Video Narration Script (video-script)

Turns an already-analyzed video into a directing/editing plan plus a timestamped narration script, with automated review and validation.

Image & VideoAdvanced★ 482⑂ 93AI score 8/10Last updated: Aug 28, 2026

What it does

Reads a work_dir that already contains video-understanding artifacts (VLM/ASR) and runs the whole creative stage of a recap or commentary video.

Enforced role sequence: the agent acts as director → story editor → picture editor → sound/narration editor → first-time viewer
Structured deliverables: recap_story_plan.json (intent, POV, beats), visual_audio_board.json (in/out points, audio_owner, narration_job), optional style_card.json
Two edit modes: full mode writes against source timecode; cut mode writes clip_plan.json first, then narration against the edited output timeline
Checking pipeline: review.py for advisory semantic review (flagging hallucinations), validate.py for deterministic time/quiet-window checks and alignment
Writing discipline: narration only when a narration_job exists, no describing what's already on screen, and explicit hand-off of audio ownership to source dialogue or silence

Who it's for

Creators producing recap or explainer videos for film/TV content
Users already running the video analysis pipeline from the same repo
Editing teams wanting consistent, auditable narration quality

Examples

First pass (CREATE): ask for a narration script on an analyzed 40-minute episode → two viable structures compared, POV and beats locked, beat-by-beat visual/source-audio/narration split, timestamped draft written
10-minute cut: cut-mode phase 1 produces clip_plan.json with reasons formatted as beat_id | function | change | POV | in point | out point; after the edit exists, narration is rewritten on output timing
Revision round: feedback like "beat 3 sounds too stiff" updates only style_card.json while other layers stay frozen, then review.py/validate.py are rerun until clean

· · · 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-script/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.

↓ 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-script folder from the GitHub repo zenstory-ai/video-recap-skills into my ~/.claude/skills/video-script/.
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/video-script ~/.claude/skills/

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

Open a terminal.
Clone the repo: git clone https://github.com/zenstory-ai/video-recap-skills.git
Create the skills folder: mkdir -p ~/.claude/skills
Copy the skill: cp -r video-recap-skills/skills/video-script ~/.claude/skills/
Verify Python 3 is available with python3 --version (needed for review.py and validate.py).
Restart Claude Code and test a trigger phrase such as "write the narration script".
Important: this skill is not standalone. Run the repo's video analysis stage first so work_dir contains agent_narration_brief.md, vlm_analysis.json, and recap_run_manifest.json.

View source on GitHub ↗License: MIT