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

video-assemble (Final Video Assembly)

Final-stage assembly skill that lays narration audio over the source video, ducks the original sound, generates and burns subtitles, and normalizes loudness into a finished recap.

Image & VideoAdvanced★ 450⑂ 78AI score 8/10Last updated: Jul 26, 2026

What it does

  • Places each narration audio segment (from tts_meta.json) at its exact spot on the video timeline.
  • Ducks the original audio inside narration windows with fixed / sidechain / zone modes and configurable fade.
  • Produces subtitles.srt, plus subtitles.ass burned in by default (--no-burn-subtitles to skip).
  • Normalizes final loudness to a target LUFS and emits timeline.json, assembly_manifest.json, and an assembly_qc.json release gate.
  • Optionally exports an editable Jianying/CapCut-CN draft project.

Who it's for

  • Creators producing movie/series recap or commentary videos through an automated pipeline.
  • Editors tired of hand-mixing TTS narration against original dialogue.
  • Developers orchestrating ffmpeg-based rendering from Claude Code.

Examples

  1. python3 scripts/assemble.py source.mp4 --work-dir work/ — one command for mixing, ducking, subtitle burn-in, and loudness normalization.
  2. Source has hardcoded subtitles: pass --subtitle-y-top/--subtitle-y-bot to mask that band and place the recap subtitles on the same baseline.
  3. --export-jianying --source-video orig.mp4 to hand off an editable draft for a human final pass.

· · · 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/worldwonderer/video-recap-skills/HEAD/skills/video-assemble/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-assemble folder from the GitHub repo worldwonderer/video-recap-skills into my ~/.claude/skills/video-assemble/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/worldwonderer/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. Prerequisites: Python 3 and an ffmpeg build with libass/subtitles support (check with ffmpeg -filters | grep subtitles).
  2. Clone the repo: git clone https://github.com/worldwonderer/video-recap-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the whole pipeline: cp -r video-recap-skills/skills/* ~/.claude/skills/ — this skill depends on the upstream script/TTS skills and won't work alone.
  5. Restart Claude Code, then ask it to assemble a recap video; the skill is invoked by the orchestrating pipeline.
  6. At run time make sure the source video and work_dir/tts_meta.json exist; the finished file appears as recap_<stem>.mp4.
View source on GitHub ↗License: MIT