What it does
Adds professional video and audio intelligence to the agent. It enables the agent to ingest media from local files or URLs, create semantic and visual indexes for precise searching, and perform complex timeline edits programmatically.
When to use it
- When you need to search for specific moments in a video using text or visual queries.
- For automating the creation of clips, adding subtitles, or overlaying branding/audio on videos.
- When recording and analyzing desktop sessions (screen + audio) to produce summaries or alerts.
- When transcoding video for specific platform requirements (e.g., vertical for TikTok).
What's included
- Scripts: Includes
ws_listener.py for desktop capture event monitoring.
- References: Comprehensive API documentation covering search, editing, and streaming.
- Instructions: Detailed guides on using the VideoDB SDK, managing API keys, and implementing error handling for indexing and searching.
Compatible agents
Designed for agents capable of running Python (e.g., Claude Code, Codex, Gemini CLI) with access to a local environment to install the videodb SDK.
Not yet audited
This skill has not been reviewed by our automated audit pipeline yet.