Skills de Vídeo

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,...

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...

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...

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...

Escreva e critique ganchos virais para vídeos curtos: os 1 a 3 segundos iniciais que decidem se algo mais será visto. Use isto quando precisar de um lote de ideias de gancho para um vídeo, quiser fortalecer uma linha de abertura fraca, estiver escolhendo qual arquétipo de gancho se encaixa em uma ideia, ou quiser uma crítica de um rascunho de gancho com base em padrões comprovados. Abrange o gancho de três camadas (visual, verbal, texto na tela), os frameworks de criadores nomeados (Kallaway, MrBeast, Hormozi, Brunson, Koe, Welsh, Bush, Galloway),...

We need to translate the given text from English to Brazilian Portuguese. The text describes an agent skill for brainstorming and writing short-form video content. We must preserve the name "viral-short-form" but it's not in the text, so we don't include it. We translate the entire text inside <text>. No extra labels or commentary. Just the translation. The text: "Brainstorm and write high-retention short-form video and carousel content for TikTok, Reels, and YouTube Shorts. Use whenever someone wants viral hook ideas, a video script or outline, content concepts for a product or topic, or wants to critique and improve a draft hook or script. Works for any short-form format: talking head, demo, unboxing, before/after, tutorial, storytime, listicle, carousel, or meme. Produces several diverse hook options from proven patterns, structures scripts for..." Translate to Portuguese (BR). Keep technical terms like TikTok, Reels, YouTube Shorts, etc. "high-retention" -> "alto engajamento" or

Escreva um roteiro para TikTok, um gancho para TikTok ou uma ideia nova de vídeo no TikTok moldada para como o FYP realmente ranqueia conteúdo. Use quando alguém pedir um gancho para TikTok sobre X, quiser um roteiro no formato TikTok, perguntar se um clipe é um TikTok ou um Reel, quiser melhorar um vídeo do TikTok que rascunhou, ou quiser saber quais tendências do TikTok valem a pena seguir esta semana. Abrange os sinais do algoritmo do TikTok (interações do usuário, informações do vídeo, dispositivo e conta), matemática da taxa de conclusão por duração, sons em alta...

We need to translate the given text from English to Brazilian Portuguese. The text describes an agent skill for generating text-to-video with Wan 2.7 on RunComfy. We must preserve product names, protocol names, URLs, numbers, and technical terms. The name "wan-2-7" is to be preserved but not included 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 terms like "multi-reference conditioning", "audio-driven lip-sync", "audio_url", "prompt expansion", "duration / resolution / aspect-ratio schema". Also numbers like "2.7", "1.0", "2.0", "2". We need to translate the rest naturally. The text: "Generate

We need to translate the given text from English to Brazilian Portuguese. The text describes an agent skill for generating text-to-video with Wan 2.7 on RunComfy. We must preserve product names, protocol names, URLs, numbers, and technical terms. The name "wan-2-7" is to be preserved but not included 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", "audio_url", "runcomfy run wan-ai/wan-2-7/text-to-video", "RunComfy CLI", and terms like "multi-reference conditioning", "audio-driven lip-sync", "prompt expansion", "duration / resolution / aspect-ratio schema". Also the trigger words: "wan", "wan 2.7", "wan-2-7", "wan video". We need to translate the surrounding text while

We need to translate the given text from English to Brazilian Portuguese. The text describes an agent skill for generating text-to-video with Wan 2.7. We must preserve product names, protocol names, URLs, numbers, and technical terms. The name "wan-2-7" is to be preserved but not included 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 terms like "multi-reference conditioning", "audio-driven lip-sync", "audio_url", "prompt expansion", "duration / resolution / aspect-ratio schema". Also numbers like 2.7, 1.0, 2.0, 2. Also "wan", "wan 2.7", "wan-2-7

Assistir a um vídeo (URL ou caminho local). Faz o download com yt-dlp, extrai frames com redimensionamento automático usando ffmpeg, obtém a transcrição das legendas (ou usa a Whisper API como alternativa) e envia o resultado para o Claude, que pode responder perguntas sobre o conteúdo do vídeo.

Capture um site/URL geral e transforme-o em um vídeo HyperFrames (tour do site, demonstração ou clipe social a partir dos próprios visuais do site). Usa capturas de tela do Chrome headless + ativos da marca. Use quando a intenção for geral — demonstração de portfólio/blog/landing-page ou clipe social a partir do site. NÃO para: lançamento ou promoção de produto/SaaS (→ /product-launch-video, mesmo a partir de uma URL); explicador de tópico sem site (→ /faceless-explainer); PR do GitHub (→ /pr-to-video); adicionar legendas a vídeo existente (→...

Design de thumbnail para YouTube com dimensões específicas, regras de contraste e otimização para visualização em dispositivos móveis. Abrange zonas seguras, posicionamento de texto, psicologia da expressão facial e teste A/B. Use para: thumbnails do YouTube, imagens de capa de vídeo, otimização de taxa de cliques. Gatilhos: thumbnail do YouTube, design de thumbnail, thumbnail de vídeo, taxa de cliques, otimização de CTR, capa do YouTube, imagem de capa de vídeo, criador de thumbnail, dicas de thumbnail, design do YouTube, imagem de pré-visualização de vídeo