{
  "version": "2",
  "generatedAt": "2026-11-03T22:49:39.280Z",
  "listing": {
    "slug": "browser-use--video-use",
    "name": "video-use",
    "tagline": "Agent skill that turns a folder of raw takes into a finished MP4 from a chat prompt.",
    "shortTagline": "Agent skill: raw takes to MP4",
    "description": "A Claude Code, Codex, or Hermes skill that reads footage through an ElevenLabs word-level transcript instead of frames, proposes a cut, renders it with ffmpeg, and self-checks the output at every cut boundary. Filler-word removal, color grades, burned subtitles, and animation overlays with HyperFrames, Remotion, or Manim are the built-in jobs.",
    "capabilities": [
      "adaptable",
      "operable"
    ],
    "vertical": "video-streaming",
    "alternativeTo": [
      "Descript",
      "CapCut"
    ],
    "shape": "skill",
    "formFactor": "skill",
    "executionModel": "hybrid",
    "provenance": "unknown",
    "codeStack": {
      "languages": [
        "Python"
      ],
      "frameworks": [
        "ffmpeg"
      ],
      "packageManager": "uv",
      "database": [],
      "hostingTarget": [
        "local"
      ]
    },
    "modelStack": {
      "providers": [
        "ElevenLabs",
        "any coding agent with shell access"
      ],
      "models": [
        "ElevenLabs Scribe"
      ],
      "requiredKeys": [
        "ELEVENLABS_API_KEY"
      ],
      "promptLocations": [
        "SKILL.md",
        "install.md"
      ],
      "tools": [
        "helpers/ editing scripts",
        "timeline_view"
      ]
    },
    "repos": [
      {
        "url": "https://github.com/browser-use/video-use",
        "owner": "browser-use",
        "name": "video-use",
        "license": "MIT",
        "stars": 23605,
        "lastCommit": "2026-08-30"
      }
    ],
    "interface": {
      "kind": "cli",
      "url": "https://github.com/browser-use/video-use/blob/main/SKILL.md",
      "official": true,
      "hosted": "local"
    },
    "operability": "native",
    "recommendedWrapper": null,
    "reach": [
      {
        "job": "Cut filler words and dead space between takes",
        "reachable": true,
        "evidence": "README 'What it does'; cuts come from the Scribe transcript and silence gaps, executed by helpers/ scripts"
      },
      {
        "job": "Auto color grade every segment",
        "reachable": true,
        "evidence": "README: warm cinematic, neutral punch, or any custom ffmpeg chain"
      },
      {
        "job": "Audio fades at every cut",
        "reachable": true,
        "evidence": "README: 30ms audio fades at every cut"
      },
      {
        "job": "Burn styled subtitles",
        "reachable": true,
        "evidence": "README: 2-word UPPERCASE chunks by default, fully customizable"
      },
      {
        "job": "Generate animation overlays",
        "reachable": true,
        "evidence": "README: with HyperFrames, Remotion, Manim, or PIL in parallel sub-agents"
      },
      {
        "job": "Self-evaluate the rendered output",
        "reachable": true,
        "evidence": "README: timeline_view run on rendered output at every cut boundary, max 3 fix loops"
      },
      {
        "job": "Persist session memory across sessions",
        "reachable": true,
        "evidence": "README: project.md next to the sources"
      },
      {
        "job": "Download online sources",
        "reachable": true,
        "evidence": "README manual install: yt-dlp optional for downloading online sources"
      }
    ],
    "editions": [
      {
        "name": "Free",
        "price": null,
        "open": true,
        "distributions": [
          {
            "kind": "source",
            "url": "https://github.com/browser-use/video-use"
          },
          {
            "kind": "installable",
            "url": "https://github.com/browser-use/video-use#manual-install",
            "command": "git clone https://github.com/browser-use/video-use ~/Developer/video-use && ln -sfn ~/Developer/video-use ~/.claude/skills/video-use"
          }
        ]
      },
      {
        "name": "Browser Use Cloud",
        "price": null,
        "open": false,
        "distributions": [
          {
            "kind": "hosted",
            "url": "https://cloud.browser-use.com/v4"
          }
        ]
      }
    ],
    "skills": {
      "kind": "pure",
      "paths": [
        "SKILL.md",
        "skills/manim-video/SKILL.md"
      ],
      "install": null,
      "note": "Repo is a skill: root SKILL.md plus a manim-video sub-skill; helpers/ holds Python helper scripts the skill calls, not a CLI or app."
    },
    "customization": {
      "summary": "Set ELEVENLABS_API_KEY in .env, then change editing behavior by editing SKILL.md (the 12 production rules and default subtitle style) or the ffmpeg chains in helpers/. No code change is needed for a different look; the agent reads the prompt files each session.",
      "envVars": [
        "ELEVENLABS_API_KEY"
      ],
      "configFiles": [
        ".env",
        "pyproject.toml"
      ],
      "promptFiles": [
        "SKILL.md",
        "install.md",
        "helpers/"
      ],
      "effort": "config-only",
      "editCount": 6
    },
    "useWhen": [
      "I have a folder of talking-head takes and want a clean cut with subtitles without opening an editor",
      "I want my coding agent to edit tutorials and launch videos the same way it edits code"
    ],
    "accounts": [
      "ElevenLabs"
    ],
    "active": true,
    "lastActivity": "2026-08-30",
    "gotchas": [
      "ElevenLabs Scribe is the only transcription path; no key, no cuts",
      "ffmpeg must be on PATH; yt-dlp only for online sources",
      "The agent proposes a strategy and waits for approval before cutting, so unattended runs need an agent configured to auto-approve"
    ],
    "fit": {
      "adaptable": 3,
      "operable": 3
    },
    "evidence": {
      "formFactor": "README: symlinked into ~/.claude/skills or ~/.codex/skills; SKILL.md marker in shortlist",
      "executionModel": "README pipeline: Transcribe -> Pack -> LLM Reasons -> EDL -> Render -> Self-Eval; fixed stages, model decides cuts",
      "operability": "README: setup is a prompt pasted into Claude Code, Codex, Hermes, or Openclaw; no GUI in the tree; the pipeline stage LLM Reasons has no non-model substitute",
      "effort": ".env.example contains ELEVENLABS_API_KEY only; SKILL.md holds the editing rules",
      "editions": "MIT LICENSE; README links Browser Use Cloud with no price shown",
      "active": "GitHub pushedAt 2026-08-30"
    },
    "confidence": {
      "formFactor": 0.95,
      "executionModel": 0.85,
      "operability": 0.95,
      "effort": 0.85,
      "reach": 0.85,
      "editions": 0.7
    },
    "openQuestions": [
      "Browser Use Cloud pricing for running video-use hosted was not found on the README; check cloud.browser-use.com",
      "Provenance: browser-use is an AI-agent company; no statement on whether the skill itself was vibe-coded"
    ],
    "sources": [
      {
        "url": "https://github.com/browser-use/video-use",
        "foundBy": "sourcing:video-streaming:community"
      }
    ],
    "research": {
      "stage": "verified",
      "verdict": "approve",
      "reason": "Native holds: the repo has no GUI, the README install path is a prompt pasted into Claude Code, Codex, Hermes, or Openclaw, and the core loop needs an LLM to read the packed transcript and decide cuts. SKILL.md, install.md, helpers/ and .env.example (ELEVENLABS_API_KEY only) all exist at the stated paths; the 12 hard rules and default subtitle style live in SKILL.md, so editing it changes behavior without a code change.",
      "disputed": []
    },
    "url": "apps/browser-use--video-use.html",
    "coverage": "complete",
    "paid": false,
    "source": "research/verified/browser-use--video-use.json"
  }
}