Shift+Tab``. Users can independently browse and select from existing plans with a plan selector popover. Context paths preserved between planning and execution phases. Enhanced case studies page with setup guides and quick start instructions.

**v0.1.43 (January 26, 2026)** - Tool Call Batching & Interactive Case Studies

...

**v0.1.42 (January 23, 2026)** - TUI Visual Redesign

...
```

Keep only the 3 most recent releases in this section. Older releases remain in the full changelog.

### 5. Update Configs Documentation

Update `massgen/configs/README.md` Release History section:

```markdown
## Release History & Examples

### v0.1.44 - Latest
**New Features:** Execute Mode for Independent Plan Selection, Case Studies UX Enhancements

**Key Features:**
- **Execute Mode Cycling**: Navigate through Normal → Planning → Execute modes via `Shift+Tab`
- **Plan Selector Popover**: Browse and select from up to 10 recent plans with timestamps
- **Context Path Preservation**: Context paths automatically preserved between planning and execution
- **Enhanced Case Studies**: Setup guides and quick start instructions on case studies page

**Example Usage:**
```bash
# Use the TUI with plan mode cycling
massgen --config @examples/basic/multi/three_agents_default

# In the TUI:
# 1. Press Shift+Tab to enter Planning mode
# 2. Create a plan: "Create a Python web scraper for news articles"
# 3. Press Shift+Tab twice to enter Execute mode
# 4. Select your plan from the popover and press Enter to execute
```
```

### 6. Update README.md

#### 6.1 Latest Features Section

Update the "🆕 Latest Features" section:

```markdown
## 🆕 Latest Features (v0.1.44)

**🎉 Released: January 28, 2026**

**What's New in v0.1.44:**
- **🔄 Execute Mode** - Cycle through Normal → Planning → Execute modes via `Shift+Tab` to independently browse and execute existing plans
- **📋 Plan Selector** - Browse up to 10 recent plans with timestamps, view full task breakdowns, and execute with preserved context paths
- **📚 Enhanced Case Studies** - Interactive setup guides and quick start instructions on case studies page
- **⚡ TUI Performance** - Optimized timeline rendering with viewport-based scrolling for faster UI responsiveness
- **🔧 Plan Mode Fixes** - Fixed planning instruction injection bug in execute mode, improved tool tracking

**Try v0.1.44 Features:**
```bash
# Install or upgrade
pip install --upgrade massgen

# Experience Execute mode with plan cycling
uv run massgen --display textual

# In the TUI:
# 1. Press Shift+Tab to enter Planning mode
# 2. Create a plan: "Build a Python web scraper"
# 3. Press Shift+Tab twice to enter Execute mode
# 4. Select your plan and press Enter to execute
```
```

Also update the table of contents link from v0.1.43 → v0.1.44.

#### 6.2 Recent Achievements Section

Move the current "Recent Achievements" to "Previous Achievements" and add new release:

```markdown
### Recent Achievements (v0.1.44)

**🎉 Released: January 28, 2026**

#### Execute Mode for Independent Plan Selection
- **Mode Cycling**: Navigate through Nor
audio-generationSkill

Guide to audio generation and understanding in MassGen. Covers text-to-speech, music, sound effects, and audio understanding across ElevenLabs and OpenAI backends.

backend-integratorSkill

Complete guide for integrating a new LLM backend into MassGen. Use when adding a new provider (e.g., Codex, Mistral, DeepSeek) or when auditing an existing backend for missing integration points. Covers all ~15 files that need touching.

evolving-skill-creatorSkill

Guide for creating evolving skills - detailed workflow plans that capture what you'll do, what tools you'll create, and learnings from execution. Use this when starting a new task that could benefit from a reusable workflow.

file-searchSkill

This skill should be used when agents need to search codebases for text patterns or structural code patterns. Provides fast search using ripgrep for text and ast-grep for syntax-aware code search.

image-generationSkill

Guide to image generation and editing in MassGen. Use when creating images, editing existing images, iterating on image designs, or choosing between image backends (OpenAI, Google Gemini/Imagen, Grok, OpenRouter).

massgen-config-creatorSkill

Guide for creating properly structured YAML configuration files for MassGen. This skill should be used when agents need to create new configs for examples, case studies, testing, or demonstrating features.

massgen-develops-massgenSkill

Guide for using MassGen to develop and improve itself. This skill should be used when agents need to run MassGen experiments programmatically (using automation mode) OR analyze terminal UI/UX quality (using visual evaluation tools). These are mutually exclusive workflows for different improvement goals.

massgen-log-analyzerSkill

Run MassGen experiments and analyze logs using automation mode, logfire tracing, and SQL queries. Use this skill for performance analysis, debugging agent behavior, evaluating coordination patterns, and improving the logging structure, or whenever an ANALYSIS_REPORT.md is needed in a log directory.