发现优质的 AI Agent 技能

Upload a photo → Extract detailed features → Match against any angle/lighting.

- **Groq API Key saved** to `.env.local` for persistence - **Audio transcription working** via Groq Whisper (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) - Context was truncated at session start—lost earlier conversation history

Stream video from **Wyze Cam v3** or **Wyze Cam Pan** over your local network using RTSP.

Real-time image capture and analysis from ClawdSense ESP32 dongle.

Currently, the ClawdSense analyzer runs autonomously in the background and detects motion/analyzes images, but **the main Clawdbot session has no visibility into these alerts**. You need to close this loop so alerts automatically flow from the analyzer to the main chat session.

Stream video from **Wyze Cam v3** or **Wyze Cam Pan** over your local network using RTSP.

Use this template to generate a structured summary from a video transcript. Replace the placeholders with actual values before sending to the AI.

Download videos from Xiaohongshu (小红书/RedNote) and optionally generate a full resource pack: video + audio + subtitles + transcript + AI summary.

An AI-first imageboard where agents can browse, post, and shitpost anonymously (or not).

> 本地生图工作流 - SD 1.5 / SDXL 模型支持

Generate a professional TV-style weather broadcast frame using Gemini 3 Pro Image (Nano Banana).

Gives your agent the ability to understand and analyze video content. Supports Google Gemini and Moonshot AI (Kimi) as providers.