Skills Agentes

Editor

Entiende, genera y edita metraje con Diffusion Studio vía `dapi`: analiza vídeo/audio/imágenes, genéralos con IA y compón vídeos. Para análisis, generación o edición de vídeo.

Estrellas
145

en todo el repo

Actividad
100

0–100, la ruta de este skill

Actualizado
el mes pasado

último commit aquí

Commits
62

últimos 90 días

Contexto
1.9k tok

58 tok en reposo

Paquete
26 archivos

62 KB

Instalar

Funciona con cualquier agente que lea SKILL.md

npx -y skills add diffusionstudio/skills --skill editor --agent claude-code

Se instala solo en este repositorio.

Qué hace

  • Edita y compone vídeo en Diffusion Studio vía `dapi`: analiza metraje, genera imagen/vídeo/voz y monta la composición en JSX.
  • Inspecciona el material con `dapi media probe`, waveform, filmstrip, `listen`, `transcribe` y `grab` antes de cortar.
  • Sigue un bucle de edición: brief en markdown, A-roll, B-roll y assets; el proyecto es una carpeta de JSX que se recompila al guardar.
  • Verifica con `dapi check` y `dapi capture`; no exporta a vídeo salvo que el usuario lo pida.

Úsalo cuando

  • Cualquier tarea de análisis de media, generación de media o edición de vídeo.
  • Cuando el usuario pide montar, cortar, subtitular o componer metraje con Diffusion Studio.

No lo uses cuando

    Qué lo activa

    Di cualquiera de estas frases y el agente debería cargar este skill.

    • “Edita el metraje de esta carpeta”
    • “Haz un promo de 20 segundos de este producto”
    • “Saca el mejor momento de 30 segundos y ponlo en vertical”
    • “Añade subtítulos y un gancho visual al inicio”

    SKILL.md

    En inglés

    The CLI is self-describing and ships its own API reference. Use dapi --help, dapi <group> --help, and dapi <group> <command> --help to enumerate every command, argument, and option, and treat live help as authoritative rather than working from memory.

    Footage analysis

    How to understand source material before editing it. Inspect only the modalities the decision turns on — speech, action, music, graphics, or atmosphere may lead, so there is no fixed priority. Sample the picture against what the audio tells you.

    • Always probe first. dapi media probe <id|path> reports the container and its tracks, telling you up front whether the file has a video track, an audio track, or both. Everything after branches on that.
    • Get the lay of the land. Render a dapi media waveform (audio) and a dapi media filmstrip (video) for a fast, cheap overview of where the loud and quiet stretches fall, and where the visual scene changes are. A filmstrip shows coarse structure and scene state, not crop, framing, readability, or an exact cut frame.
    • Listen to the audio. Run dapi media listen with a prompt tailored to the context (what you actually need to know), and explicitly ask the model to include timestamps in its answer. See media-listen.md for prompt patterns.
    • Transcribe speech. For speech, dapi media transcribe prints the full transcript with word-level start/end times directly — read any segment straight from it.
    • Sample the video against the audio. Use dapi media grab to pull frames. When the audio has already pointed you at specific moments, feed those timestamps straight in from the transcript or listen output, e.g. -t '00:32' '00:45' .... When you need a visual pass without such cues, reach for --auto: it scans the footage and keeps only the frames where the picture settles into a new visual state, dropping near-duplicates.

    The editing loop

    • Write the brief first. For anything nontrivial, capture the edit as a markdown file: it is the plan every save works toward and the thing to check the result against.
    • Lay down the A-roll. Assemble the primary footage as JSX and save. Get the spine of the edit right before anything else.
    • Layer the rest on top. Once the A-roll holds, add B-roll and secondary assets (sound effects, captions, overlays) in the same source.
    • Symlink media the project uses into its assets/ folder and name it by library path (assets/b-roll/drone.mp4 is "b-roll/drone.mp4"); local and remote paths work too but stay outside the library.
    • dapi context reports which folder the app actually has open, where the playhead sits, and where every generate.* declaration stands — poll it to wait for generations without blocking.

    The source is the document. A project is a folder of JSX; Use dapi open <dir> once, then write the files and save. Saving recompiles and re-renders the canvas.

    Compositing

    • Chrome, scaffolding, and ornament all draw from a visual budget whose default balance is 0; prefer not to use them. A cut, hold, or change of size can separate two ideas as clearly as a divider without adding visual clutter. An element earns its place by deepening the story, guiding attention, or expanding imagination, never by filling space.
    • Video is its own medium, with its own rules; it is not a website, poster, slide, or UI. It is watched, not read.
    • Don't darken, blur, or cover the picture to make something on top of it legible
    • Let visuals, sound, and voice carry context; let text punctuate rather than explain. Do not add copy, eyebrows, labels, underlines, or brand color highlights unless the brief or explicit video guidance calls for them; examples alone are not instructions.
    • Choose easing from the intended weight, energy, and continuity of the action.
    • When the brief, project, or user specifies branding, follow it. Only when none is specified, fall back to the Diffusion Studio brand — its design, voice, video, and library references, and the components and compositions bundled with them.

    Verification

    How to confirm a change actually produced what you intended. A clean save does not guarantee a correct-looking composition.

    • Run dapi check <id> first. It catches black frames, clips that never become visible, zero-duration or fully transparent nodes, and assets that failed to load or generate.
    • Use dapi capture <id> to see what the viewer actually gets.
    • Reconcile captured frames with the brief, and the brief with these guidelines.
    • Verify after every stage, not only at the end — build the composition incrementally so a problem is caught next to the change that caused it.
    • Scale verification to the change. A small or incremental tweak the user asked for needs no visual confirmation so the user gets the result back fast and can keep iterating.
    • Fix the largest viewer-facing problem before polishing details, and recheck related moments after structural changes, since pacing, continuity, emphasis, and meaning are relational.
    • Use screenshot or logs to debug issues.
    • DO NOT export/render the scene for visual confirmation — dapi capture is equivalent to a render but far more efficient. Rendering to a video should be a user-triggered action unless explicitly requested in the prompt.

    Best practices

    • Wrap clips in <sequence> tags wherever the parent tag supports it — A-roll, B-roll, and other clips belong in sequences so the timeline stays structured rather than a flat, messy pile. A sequence does not place its children: give every clip an explicit start.
    • Use the built-in tags for the media a composition is made of (audio, video, images, captions).
    • For anything 3D, use Three.js drawn into a <surface> tag.
    • For motion graphics, overlays and UI-heavy graphics, the <html> tag driven by a paused anime.js timeline
    • Before animating anything, read the easings reference and choose easings deliberately — default or linear easing is what makes motion read as a slideshow.
    • Add auto captions last, after everything else is assembled, so they transcribe the finished audio at its final placement.
    • Open the application in the background (dapi open -b) for tasks that don't require an editing UI.
    • Only render (export) the result when prompted.
    • Start with a fresh project.

    Docs

    Every project carries its own authoring reference, written by the app for the installed version, and its AGENTS.md points at it. Read it there and trust it over memory; it is app-owned, so never edit it.

    Examples

    Read worked example(s) that match your context.

    Video editing

    Prompts

    Reproducido de diffusionstudio/skills bajo licencia MIT. Leer esta página en markdown.

    Archivos

    26 archivos en el paquete. Solo se lee SKILL.md al activarse — las referencias se cargan si el skill decide que las necesita.

    Antes de instalar

    Requiere la CLI `dapi` (Diffusion Studio). Si no está, lee `references/installation.md`. `dapi media listen` consume créditos.

    Detalles

    Licencia
    MIT
    Recursos incluidos
    referencias
    Código fuente
    Ver SKILL.md

    Más de diffusionstudio/skills

    Este repo incluye 2 skills. Si instalas uno, normalmente ya tienes los demás. Ver el pack skills entero y su comando de instalación

    Ve y entiende metraje con Diffusion Studio vía `dapi`: responde preguntas, resume, localiza escenas, saca citas y describe qué ocurre y cuándo.

    Costo de contexto al activarse
    1.1k tok
    Tamaño del paquete
    3 archivos
    Última actualización
    hace 2 meses
    investigacion

    Skills relacionados

    Se usa cuando el usuario pide generar, crear o imaginar videos. Admite prompts estructurados e imagen de referencia opcional para guiar la generación.

    Costo de contexto al activarse
    1.3k tok
    Tamaño del paquete
    2 archivos
    Última actualización
    hace 3 meses
    video

    Genera vídeos con IA desde texto usando varias pasarelas — HeyGen, fal.ai, Kling y Gemini — con soporte de imagen a vídeo y comparación entre VEO, Kling, Sora, Runway, Seedance y MiniMax.

    Costo de contexto al activarse
    3k tok
    Tamaño del paquete
    1 archivo
    Última actualización
    hace 2 meses
    video

    Genera o edita imágenes y vídeos por la pasarela Atlas Cloud: Seedance 2.5/2.0, Gemini Omni Flash, MiniMax H3, Seedream 5.0, GPT Image 2 y Nano Banana 2 con una sola ATLASCLOUD_API_KEY.

    Costo de contexto al activarse
    1.2k tok
    Tamaño del paquete
    1 archivo
    Última actualización
    el mes pasado
    video