Video Recap (automated narrated recap pipeline)
Turns a raw video into a finished recap by orchestrating understanding, story planning, cutting, AI voiceover and final assembly.
Image & VideoAdvanced★ 548⑂ 103AI score 9/10Last updated: Oct 3, 2026
What it does
- Takes an mp4/mov/mkv/webm file and conducts a five-skill chain: video understanding → story plan → cut → voiceover → assembly.
- Stages communicate only through JSON artifacts in
work_dir(clip_plan.json,narration.json,final_qc.json), so the run pauses for your creative approval and resumes with the exact same command. - Separate switches for picture (
--edit-mode full|cut|dub) and sound (--audio-mode narration|source-mix|adopted-packet-copy); invalid combinations fail fast at startup. - Extras: subtitle burn-in with measured placement, voice cloning, a grep-based material library, resource locking, a read-only local dashboard and a deterministic final QC report.
Who it's for
- Creators running movie/series/documentary recap channels.
- Content and marketing teams repurposing long footage into narrated short cuts.
- Command-line comfortable users who can install ffmpeg and manage API keys.
Example uses
- Feed one episode with
--edit-mode cut --target-duration 10mto get a 10-minute narrated highlight. - Pass
ep1.mp4 ep2.mp4for a multi-source recap where every clip carries asource_id. - Run
--edit-mode dubto translate an English talk into Chinese with the original speaker's cloned voice. - Re-package a locked master with
--audio-mode adopted-packet-copyso the approved AAC track is frozen untouched.
· · · 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-recap/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)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the 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-recap folder from the GitHub repo zenstory-ai/video-recap-skills into my ~/.claude/skills/zenstory-ai-video-recap/. 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.
- Install ffmpeg first:
brew install ffmpeg(macOS),sudo apt install ffmpeg(Linux) orchoco install ffmpeg(Windows). Prefer a build with libass so subtitles can be burned in. - Clone the repo:
git clone https://github.com/zenstory-ai/video-recap-skills.git - Copy all skills into Claude Code:
mkdir -p ~/.claude/skills && cp -r video-recap-skills/skills/* ~/.claude/skills/— keep the sibling video-* skills, the orchestrator needs them. - Export your API key:
export MIMO_API_KEY=your_key(add it to your shell profile to persist). - Verify offline config:
python3 ~/.claude/skills/video-recap/scripts/recap.py --doctor - Restart Claude Code and ask something like "make a narrated recap from this video".
- When the run pauses, write the requested JSON (clip plan or narration) and re-run the identical command to finish rendering.
View source on GitHub ↗License: MIT