O que cut-as-code faz?
Habilidades de edição de vídeo agêntica de código aberto — corte, legendas, B-roll, shorts.
Habilidades de edição de vídeo agêntica de código aberto — corte, legendas, B-roll, shorts.
O projeto WhiteTowerAI/cut-as-code oferece habilidades agênticas de edição de vídeo de código aberto, permitindo que agentes de IA como Claude Code, Cursor ou Codex realizem tarefas de edição de vídeo de forma autônoma. Ele suporta operações como corte de vídeos, adição de legendas automáticas, inserção de B-roll e criação de shorts. A ferramenta é útil para desenvolvedores que desejam integrar edição de vídeo em fluxos de trabalho baseados em IA, simplificando a automação de tarefas repetitivas de pós-produção. Baseia-se em bibliotecas de código aberto e fornece uma interface programática para orquestrar o processo de edição.
npx skills add WhiteTowerAI/cut-as-codeHabilidades de edição de vídeo agêntica de código aberto — corte, legendas, B-roll, shorts.
This repo contains 9 individual skills — each has its own dedicated page.
>
Use when a talking-head, interview, documentary, or explanatory video needs deliberate transcript-timed visual cutaways from local media or Pexels.
>
Use when an understood video project needs selective transcript-timed titles, lower-thirds, statistics, metric spotlights, comparisons, lists, quotes, chapter cards, or calls to action authored as HyperFrames HTML graphics.
Use when footage needs color correction, white-balance or exposure repair, Log-to-Rec.709 conversion, named creative looks, skin-tone review, or a portable .cube LUT for a cut-as-code delivery.
>
Use when a completed cut-as-code delivery needs a strict side-by-side review against its original source, including cuts, varispeed, color grade, and graphics.
>
Use when a video project needs reusable media metadata, word-level transcription, objective speech analysis, or evidence-backed semantic understanding before optional editing skills run.
Extract frames or short clips from videos using ffmpeg.
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
Obra superpowers agent skills.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...
End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.