Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
claude-video-vision
Give Claude the ability to watch and understand videos — Claude Code plugin with frame extraction and multimodal audio analysis
698stars
82forks
TypeScript
claude-codeclaude-code-pluginffmpeggeminimcpmcp-servermultimodalvideo-analysiswhisper
Quality signals
ActiveNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
A Claude Code plugin that lets Claude watch and analyze videos by extracting frames and processing audio with timestamps for direct multimodal understanding.
Use this when
- Debugging a tutorial video to find specific code snippets
- Summarizing a conference talk or lecture from a YouTube URL
- Reviewing UI changes in a screen recording for accessibility issues
- Extracting key moments from a long demo video with timestamps
- Analyzing a bug report video for on-screen error messages
Don't use when
- Processing silent videos with no audio track
- Analyzing videos longer than 1 hour with local Whisper backend on low-RAM machines
- Extracting text from low-resolution or heavily compressed videos
Capabilities
- Extracts video frames via ffmpeg at adjustable FPS and resolution
- Processes audio with Gemini API, OpenAI Whisper API, or local Whisper models
- Supports direct YouTube URL analysis with yt-dlp integration
- Preserves source metadata and captions for context
- Auto-downloads Whisper models on first use
- Provides interactive setup wizard for backend configuration
InstallMCP + SKILLInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest jordanrendric/claude-video-visionAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor or Cline.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/claude-video-vision curl -fsSL https://raw.githubusercontent.com/jordanrendric/claude-video-vision/main/SKILL.md -o ~/.claude/skills/claude-video-vision/SKILL.md
Readme
Loading README…