Skill

video-use

browser-use/video-use

A skill that lets a coding agent edit raw footage by conversation: it cuts from a word-level transcript, grades color, adds overlay animations and subtitles, then checks its own render.

View on GitHub
01Author
Browser Use
03Stars
27,870 · as of Oct 3, 2026
04Last updated
Oct 2, 2026
05License
MIT
06Works with
Claude Code · Codex · OpenClaw · Any agent
07Models
ElevenLabs Scribe · FFmpeg · HyperFrames · Remotion · Manim
08Content language
English
09Domains
Filmmaking · AI video
10Stages
Editing · Audio
SC 01Overview

What it does

You point the agent at a folder of raw takes; the skill has ElevenLabs Scribe transcribe each source at word level and condenses the result into a phrase-level text file, so the model reads the footage as text and pulls up filmstrip-and-waveform images only at tricky cut points. Once you approve a plain-English cut plan, it writes an edit decision list, renders each segment with an optional color grade and short audio fades, joins them, and adds overlay animations and burned-in subtitles last; sub-agents build the animations in parallel with HyperFrames, Remotion, Manim or PIL. Before showing a preview it inspects every cut boundary and the audio levels, then logs the session in project.md; its notes on music and sound effects cover ducking under speech and loudness normalization. Cuts follow speech and silence, so it fits talking heads, tutorials, interviews and montages better than scripted scenes, and it needs ffmpeg, Python dependencies and an ElevenLabs API key.

SC 02Install

How to install it

  • 01From the README

    The install command quoted from the repository README.

    git clone https://github.com/browser-use/video-use ~/Developer/video-use ln -sfn ~/Developer/video-use ~/.claude/skills/video-use
  • 02skills CLI, for Claude Code, Codex and others

    The open skills CLI from Vercel Labs installs a skill from a GitHub repo into the folder each agent expects. It asks which skills and which agents you want, and it installs for the current project unless you add the -g flag, which installs for your user account. Add --list to see what a repo contains before you install anything.

    npx skills add browser-use/video-use
  • 03Claude Code, skills folder

    Copy the skill's folder, the one that holds SKILL.md, into ~/.claude/skills/ to use it in every project on your machine, or into .claude/skills/ in a repository to use it there and share it by committing it. Claude Code picks up changes to these folders during a session. If the folder did not exist when the session started, run /reload-skills.

  • 04Claude Code, plugin marketplace

    Some repos publish a plugin marketplace, a .claude-plugin/marketplace.json file. Add it in Claude Code, then install a plugin from it with /plugin install plugin-name@marketplace-name. Plugins can bundle hooks and MCP servers along with skills, so read the details panel before you confirm.

    /plugin marketplace add browser-use/video-use
  • 05Codex, skills folder or $skill-installer

    Codex reads skills from .agents/skills in your working folder and its parent folders up to the repository root, and from $HOME/.agents/skills for every repository. Copy the skill's folder into one of them, or run $skill-installer inside Codex and ask it to install from the repo. Codex detects new skills automatically and needs a restart only if one does not appear.

The first command is quoted from the author's README. The others are the standard ways to install a skill from a GitHub repository. They are templates and may not apply here, for example if the repo has no plugin marketplace, so follow the README first.

SC 03Guide

How to get the most from it

Good for

  • Cutting talking-head, tutorial, interview or travel footage: filler words, false starts and dead air are removed at word boundaries.
  • Combining several takes of the same pitch into one edit by picking the best take for each beat.
  • Short promos that need burned-in captions plus a few animated cards or diagrams over the footage.
  • Revising an edit in plain English: you give notes and it re-renders without transcribing again.

Watch out for

  • Transcription runs on ElevenLabs Scribe and needs an ElevenLabs API key, so check its pricing for your volume. You also need ffmpeg and Python dependencies, plus Node.js if you want HyperFrames or Remotion overlays.
  • It edits footage you already have and builds overlay graphics; it does not generate video clips from prompts. Cuts follow speech and silence and there is no screenwriting or shot-continuity workflow, so scripted scenes are a weaker fit than talking heads, tutorials or montages.
  • The agent cannot listen to audio. It checks sound by measuring loudness and reading waveforms and frames, so review the preview yourself before publishing.

Typical workflow

01Step
Install: clone the repo, symlink it into your agent's skills folder, run uv sync, install ffmpeg and put your ElevenLabs key in .env.
02Step
Open the agent in the folder with your raw footage and state the goal, for example "edit these into a launch video".
03Step
The agent transcribes every source, reads the packed transcript, and asks about length, aspect ratio, pacing, color, subtitles and animations.
04Step
Approve the plain-English strategy it proposes: which takes, how to cut, which overlays, the color direction and an estimated length.
05Step
It writes the edit decision list, renders a 720p preview, and self-checks every cut boundary and the audio levels, fixing problems over up to three passes.
06Step
Give notes in plain English; it re-renders without re-transcribing, writes edit/final.mp4 once you confirm, and logs the session in project.md.
SC 04Fit

Where it fits in a film pipeline

The production stages this skill covers, and where Pencil0 picks up.

SC 05Related

Related skills

  • Pack

    OpenMontage

    calesthio/OpenMontage

    An open-source repo in which a coding agent directs video production through staged pipelines, with a large set of skills on video-model APIs, music, speech, editing and composition.

    • Pipeline
    • Generation
    • Editing
    62.4kGitHub starsUpdated Sep 2026
  • OfficialPack

    HyperFrames Skills

    heygen-com/hyperframes

    HeyGen's 21 skills for its open-source HTML-to-video framework: an agent plans, codes and renders explainers, launch videos, captions and music-synced clips as deterministic MP4s.

    • Editing
    • Pipeline
    • Audio
    55.8kGitHub starsUpdated Oct 2026
  • OfficialPack

    AiToEarn video agent skills

    yikart/AiToEarn

    Video-focused SKILL.md files from the AiToEarn content agent, led by a short-drama recap skill that submits clips for AI narration and voice-over; they rely on the platform's own tool calls.

    • Editing
    • Audio
    • Generation
    26.2kGitHub starsUpdated Sep 2026
  • OfficialPack

    Remotion Agent Skills

    remotion-dev/skills

    Remotion's own skill set for coding agents that build videos as React code: project setup, markup rules, captions, live preview and rendering to video or stills.

    • Editing
    4.8kGitHub starsUpdated Oct 2026
  • JianYing Editor Skill

    luoluoluo22/jianying-editor-skill

    Lets a coding agent script the desktop JianYing Pro app (CapCut's China edition): import media, add subtitles, TTS voiceover, music, effects and keyframes into an editable draft.

    • Editing
    • Audio
    3.7kGitHub starsUpdated Sep 2026
  • OfficialPack

    FireRed-OpenStoryline

    FireRedTeam/FireRed-OpenStoryline

    A conversational video-editing agent whose editing workflows ship as skills, plus two skills that let Claude Code or OpenClaw install it and run an editing session.

    • Editing
    • Audio
    3.5kGitHub starsUpdated Jul 2026

This is a third-party skill. It is not maintained or audited by Pencil0, and skills can run scripts on your machine, so read the SKILL.md and any scripts before installing. Stars, license and dates are a GitHub snapshot and may be out of date.