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

Video Understanding Indexer

Turns a video file into a structured understanding index — scenes, transcript, per-scene visual observations, silence windows — plus a creative brief.

Image & VideoAdvanced★ 494⑂ 96AI score 7/10Last updated: Aug 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.
  • Produces timestamped dialogue via ASR (mimo-v2.5-asr) and marks quiet windows in silence_periods.json.
  • Fuses every signal into a single timeline_fusion.json, plus asr_writing_chunks.json and an agent_narration_brief.md that downstream stages read first.
  • Keeps facts separate from inference and preserves uncertainty instead of inventing dramatic conclusions.

Who it's for

  • Creators making recaps, summaries, or narrated video who need to understand footage before writing.
  • Teams indexing a video archive scene-by-scene for search and reuse.
  • Users comfortable with ffmpeg, JSON pipeline artifacts, and holding a MIMO API key.

Example uses

  1. Feed a variety-show clip with --context "show name/cast names" to get per-scene observations and ASR writing chunks for a narration script.
  2. Use --skip-asr on a dialogue-free video to index only the visual narrative.
  3. Re-run with --force and a different --scene-threshold to recompute an existing work directory.

· · · 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: brew install ffmpeg (macOS), sudo apt install ffmpeg (Ubuntu), or choco install ffmpeg (Windows).
  2. Confirm Python 3 is installed and python3 works in your shell.
  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 API key: export MIMO_API_KEY=your_key (add it to your shell profile to persist).
  6. Restart Claude Code and try a request like "analyze this video" to confirm the skill triggers.
  7. To run manually, from the skill directory: python3 scripts/understand.py <video> --work-dir <work_dir>.
View source on GitHub ↗License: MIT