watch-skill

oxbshw/watch-skill

★ 145 stars Python AI/LLM Updated 3d ago ✗ Risk

Give any AI agent the ability to watch video — and to watch its own work and fix it. MCP + CLI + REST; scene-aware frames, OCR, local-first transcription, persistent index, and THE LOOP.

View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "watch-skill": {
      "command": "uvx",
      "args": [
        "watch-skill"
      ]
    }
  }
}

Or install with pip: pip install watch-skill

README Excerpt

<div align="center"> **Give any AI agent the ability to actually watch video.** Watch Skill turns any video — a URL from 1800+ sites, a live HLS/DASH stream, a local file, or a recording of the agent's own output — into a persistent, searchable index of frames, on-screen text, and transcript. Agents ask

Topics

agent-toolsai-agentsclaudeclaude-codecomputer-visionffmpegmcpmultimodalocrvideo-understandingwhisperyt-dlp

watch-skill

Quick Install

README Excerpt

Topics

Related AI/LLM Servers