Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Video Understanding Index

Turns a video into a structured understanding index — scenes, ASR transcript, per-scene VLM observations, silence windows, a fused timeline and a writing brief.

Image & VideoIntermediate★ 545⑂ 103AI score 7/10Last updated: Sep 28, 2026

What it does

  • Detects scene cut points into scenes.json and filters out junk segments.
  • Extracts representative frames and runs a VLM (mimo-v2.5) for per-scene descriptions, deeper analysis and frame_facts.
  • Transcribes dialogue with ASR (mimo-v2.5-asr) plus an evidence sidecar documenting timing precision and text corrections.
  • Detects silence windows, fuses everything into one timeline_fusion.json, and writes agent_narration_brief.md for the agent to read first.
  • Acts as an observer/script supervisor: facts are kept separate from inference, and uncertainty is preserved instead of inventing drama.

Who it's for

  • Creators automating video recap, summary or narration workflows.
  • Editors who need a scene-level index of a large video archive.
  • Developers building a video-understanding pipeline who are comfortable with ffmpeg and Python CLIs.

Examples

  1. Feed an episode with --context "show name/character names" to get per-scene analysis that uses the right character names.
  2. For a mostly silent vlog, pass --skip-asr and build the timeline from visual observations plus silence windows only.
  3. After changing settings, add --force to bypass cached artifacts and recompute every stage.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/zenstory-ai/video-recap-skills/HEAD/skills/video-understanding/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/video-understanding folder from the GitHub repo zenstory-ai/video-recap-skills into my ~/.claude/skills/video-understanding/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/zenstory-ai/video-recap-skills.git && mkdir -p ~/.claude/skills && cp -r video-recap-skills/skills/* ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Install ffmpeg: macOS brew install ffmpeg, Ubuntu sudo apt install ffmpeg, Windows choco install ffmpeg.
  2. Confirm Python 3 is available: python3 --version.
  3. Clone the repo: git clone https://github.com/zenstory-ai/video-recap-skills.git
  4. Copy the skills in: mkdir -p ~/.claude/skills && cp -r video-recap-skills/skills/* ~/.claude/skills/
  5. Export your MiMo API key: export MIMO_API_KEY=your_key (add it to ~/.zshrc or ~/.bashrc to persist).
  6. Restart Claude Code and ask it to "analyze this video", or run the script directly: python3 ~/.claude/skills/video-understanding/scripts/understand.py video.mp4 --work-dir ./work.
View source on GitHub ↗License: MIT