Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Deploy 77 pre-built SKILL.md agents and skills to parallelize complex code implementation and debugging via councils, port features between React, Android, and iOS/Swift, generate AI media like videos, audio, and images, analyze code styles/testing patterns, and run market/brand research workflows directly in Claude Code sessions.
npx claudepluginhub michaelboeding/skills --plugin skillsParallel Builder Solver - Implements assigned piece of a decomposed plan. Used by parallel-builder skill. DO NOT invoke directly.
Parallel Builder Solver - Implements assigned piece of a decomposed plan. Used by parallel-builder skill. DO NOT invoke directly.
Parallel Builder Solver - Implements assigned piece of a decomposed plan. Used by parallel-builder skill. DO NOT invoke directly.
Parallel Builder Solver - Implements assigned piece of a decomposed plan. Used by parallel-builder skill. DO NOT invoke directly.
Parallel Builder Solver - Implements assigned piece of a decomposed plan. Used by parallel-builder skill. DO NOT invoke directly.
REQUIRED: After creating ANY .swift, .m, .mm, .c, .cpp, or .h file in a directory containing a .xcodeproj, you MUST run add_to_xcode.rb to register it with the project. Without this step, the file will NOT appear in Xcode and will NOT compile.
Use Android/Kotlin code as the source of truth and implement the equivalent feature in iOS/Swift. Understands the feature behavior, data structures, and logic from Android, then creates idiomatic iOS code that matches the target codebase's existing patterns. Use when porting features from Android to iOS or ensuring platform consistency.
Use this skill to turn screen recordings into polished app demo videos with AI voiceover and music. Triggers: "app demo", "demo video from recording", "screen recording demo", "narrate this recording", "add voiceover to screen recording", "make a demo from this recording", "polish this screen recording", "app walkthrough video", "product demo video", "turn this recording into a demo", "screen recording with voiceover", "app showcase video", "demo with narration" Orchestrates: screen analysis, voiceover script, device framing, TTS, background music, and final assembly. NOTE: This skill requires an existing screen recording as input. It does NOT generate screen recordings.
Use this skill to create single-voice audio content like audiobooks, voiceovers, narrations, jingles, and audio ads. Triggers: "create audiobook", "generate voiceover", "narration", "audio ad", "radio ad", "jingle", "brand audio", "sonic logo", "text to audio", "read this aloud", "audio guide", "meditation audio", "soundscape" Orchestrates: narration/TTS, background music, and audio assembly. NOTE: For conversations/dialogues, use podcast-producer instead.
Disable the auto permissions review hook for this session. Tool calls return to normal permission prompts. Other terminal sessions are not affected.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Create and validate production-grade agent skills with 100-point marketplace grading
Professional skill creation with TDD workflow. Features dual-mode (fast/full), behavioral validation, and automated quality gates for 9.0/10+ scores.
Ultimate Claude Code skill creator. Design, scaffold, build, review, evolve, and publish production-grade AI agent skills following the Agent Skills open standard and 3-layer architecture.
18 universal AI skills for Claude Code — skill creation, deep research, strategic planning, content processing, solution architecture, and orchestration workflows
🤖 AI Engineer — AI Engineer + LLM Systems Specialist
4つの専門エージェント(アーキテクト・リサーチャー・ライター・レビュアー)がチームで高品質なスキルを設計・作成する
Version 5.27.0 - Added walkthrough-script-agent: generate timed walkthrough video scripts for app features
Personal collection of agent skills using the open SKILL.md standard. Works with Claude Code and other AI assistants.
# Add the marketplace
/plugin marketplace add michaelboeding/skills
# Install the plugin
/plugin install skills@michaelboeding-skills
Copy the skills/ folder to your project or follow your tool's skill installation docs.
Many skills require Python packages. Run the install script:
# From the skills directory
./scripts/install.sh
Or install manually:
pip install -r requirements.txt
Requirements:
google-genai package)What gets installed:
| Package | Version | Used By |
|---|---|---|
google-genai | ≥1.0.0 | image-generation, video-generation, voice-generation, music-generation |
matplotlib | ≥3.7.0 | chart-generation |
numpy | ≥1.24.0 | chart-generation |
python-pptx | ≥0.6.21 | slide-generation |
Pillow | ≥10.0.0 | slide-generation, image processing |
rembg | ≥2.0.50 | background-remove, icon-generation |
Optional tools:
| Tool | Install | Used By |
|---|---|---|
ffmpeg | brew install ffmpeg | media-utils, audio/video processing |
Some skills require API keys to function. Copy the example environment file and add your keys:
# Copy to your config directory (recommended - keeps keys safe from git)
mkdir -p ~/.config/skills
cp env.example ~/.config/skills/.env
# Edit ~/.config/skills/.env with your keys
Then export the variables in your shell profile (~/.bashrc, ~/.zshrc, or ~/.bash_profile):
# Core APIs (used by multiple skills)
export OPENAI_API_KEY="sk-..." # DALL-E, Sora, TTS
export GOOGLE_API_KEY="..." # Imagen, Gemini (AI Studio)
export ELEVENLABS_API_KEY="..." # ElevenLabs TTS
# Music Generation
export SUNO_API_KEY="..." # Suno music
export UDIO_API_KEY="..." # Udio music
# Model Council (optional)
export ANTHROPIC_API_KEY="sk-ant-..." # Claude API
export XAI_API_KEY="..." # Grok API
Restart your terminal or run source ~/.bashrc (or equivalent) for changes to take effect.
Vertex AI is the default backend for all Google-powered skills with higher rate limits:
| Skill | AI Studio | Vertex AI |
|---|---|---|
| Video (Veo) | 10/day | 10/min |
| Voice (Gemini TTS) | Limited | Higher |
| Music (Lyria) | Limited | Higher |
| Image (Imagen) | Limited | Higher |
Setup Vertex AI (one-time):
# 1. Install Google Cloud SDK: https://cloud.google.com/sdk/docs/install
# 2. Login and set project
gcloud auth application-default login
gcloud config set project YOUR_PROJECT_ID
# 3. Enable Vertex AI API
gcloud services enable aiplatform.googleapis.com
# 4. Export project (add to .env or shell profile)
export GOOGLE_CLOUD_PROJECT="your-project-id"
export GOOGLE_CLOUD_LOCATION="us-central1" # or us-east4
The video generation scripts auto-detect and use Vertex AI when GOOGLE_CLOUD_PROJECT is set.
Where to get API keys:
| ✅ Do | ❌ Don't |
|---|---|
Store keys in ~/.config/skills/.env | Commit .env files to git |
Use gcloud auth for local dev | Hardcode keys in scripts |
| Use service accounts for CI/CD | Share API keys publicly |
| Rotate keys if exposed | Store keys in repo, even private |
For CI/CD / Production:
# Option 1: Service Account (recommended)
export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account.json"
# Option 2: Workload Identity (GKE/Cloud Run)
# Automatically authenticated, no keys needed
Everything is a skill (has a SKILL.md file), but there are two types: