# MOP Skills 🐙

This repository contains a collection of specialized **Claude Skills**. These skills extend Claude's capabilities with domain-specific knowledge, workflows, and automated reporting.

## Repository Structure

```
.
├── AGENTS.md           # This file (purpose and overview)
├── skills/             # Dedicated directory for individual skills
│   ├── nerd-report/    # Personal report generator for Moritz Graf
│   ├── rvv-regensburg/ # Real-time public transport for Regensburg
│   └── skill-creator/  # Toolkit for creating and validating new skills
```

## Available Skills

### [nerd-report](skills/nerd-report/SKILL.md)
A professional "Octobot Journalist" that generates daily, weekly, and monthly reports for Moritz Graf.
- **Topics:** IT News, GCP, AI (Anthropic/OpenAI), Hacker News, Regensburg Local News.
- **Special Features:** Monday catch-up, Drill-down ("Tell me more"), Gardening (Hochbeet), Supermarket Shopping Guide.

### [memobird](skills/memobird/SKILL.md)
Direct printing to the Memobird thermal printer. Allows sending text, images, and notes to the device on the local network.
- **Features:** Text styling (big, bold, underline), automated 1-bit image conversion, separator lines.
- **Target:** Default targets the static IP `192.168.10.165`.

### [rvv-regensburg](skills/rvv-regensburg/SKILL.md)
Real-time public transport information for Regensburg (RVV). Provides departures, stop finding, and journey planning via direct API access.
- **Features:** Real-time departures with delay info, connection search, Stop ID resolver.
- **Tools:** Includes `rvv_query.py` for direct EFA API interaction.

### [text-to-audio](skills/text-to-audio/SKILL.md)
Audio dossier and podcast producer. Converts arbitrary research, summaries, notes, or articles into audio dossiers with duration target, importance compression, and solo or NotebookLM-style dialogue.
- **Features:** Target duration pacing (~130 words/min), importance filtering, solo monologue or multi-speaker dialogue.
- **Voices:** Primary Google Gemini 3.1 Flash TTS with automatic MiniMax Speech 02 HD fallback. German voices (`Puck` host/solo, `Aoede` co-host, `Charon` deep), English voices (`Zephyr` host/solo, `Aoede` co-host).
- **Tools:** Includes `scripts/text_to_audio.py` for parallel chunk synthesis, auto-fallback, and MP3 generation.

### [jelly-media](skills/jelly-media/SKILL.md)
Seamless Jellyfin and Jellyseerr integration. Enables natural-language discovery, stream & download URLs, living room playback dispatch, continue watching, and media requests.
- **Features:** Smart search cross-referenced with library availability, discover with genre & rating filters, direct stream & download links, Jellyfin active sessions & remote play, Jellyseerr requests.
- **Tools:** Standalone MCP server and CLI at `scripts/jelly_media.py`.

### [skill-creator](skills/skill-creator/SKILL.md)
Guidelines and scripts to help developers build high-quality, token-efficient Claude skills.

## How to use
Add individual skill directories to your Claude context. Each skill is self-contained within its directory and driven by its `SKILL.md` file.

## Creating New Skills
Use the templates and scripts in `skills/skill-creator` to bootstrap new skills:
```bash
python3 skills/skill-creator/scripts/init_skill.py <name> --path skills/
```