Skills de Medios

Run any model on RunComfy from the command line. The `runcomfy` CLI is one binary, one auth, hundreds of model endpoints — image generation, image edit, video generation, image-to-video, lip-sync, face swap, video edit, inpainting, outpainting, extend, ControlNet, relight, upscale, LoRA training and more. Submit a request, poll for status, download the output. This skill teaches the agent how to install, authenticate, discover model schemas, invoke models, stream / poll / no-wait, script in...

We need to translate the given text from English to Spanish. The text describes a CLI tool called runcomfy-cli. The instruction says to preserve the name "runcomfy-cli" but only if it appears in the source text. The source text mentions "runcomfy" and "runcomfy CLI" but not "runcomfy-cli" exactly. However, the directory item type is "agent skill" and the name to preserve is "runcomfy-cli". The instruction says "Do not include the name unless it appears in the source text." The source text has "runcomfy" and "runcomfy CLI" but not "runcomfy-cli". So we should not add it. But careful: The instruction says "Name to preserve: runcomfy-cli" and then "Translate only the text inside <text>. Do not include the name unless it appears in the source text." So we only translate the text inside <text>. The text inside <text> includes "runcomfy" and "runcomfy CLI". We

Run any model on RunComfy from the command line. The `runcomfy` CLI is one binary, one auth, hundreds of model endpoints — image generation, image edit, video generation, image-to-video, lip-sync, face swap, video edit, inpainting, outpainting, extend, ControlNet, relight, upscale, LoRA training and more. Submit a request, poll for status, download the output. This skill teaches the agent how to install, authenticate, discover model schemas, invoke models, stream / poll / no-wait, script in...

Genera videos con ByteDance Seedance 2.0 mediante la CLI de inference.sh. Modelo unificado para texto a video, imagen a video y referencia a video con audio sincronizado, hasta 1080p, duración de 4 a 15 segundos. Variantes Pro y Fast. Variantes Studio con biblioteca de activos privada para consistencia de retratos. Útil para: videos en redes sociales, videos musicales, demostraciones de productos, contenido animado, video con sonido de IA. Disparadores: seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video con audio,...

Genera videos con ByteDance Seedance 2.0 mediante la CLI de inference.sh. Modelo unificado para texto a video, imagen a video y referencia a video con audio sincronizado, hasta 1080p, duración de 4 a 15 segundos. Variantes Pro y Fast. Variantes Studio con biblioteca de activos privada para consistencia de retratos. Útil para: videos en redes sociales, videos musicales, demostraciones de productos, contenido animado, video con sonido de IA. Disparadores: seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video con audio,...

We need to translate the given text from English to Spanish. The text is a description of an agent skill for generating cinematic short-form video using ByteDance Seedance 2.0 Pro on RunComfy. The name "seedance-v2" is to be preserved, but it appears in the text as "seedance-v2" in the CLI command. Also note the list of trigger words at the end: "seedance", "seedance 2", "seedance v2", "seedance..." - these should be preserved as they are likely technical terms or product names. The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. So "ByteDance Seedance 2.0 Pro", "RunComfy", "HappyHorse 1.0", "Wan 2.7", "Kling", "runcomfy run bytedance/seedance-v2/pro" should remain as is. Also the duration "4–15s" should be preserved. The text inside <text> is the only

We need to translate the given text from English to Spanish. The text is a description of an agent skill for generating video using ByteDance Seedance 2.0 Pro on RunComfy. We must preserve the name "seedance-v2" and other technical terms like "ByteDance Seedance 2.0 Pro", "RunComfy", "HappyHorse 1.0", "Wan 2.7", "Kling", "CLI", etc. Also preserve numbers, URLs, and protocol names. Do not add any extra commentary or labels. The translation should be natural Spanish. The text inside <text> is: "Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy. Documents Seedance 2.0 Pro's strengths (multi-modal references — up to 9 images, 3 videos, 3 audio — synchronized in-pass audio with natural lip-sync, cinematic motion refinement), the 4–15s duration schema, and when to route to HappyHorse 1.0

Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy. Documents Seedance 2.0 Pro's strengths (multi-modal references — up to 9 images, 3 videos, 3 audio — synchronized in-pass audio with natural lip-sync, cinematic motion refinement), the 4–15s duration schema, and when to route to HappyHorse 1.0 / Wan 2.7 / Kling instead. Calls `runcomfy run bytedance/seedance-v2/pro` through the local RunComfy CLI. Triggers on "seedance", "seedance 2", "seedance v2", "seedance...

We need to translate the given text from English to Spanish. The text is a description of an agent skill for generating video using ByteDance Seedance 2.0 Pro on RunComfy. We must preserve the name "seedance-v2" and other technical terms like "ByteDance Seedance 2.0 Pro", "RunComfy", "HappyHorse 1.0", "Wan 2.7", "Kling", "CLI", etc. Also preserve numbers, URLs, and protocol names. Do not add any extra commentary or labels. The translation should be natural Spanish. The text inside <text> is: "Generate cinematic short-form video with ByteDance Seedance 2.0 Pro on RunComfy. Documents Seedance 2.0 Pro's strengths (multi-modal references — up to 9 images, 3 videos, 3 audio — synchronized in-pass audio with natural lip-sync, cinematic motion refinement), the 4–15s duration schema, and when to route to HappyHorse 1.0

Creación de storyboards para cine y video con vocabulario de tomas, reglas de continuidad y diseño de paneles. Cubre tipos de tomas, ángulos de cámara, movimiento, regla de 180 grados y formato de anotación. Útil para: planificación de video, preproducción cinematográfica, storyboards publicitarios, planificación de videos musicales, animación. Disparadores: storyboard, storyboarding, lista de tomas, planificación cinematográfica, planificación de video, preproducción, composición de tomas, ángulos de cámara, planificación de escenas, guion visual, animática, paneles de storyboard, storyboard de video.

Creación de storyboards para cine y video con vocabulario de tomas, reglas de continuidad y diseño de paneles. Cubre tipos de tomas, ángulos de cámara, movimiento, regla de 180 grados y formato de anotación. Útil para: planificación de video, preproducción cinematográfica, storyboards publicitarios, planificación de videos musicales, animación. Disparadores: storyboard, storyboarding, lista de tomas, planificación cinematográfica, planificación de video, preproducción, composición de tomas, ángulos de cámara, planificación de escenas, guion visual, animática, paneles de storyboard, storyboard de video.

Creación de storyboards para cine y video con vocabulario de tomas, reglas de continuidad y diseño de paneles. Cubre tipos de tomas, ángulos de cámara, movimiento, regla de los 180 grados y formato de anotación. Útil para: planificación de video, preproducción cinematográfica, storyboards publicitarios, planificación de videos musicales, animación. Disparadores: storyboard, storyboarding, lista de tomas, planificación cinematográfica, planificación de video, preproducción, composición de tomas, ángulos de cámara, planificación de escenas, guion visual, animática, paneles de storyboard, storyboard de video.

Crea una animación Lottie (Bodymovin) en formato JSON que se renderice en un reproductor skia local. Úsalo siempre que el usuario solicite crear, generar, editar o corregir una animación Lottie, o pida "una animación" para cargar.

Cuando el usuario desea crear, generar o producir contenido de video utilizando herramientas de IA o marcos programáticos. También se usa cuando el usuario menciona 'producción de video', 'video con IA', 'Remotion', 'Hyperframes', 'HeyGen', 'Synthesia', 'Veo', 'Sora', 'Runway', 'Kling', 'Seedance', 'Hailuo', 'MiniMax', 'Pika', 'Hunyuan', 'Wan', 'generación de video', 'avatar de IA', 'video de persona hablando', 'video programático', 'plantilla de video', 'video explicativo', 'video de demostración de producto', 'pipeline de video' o 'hazme un video'. Usar...

Editar video existente en RunComfy — esta habilidad es un enrutador inteligente que empareja la intención del usuario con el modelo de edición adecuado en el catálogo de RunComfy. Selecciona Wan 2.7 Edit-Video (reestilización general / cambio de fondo / cambio de empaque, preservación de identidad y movimiento), Kling 2.6 Pro Motion Control (transferir movimiento preciso desde un video de referencia a un personaje objetivo), o Lucy Edit Restyle (reestilización ligera con preservación de identidad / cambio de atuendo). Agrupa los patrones de indicaciones documentados de cada modelo para que la habilidad...

Editar video existente en RunComfy — esta habilidad es un enrutador inteligente que empareja la intención del usuario con el modelo de edición adecuado en el catálogo de RunComfy. Selecciona Wan 2.7 Edit-Video (reestilización general / cambio de fondo / cambio de empaque, preservación de identidad y movimiento), Kling 2.6 Pro Motion Control (transferir movimiento preciso desde un video de referencia a un personaje objetivo), o Lucy Edit Restyle (reestilización ligera con preservación de identidad / cambio de atuendo). Agrupa los patrones de indicaciones documentados de cada modelo para que la habilidad...

Editar video existente en RunComfy — esta habilidad es un enrutador inteligente que empareja la intención del usuario con el modelo de edición adecuado en el catálogo de RunComfy. Selecciona Wan 2.7 Edit-Video (reestilización general / cambio de fondo / cambio de empaque, preservación de identidad y movimiento), Kling 2.6 Pro Motion Control (transferir movimiento preciso desde un video de referencia a un personaje objetivo), o Lucy Edit Restyle (reestilización ligera con preservación de identidad / cambio de atuendo). Agrupa los patrones de indicaciones documentados de cada modelo para que la habilidad...

Extend or continue an existing video clip on RunComfy via the `runcomfy` CLI. Routes to Google Veo 3-1's `extend-video` and `fast/extend-video` endpoints — pick the source video plus a prompt describing what should happen next, and the model produces a clip that continues the original with consistent motion, lighting, and subject identity. Use when the user has a short Veo clip and wants it longer, or wants a chained narrative built shot-by-shot from a single seed clip. Triggers on "extend...

Extend or continue an existing video clip on RunComfy via the `runcomfy` CLI. Routes to Google Veo 3-1's `extend-video` and `fast/extend-video` endpoints — pick the source video plus a prompt describing what should happen next, and the model produces a clip that continues the original with consistent motion, lighting, and subject identity. Use when the user has a short Veo clip and wants it longer, or wants a chained narrative built shot-by-shot from a single seed clip. Triggers on "extend...

Extend or continue an existing video clip on RunComfy via the `runcomfy` CLI. Routes to Google Veo 3-1's `extend-video` and `fast/extend-video` endpoints — pick the source video plus a prompt describing what should happen next, and the model produces a clip that continues the original with consistent motion, lighting, and subject identity. Use when the user has a short Veo clip and wants it longer, or wants a chained narrative built shot-by-shot from a single seed clip. Triggers on "extend...

Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language), Lucy Edit Restyle (identity-stable region-aware restyle), and Seedream 4-0 edit-sequential (when treating the clip as a frame stack). Picks the right route based on whether the change is prose-driven,...

Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language), Lucy Edit Restyle (identity-stable region-aware restyle), and Seedream 4-0 edit-sequential (when treating the clip as a frame stack). Picks the right route based on whether the change is prose-driven,...

Region edits across video frames on RunComfy via the `runcomfy` CLI — remove an object that appears across many frames, clean up wires or watermarks, replace a region with matching motion. Routes across Wan 2-7 edit-video (default, prompt-driven region edits with spatial language), Lucy Edit Restyle (identity-stable region-aware restyle), and Seedream 4-0 edit-sequential (when treating the clip as a frame stack). Picks the right route based on whether the change is prose-driven,...

We need to translate the given text from English to Spanish. The text describes a video outpainting skill. We must preserve the name "video-outpainting" but it's not in the text; the text has "video outpainting" (lowercase, no hyphen). The instruction says "Do not include the name unless it appears in the source text." The source text has "Video outpainting" at the beginning. So we should translate that as "Video outpainting" but keep the term? Actually, the name to preserve is "video-outpainting" but the source has "Video outpainting". We should preserve the term as is? The instruction says "Preserve product names, protocol names, URLs, numbers, and technical terms." "video outpainting" is a technical term. So we should keep it as "video outpainting" (or maybe "video outpainting" in Spanish? But it's a technical term, likely kept in English). However, the target language is Spanish, so we need to translate the surrounding text.

We need to translate the given text from English to Spanish. The text describes a video outpainting skill. We must preserve the name "video-outpainting" but it's not in the text; the text mentions "video outpainting" and "video outpainting" as terms. The instruction says: "Do not include the name unless it appears in the source text." The name "video-outpainting" does not appear in the source text; only "video outpainting" (without hyphen) appears. So we should not add the hyphenated version. We translate the text inside <text> only. We need to preserve product names, protocol names, URLs, numbers, technical terms. "RunComfy", "runcomfy CLI", "Wan 2-7 edit-video", "ComfyUI" are proper names/technical terms, keep as is. "9:16", "16:9" are numbers/ratios, keep. "hero delivery" might be a term, but we can translate as "entrega del héroe

Video outpainting on RunComfy via the `runcomfy` CLI — extend the spatial canvas of a video, change aspect ratio (9:16 vertical to 16:9 horizontal or vice versa), add environment beyond the original frame while preserving the central action. Routes prompt-shaped spatial extension through Wan 2-7 edit-video and points the agent at dedicated ComfyUI outpaint workflows when seam quality matters for hero delivery. Triggers on "video outpaint", "video outpainting", "extend video canvas", "expand...

We need to translate the given text from English to Spanish, preserving the name "wan-2-7" and other technical terms. The text describes a skill for generating text-to-video with Wan 2.7. We must not include the name unless it appears in the source text. The source text includes "Wan 2.7", "Wan-AI", "RunComfy", "HappyHorse 1.0", "Seedance 2.0", "Kling", "LTX 2", "runcomfy run wan-ai/wan-2-7/text-to-video", "RunComfy CLI", and the trigger words. We need to translate the surrounding text while keeping these terms as is. Also note the instruction: "Do not include the name unless it appears in the source text." The name to preserve is "wan-2-7", which appears in the source as "wan-2-7" and "wan-2-7" in the command. So we keep it. Translate the rest. Let's

Generate text-to-video with Wan 2.7 (Wan-AI's flagship motion model) on RunComfy. Documents Wan 2.7's strengths (multi-reference conditioning, audio-driven lip-sync via `audio_url`, smoother transitions, prompt expansion), the duration / resolution / aspect-ratio schema, and when to route to HappyHorse 1.0 / Seedance 2.0 / Kling / LTX 2 instead. Calls `runcomfy run wan-ai/wan-2-7/text-to-video` through the local RunComfy CLI. Triggers on "wan", "wan 2.7", "wan-2-7", "wan video", or any...

Genera texto a video con Wan 2.7 (el modelo de movimiento insignia de Wan-AI) en RunComfy. Documenta las fortalezas de

Reproduce un video (URL o ruta local). Descarga con yt-dlp, extrae fotogramas con escala automática usando ffmpeg, obtiene la transcripción de los subtítulos (o recurre a la API de Whisper), y entrega el resultado a Claude para que pueda responder preguntas sobre el contenido del video.