Skip to content
TakoAPI
Back to skills

video-understand

by sifr42

Coding Agents & IDEs
426Downloads reported by clawskills.sh
0Views
0 likesSign in to like this skill
—Not yet rated
Your rating

Brief

Analyze and understand video content using AI.

Description

What This Skill Does

Analyzes video content using AI, accepting local files, YouTube URLs, or HTTP video URLs as input. Supports Google Gemini and Moonshot AI (Kimi) as backends. Returns summaries, answers to specific questions, and optional timestamped breakdowns.

Handles YouTube and HTTP URLs natively through Gemini without downloading, caches local uploads by content hash to skip re-uploads, and wraps multiple AI providers in one CLI instead of requiring separate tools per source type.

When to Use It

  • Summarizing a recorded team meeting without watching it
  • Asking follow-up questions about a YouTube tutorial
  • Getting a timestamped breakdown of a product demo video
  • Identifying key moments in a dashcam or security clip
  • Extracting spoken content or descriptions from an HTTP-hosted video

Example Workflow

INPUT

User asks: Summarize the key moments in this YouTube video with timestamps

AGENT
  1. 1

    Run video-understand analyze "https://www.youtube.com/watch?v=VIDEO_ID" "What are the key moments?" --timestamps

  2. 2

    Gemini receives the YouTube URL natively without downloading

  3. 3

    AI returns a timestamped breakdown of notable moments

  4. 4

    Agent formats and returns the summary to the user

OUTPUT

A timestamped list of key moments from the video

Requirements

  • GEMINI_API_KEY environment variable (Google Gemini API key)
  • MOONSHOT_API_KEY environment variable (required only if using Kimi provider)
  • yt-dlp installed (required only when using Kimi provider with YouTube URLs)

Installation

clawhub install sifr42/video-understand

Run the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.

Links