Skills de Video

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. The text describes a skill for writing and critiquing viral hooks for short-form video. We must preserve the name 'viral-hooks' but it's not in the text, so we don't include it. We translate the text inside <text> only. No extra labels. Keep technical terms like "three-layer hook", "Kallaway", "MrBeast", etc. as is. Translate the rest naturally. The text: "Write and critique viral hooks for short-form video: the opening 1 to 3 seconds that decide whether anything else gets seen. Use this when you need a batch of hook ideas for a video, want to make a weak opening line stronger, are picking which hook archetype fits an idea, or want a critique of a draft hook against proven patterns. Covers the three-layer hook (visual, verbal, on-screen text), the named-creator frameworks (Kallaway, MrBeast, Hormozi, Brunson, Koe, Welsh, Bush, Galloway),

Genera ideas y escribe contenido de video corto y carrusel de alta retención para TikTok, Reels y YouTube Shorts. Úsalo cada vez que alguien quiera ideas de ganchos virales, un guion o esquema de video, conceptos de contenido para un producto o tema, o quiera criticar y mejorar un borrador de gancho o guion. Funciona para cualquier formato de video corto: talking head, demostración, unboxing, antes/después, tutorial, storytime, listicle, carrusel o meme. Produce varias opciones de gancho diversas a partir de patrones probados, estructura guiones para...

Escribe un guion de TikTok, un gancho de TikTok o una idea fresca de video de TikTok adaptada a cómo el FYP realmente clasifica el contenido. Úsalo cuando alguien pida un gancho de TikTok para X, quiera un guion con formato de TikTok, pregunte si un clip es un TikTok o un Reel, quiera mejorar un video de TikTok que haya borrador, o quiera saber qué tendencias de TikTok vale la pena seguir esta semana. Cubre las señales del algoritmo de TikTok (interacciones de usuarios, información del video, dispositivo y cuenta), matemáticas de tasa de finalización por duración, sonidos de tendencia...

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.

Captura un sitio web/URL general y conviértelo en un video de HyperFrames (recorrido del sitio, presentación o clip social a partir de los propios elementos visuales del sitio). Utiliza capturas de pantalla de Chrome sin interfaz gráfica + activos de marca. Úsalo cuando la intención sea general: presentación de portafolio/blog/página de aterrizaje o clip social del sitio. NO para: lanzamiento o promoción de producto/SaaS (→ /product-launch-video, incluso desde una URL); explicador de tema sin sitio (→ /faceless-explainer); PR de GitHub (→ /pr-to-video); agregar subtítulos a un video existente (→...

Diseño de miniaturas de YouTube con dimensiones específicas, reglas de contraste y optimización para vista previa móvil. Cubre zonas seguras, colocación de texto, psicología de expresiones faciales y pruebas A/B. Útil para: miniaturas de YouTube, imágenes de portada de video, optimización de clics. Desencadenantes: miniatura de YouTube, diseño de miniatura, miniatura de video, tasa de clics, optimización de CTR, portada de YouTube, imagen de portada de video, creador de miniaturas, consejos para miniaturas, diseño de YouTube, imagen de vista previa de video