Skills Vidéo

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 French. 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" is not in the source text, so we don't include it. The source text has "Video outpainting" at the beginning. We translate that. We need to translate the entire text inside <text> tags. Keep technical terms like "RunComfy", "runcomfy CLI", "Wan 2-7 edit-video", "ComfyUI", "hero delivery" etc. Preserve URLs? None. Numbers: 9:16, 16:9. Also "outpainting" is a technical term, likely kept as is or translated? In French, "outpainting" is often used as is, but sometimes

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 French. 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" at the start. We should translate that as "Video outpainting" is a term, but we can translate it as "Extension vidéo" or keep "Video outpainting"? The instruction says preserve product names, protocol names, URLs, numbers, technical terms. "Video outpainting" is a technical term, so likely keep as is or translate? The name to preserve is "video-outpainting" (lowercase with hyphen). In the text it's "Video outpainting" (capitalized). I think we should keep it as "Video outpainting" because it's a technical term. But the instruction says "Translate only the text inside <text>. Do not include the name unless it appears in the source text." The name "video-outpainting" does not appear in the source text; the source

Rédigez et critiquez des accroches virales pour vidéos courtes : les 1 à 3 premières secondes qui déterminent si le reste sera vu. Utilisez ceci lorsque vous avez besoin d’un lot d’idées d’accroches pour une vidéo, souhaitez renforcer une ligne d’ouverture faible, choisissez quel archétype d’accroche correspond à une idée, ou voulez une critique d’une ébauche d’accroche par rapport à des modèles éprouvés. Couvre l’accroche en trois couches (visuelle, verbale, texte à l’écran), les cadres de créateurs nommés (Kallaway, MrBeast, Hormozi, Brunson, Koe, Welsh, Bush, Galloway),...

We need to translate the given English text into French. The text describes an agent skill for creating 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..." We need to translate accurately, keeping technical terms like "TikTok", "Reels", "YouTube Shorts", "talking head", "demo", etc. Also "high-retention

Rédiger un script TikTok, une accroche TikTok ou une idée de vidéo TikTok originale adaptée au classement réel du contenu par le FYP. Utilisé lorsque quelqu'un demande une accroche TikTok pour X, souhaite un script formaté pour TikTok, demande si un clip est un TikTok ou une Reel, veut améliorer une vidéo TikTok qu'il a rédigée, ou veut savoir quelles tendances TikTok valent la peine d'être suivies cette semaine. Couvre les signaux de l'algorithme TikTok (interactions utilisateur, informations vidéo, appareil et compte), le calcul du taux de complétion par durée, les sons tendance...

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...

We need to translate the given text from English to French, preserving the name "wan-2-7" and other technical terms. The instruction says: "Translate only the text inside <text>. Do not include the name unless it appears in the source text." The name "wan-2-7" appears in the source text, so we keep it as is. Also preserve "RunComfy", "Wan-AI", "HappyHorse 1.0", "Seedance 2.0", "Kling", "LTX 2", "runcomfy run wan-ai/wan-2-7/text-to-video", "CLI", and URLs or technical terms. The text is a description of an agent skill. We need to output only the translation, no extra commentary. Let's translate paragraph by paragraph. Original: "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

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...

Regarder une vidéo (URL ou chemin local). Télécharge avec yt-dlp, extrait les images automatiquement redimensionnées avec ffmpeg, récupère la transcription des sous-titres (ou via l'API Whisper en solution de repli), et transmet le résultat à Claude pour qu'il puisse répondre à des questions sur le contenu de la vidéo.

Capturez un site web/URL général et transformez-le en vidéo HyperFrames (visite de site, démonstration ou clip social à partir des visuels propres du site). Utilise des captures d'écran headless Chrome + des éléments de marque. À utiliser lorsque l'intention est générale — démonstration de portfolio/blog/page d'accueil ou clip social à partir du site. PAS pour : lancement ou promotion de produit/SaaS (→ /product-launch-video, même à partir d'une URL) ; explicateur de sujet sans site (→ /faceless-explainer) ; PR GitHub (→ /pr-to-video) ; ajout de sous-titres à une vidéo existante (→...

Conception de miniatures YouTube avec dimensions spécifiques, règles de contraste et optimisation pour l'aperçu mobile. Couvre les zones de sécurité, le placement du texte, la psychologie des expressions faciales et les tests A/B. Utilisation pour : miniatures YouTube, images de couverture vidéo, optimisation du taux de clics. Déclencheurs : miniature YouTube, conception de miniature, miniature vidéo, taux de clics, optimisation du CTR, couverture YouTube, image de couverture vidéo, créateur de miniature, conseils pour miniatures, design YouTube, image d'aperçu vidéo.