Skip to content
Get packs

Video Use

Lets your agent edit videos through conversation: transcribe, cut, grade, add overlays and subtitles.

Source Download skill
Repository
browser-use/video-use
Stars
30,378
Licence
MIT
Files
5 files

What it does

Once installed, the agent can take your raw video files, transcribe the speech word by word using the ElevenLabs Scribe API, and work out cuts from the transcript and silences. It asks you to confirm a plain-English plan before touching anything, then renders the edit with ffmpeg, adds color grading, optional animated overlays, and burned-in subtitles, and saves its notes and outputs into an edit folder next to your footage.

Great for

  • Creators who want to cut talking-head, interview, or tutorial footage by describing what they want in plain language
  • Marketers producing short social videos with subtitles and simple overlays from existing recordings
  • Developers comfortable with Python, ffmpeg, and API keys who want a scriptable video editing workflow

Skip it if

  • People who need a point-and-click editor or a fixed template library; the skill has no menus or presets by design
  • Sensitive footage you do not want uploaded to a third-party transcription service, since audio is sent to ElevenLabs for transcription
  • Users without ffmpeg, Python, and an ElevenLabs API key, since setup is required before it works

Try asking

  • “Cut out the filler words and long pauses from this interview recording and show me the plan first”
  • “Add burned-in subtitles to my tutorial video and render a 720p preview”
  • “Color grade these travel clips warm and add a lower-third title card at the start”
  • “Build a short montage from these three takes and suggest where the cuts should go”
Step-by-step guide: how to use Video UseInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 5 original files, the MIT licence and an attribution note.

    video-use.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip video-use.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip video-use.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent a clear goal and the video type (talking head, tutorial, montage) so it can propose a sensible plan before editing
  • Review the plan it describes and the preview.mp4 before asking for the final render
  • Keep your API key in the repo's .env file rather than pasting it into shared chats, and check that outputs land in your edit folder

What's inside

  • install.md
  • poster.html
  • pyproject.toml
  • README.md
  • SKILL.md

Redistributed unmodified from browser-use/video-use under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.