gemini-video-understanding

kienhaminh/speed-reader

Analyze videos using Google's Gemini API - describe content, answer questions, transcribe audio with visual descriptions, reference timestamps, clip videos, and process YouTube URLs. Supports 9 video formats, multiple models (Gemini 2.5/2.0), and context windows up to 2M tokens (6 hours of video).

0 stars

0 forks

1 views

View on GitHub Add to Favorites

Installation

Option 1: Use slash command in Claude Code

/install-skill https://github.com/kienhaminh/speed-reader/tree/master/.claude/skills/gemini-video-understanding

Option 2: Clone to skills directory

# Global (all projects)

git clone https://github.com/kienhaminh/speed-reader/tree/master/.claude/skills/gemini-video-understanding ~/.claude/skills/speed-reader

# Project-specific

git clone https://github.com/kienhaminh/speed-reader/tree/master/.claude/skills/gemini-video-understanding .claude/skills/speed-reader

Add MCP server to .cursor/mcp.json:

{
  "mcpServers": {
    "skillz": {
      "command": "npx",
      "args": ["-y", "skillz-mcp", "https://github.com/kienhaminh/speed-reader/tree/master/.claude/skills/gemini-video-understanding"]
    }
  }
}

Restart Cursor after adding the configuration.

Option 1: Use Gemini CLI command

gemini extensions install https://github.com/kienhaminh/speed-reader/tree/master/.claude/skills/gemini-video-understanding

Option 2: Clone to extensions directory

git clone https://github.com/kienhaminh/speed-reader/tree/master/.claude/skills/gemini-video-understanding ~/.gemini/extensions/speed-reader

Related Skills

skill-writer

Tensors and Dynamic neural networks in Python with strong GPU acceleration

docstring

Tensors and Dynamic neural networks in Python with strong GPU acceleration

at-dispatch-v2

Tensors and Dynamic neural networks in Python with strong GPU acceleration

add-uint-support

Tensors and Dynamic neural networks in Python with strong GPU acceleration