Browse skills

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

AI desktop agent — control any app on Windows/macOS from your OpenClaw agent. Send natural language tasks and it handles opening apps, clicking buttons, typing text, and navigating browsers.

Semantic search sidecar for Karakeep bookmarks. Find bookmarks by meaning, not just keywords. Uses vector embeddings for intent-aware retrieval.

Local speech-to-text using faster-whisper — 4-6x faster than OpenAI Whisper with identical accuracy. GPU acceleration, SRT/VTT/TTML subtitles, speaker diarization, and chapter detection.

Async deep research via Gemini Interactions API. RAG-ground queries on local files, preview costs with --dry-run, get structured JSON output. Universal skill for 30+ AI agents.

Cost-optimizing model router for OpenClaw. Automatically routes each request to the cheapest capable Claude model (Haiku/Sonnet/Opus) using weighted scoring. Use when setting up smart model routing, reducing API costs, or configuring multi-tier LLM routing. Supports Anthropic models directly and OpenAI/Google models via OpenRouter.