Skills Agentspace So

runcomfy-agent-skills/ace-step

Generate, inpaint, and outpaint music with ACE Step on RunComfy via the `runcomfy` CLI. ACE Step is StepFun-AI's open-weights music foundation model — tag-driven composition (genre, mood, instruments), multilingual lyrics with section markers, 5 s to 4 min stereo output, $0.0002–0.0003 per second (≈ 27× cheaper than ElevenLabs Music). Four endpoints: ACE Step text-to-audio (the default), ACE Step 1.5 text-to-audio (50+ language lyrics, refined structured-lyric handling), ACE Step...

skills/agentspace

Voyez ce que votre agent IA fait, depuis n'importe où. L'agent continue d'écrire — logs, code, sorties générées, captures d'écran, artefacts. Une seule commande transforme le dossier en une URL live que vous (ou un collègue) ouvrez dans n'importe quel navigateur pour voir les fichiers évoluer, modifier sur place ou commenter — sans synchronisation, sans zip, sans compte. Les espaces de travail restent actifs 24 heures de manière anonyme ; une seule réclamation par email les rend permanents. Hébergé sur Cloudflare. Se déclenche sur "montre-moi ce que fait l'agent", "ouvre le dossier de l'agent", "partage ce dossier",...

runcomfy-agent-skills/ai-avatar-video

Create AI avatar, talking-head, and lip-sync videos on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar), Wan-AI Wan 2-7 (audio-driven mouth sync via `audio_url` on a portrait), HappyHorse 1.0 (Arena #1 t2v / i2v with in-pass audio), and Seedance v2 Pro (multi-modal cinematic with reference audio + reference subject). Picks the right model for the user's actual intent — UGC voiceover, virtual presenter, dubbed product demo, lip-synced...

runcomfy-agent-skills/ai-image-generation

Generate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits,...

runcomfy-agent-skills/ai-music

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right...

runcomfy-agent-skills/ai-video-generation

Generate AI videos on RunComfy via the `runcomfy` CLI — a smart router across the full video-model catalog: HappyHorse 1.0 (Arena #1, native in-pass audio), Wan-AI Wan 2-7 (open weights, audio-driven lip-sync), ByteDance Seedance v2 / 1-5 / 1-0 (multi-modal cinematic), Kling 3.0 / 2-6, Google Veo 3-1, MiniMax Hailuo 2-3, ByteDance Dreamina 3-0. Covers text-to-video (t2v), image-to-video (i2v), and Veo's video-extend endpoint. The skill picks the right model for the user's intent (Arena-#1...

runcomfy-agent-skills/codex-pet

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into `${CODEX_HOME:-$HOME/.codex}/pets/ /` and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2...

runcomfy-agent-skills/controlnet-pose

We need to translate the given text from English to French, preserving the specified name "controlnet-pose" and other technical terms. The text describes a directory item type "agent skill" with a name to preserve. The instruction says to translate only the text inside <text>, not including the name unless it appears in the source text. The name "controlnet-pose" does appear in the source text? Actually, the source text does not contain "controlnet-pose" explicitly; it appears in the context of "Z-Image Turbo ControlNet LoRA" but not as a standalone name. The instruction says "Name to preserve: controlnet-pose" but the source text doesn't have that exact string. However, we should preserve any occurrence of "controlnet" or similar? The instruction says "Do not include the name unless it appears in the source text." Since "controlnet-pose" does not appear in the source text, we don't need to include it. But we should preserve "ControlNet" as a technical term. Also preserve "RunComfy

runcomfy-agent-skills/elevenlabs-music-generation

Generate full songs and instrumental tracks with ElevenLabs Music on RunComfy via the `runcomfy` CLI. ElevenLabs Music turns a style description plus structured lyrics into studio-quality 44.1 kHz stereo audio — 5 seconds to 5 minutes — with section-level control (Intro / Verse / Chorus / Bridge), multilingual vocals, and commercial-friendly output. Generate a backing track, a full vocal song, a jingle, a podcast intro, a game loop, or an instrumental bed. Calls `runcomfy run...

runcomfy-agent-skills/face-swap

Swap a face / character into video or images on RunComfy via the `runcomfy` CLI. Routes across community Wan 2-2 Animate (audio-driven character animation + identity swap), GPT Image 2 Edit (single-shot precise face swap on still images via reference composition), Nano Banana Edit (batch identity-preserving swap), Flux Kontext (single-ref high-fidelity local face edit), and Kling 2-6 Motion Control Pro (transfer motion from one performance onto a target character). Picks the right model for...

skills/find-skills

Découvrir, évaluer et installer des compétences d'agent en recherchant simultanément dans tous les grands registres — skills.sh, clawhub.ai et GitHub — en présentant chaque tableau selon sa métrique native (installations / étoiles) avec la meilleure entrée par tableau, en analysant la sécurité du SKILL.md réel des meilleurs candidats pour détecter les motifs risqués, et en signalant ce qui est déjà installé. Utiliser lorsque l'utilisateur demande « comment faire X », « trouver une compétence pour X », « existe-t-il une compétence qui… », « quelle compétence installer pour… », ou souhaite étendre l'agent avec une...

runcomfy-agent-skills/flux-2-klein

Générer des images avec Flux 2 Klein (variante rapide distillée de Flux 2 par Black Forest Labs) sur RunComfy — inclut les schémas de prompt documentés du modèle pour que la compétence produise des résultats plus précis qu’un prompt naïf sur le même modèle. Documente les atouts de Flux 2 Klein (latence inférieure à la seconde, stylisme multi-référence de marque, prompts déclaratifs centrés sur le sujet), la stratégie de nombre d’étapes (4–8 pour itération rapide, ~25 pour finition), le compromis entre les variantes 9B et 4B, et le moment où orienter vers Flux 2 Pro /...

runcomfy-agent-skills/flux-kontext

Modifiez des images avec Flux 1 Kontext Pro (le modèle d'édition locale précise de Black Forest Labs) sur RunComfy — intégré aux schémas de prompt documentés du modèle pour que la compétence produise des résultats plus précis qu'une sollicitation naïve avec le même modèle. Documente les points forts de Flux Kontext (éditions locales précises à partir d'une seule référence, contrôle strict du prompt, sorties haute fidélité cohérentes), le schéma (image unique + prompt), et quand rediriger vers Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein à la place. Appels...

runcomfy-agent-skills/gpt-image-2

Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy. Documents GPT Image 2's strengths (embedded text, logos, multilingual typography, instruction precision), its 3 fixed sizes, edit-with-preservation language, and when to route to a sibling (Flux 2 / Nano Banana Pro / Seedream) instead. Calls `runcomfy run openai/gpt-image-2/text-to-image` or `/edit` through the local RunComfy CLI. Triggers on "gpt image 2", "gpt-image-2", "ChatGPT Images 2", "image 2", or any...

runcomfy-agent-skills/gpt-image-edit

Edit images with OpenAI GPT Image 2 (the `/edit` endpoint of ChatGPT Images 2.0) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents GPT Image Edit's strengths (preservation language, multilingual in-image text editing, multi-reference up to 10 images, layout / typography precision), the schema, and when to route to Nano Banana Edit / Flux Kontext / GPT Image 2 t2i instead. Calls...

runcomfy-agent-skills/happyhorse-1-0

Générer du texte vers vidéo avec HappyHorse 1.0 sur RunComfy. Documente les points forts de HappyHorse 1.0 (n°1 sur l'Artificial Analysis Video Arena, 1080p natif avec audio synchronisé dans la séquence, cohérence des personnages multi-plans, prise en charge des invites en 6

runcomfy-agent-skills/image-edit

Modifier des images sur RunComfy — cette compétence est un routeur intelligent qui associe l'intention de l'utilisateur au bon modèle d'édition dans le catalogue RunComfy. Sélectionne Nano Banana Edit (lot jusqu'à 20, préservation d'identité par défaut), OpenAI GPT Image 2 Edit (réécriture multilingue de texte dans l'image, composition multi-référence, précision de mise en page), Flux Kontext Pro (édition locale haute-fidélité à référence unique), ou Z-Image Turbo Inpaint (édition précise de région pilotée par masque). Regroupe les schémas de sollicitation documentés de chaque modèle afin que la compétence obtienne...

runcomfy-agent-skills/image-inpainting

Mask-driven image inpainting on RunComfy via the `runcomfy` CLI. Routes to Tongyi MAI Z-Image Turbo Inpainting (the dedicated inpainting endpoint with mask, strength, and control-scale) and to identity-preserving edit models (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when a mask isn't available and the region must be described instead. Use for object removal, watermark removal, region replacement, blemish cleanup, and any controlled local edit where a binary mask defines the...

runcomfy-agent-skills/image-outpainting

Image outpainting on RunComfy via the `runcomfy` CLI — extend a still beyond its original canvas, fill in what the camera didn't capture, change aspect ratio (square → 16:9, portrait → landscape) while preserving the original content. Routes across Nano Banana 2 Edit (default, spatial-language driven), GPT Image 2 Edit (multi-ref with reference-style matching), FLUX Kontext Pro (single-shot maximum-preservation), and the brand edit endpoints (Seedream / Dreamina / Qwen / FLUX 2). Picks the...

runcomfy-agent-skills/image-to-video

We need to translate the given text from English to French. The text describes an agent skill called "image-to-video" but the instruction says to preserve the name only if it appears in the source text. The name "image-to-video" does not appear in the provided text, so we don't include it. We must preserve product names, protocol names, URLs, numbers, technical terms. So "RunComfy", "HappyHorse 1.0 I2V", "Arena #1", "Wan 2.7", "audio_url", "Seedance 2.0 Pro", "i2v" etc. should remain as is. Also "I2V" is a technical term. Translate the rest naturally. Text: "Animate any still image on RunComfy — this skill is a smart router that matches the user's intent to the right i2v model in the RunComfy catalog. Picks HappyHorse 1.0 I2V (Arena #1, native audio, identity preservation) for general animations

runcomfy-agent-skills/kling-3-0

Génération vidéo Kling 3.0 sur RunComfy. Kling 3.0 (aussi appelé Kling V3.0) est le modèle vidéo multi-plan de troisième génération de Kuaishou Technology, avec audio natif synchronisé et identité de personnage cohérente entre les plans. Cette compétence couvre les six points d'accès Kling 3.0, répartis sur trois niveaux de rendu (Standard, Pro, 4K) et deux modes (texte-vers-vidéo, image-vers-vidéo). Les appels runcomfy run kling/kling-3.0/ / via l'interface CLI locale RunComfy. Déclencheurs sur "kling", "kling 3.0", "kling v3", "kling pro",...

runcomfy-agent-skills/lipsync

We need to translate the given English text into French, preserving the specified name "lipsync" and other technical terms like "RunComfy", "runcomfy CLI", "ByteDance OmniHuman", "Sync Labs sync v2 / Pro", "Kling lipsync", "Creatify lipsync". Also preserve URLs, numbers, etc. The instruction says to translate only the text inside <text>, and not include the name unless it appears in the source text. The name "lipsync" appears in the source text as "Lip-sync" at the beginning, so we should translate that? Actually the instruction says "Preserve product names, protocol names, URLs, numbers, and technical terms." "lipsync" is a skill name, but it appears as part of the text. The instruction says "Do not include the name unless it appears in the source text." So we should keep "lipsync" as is? But it says "Translate only the text inside <text>." The text includes "Lip-sync" which is the skill

runcomfy-agent-skills/nano-banana-2

Générer des images avec Google Nano Banana 2 (text-to-image de niveau flash de la famille Gemini) sur RunComfy — intégré avec les schémas de prompt documentés du modèle, afin que la compétence produise des résultats plus précis qu’un prompt naïf avec le même modèle. Documente les points forts de Nano Banana 2 (itération rapide, rendu typographique dans l’image, cadrage prévisible, contexte web facultatif), la tarification par palier de résolution, le curseur de tolérance de sécurité, et quand orienter vers Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream...

runcomfy-agent-skills/nano-banana-edit

We need to translate the given text from English to French, preserving the name "nano-banana-edit" and other technical terms. The text describes an agent skill for editing images using Google Nano Banana 2 on RunComfy. We must not include the name unless it appears in the source text, but it does appear: "nano-banana-edit" is in the name field, but the instruction says "Do not include the name unless it appears in the source text." The name "nano-banana-edit" appears in the source text? Actually, the source text includes "Nano Banana Edit's" and "nano banana edit" etc. But the name to preserve is "nano-banana-edit" (with hyphens). In the source text, it appears as "Nano Banana Edit" (without hyphens) and "nano banana edit". The instruction says "Name to preserve: nano-banana-edit". So we should preserve that exact string if it appears. It does not appear exactly in the source text. However, the

runcomfy-agent-skills/relight

Relight a still image — change the lighting setup, color temperature, direction, or mood — on RunComfy via the `runcomfy` CLI. Routes to Qwen Edit 2509's dedicated `relight` LoRA endpoint for purpose-built relighting, with fallback to identity-preserving edit endpoints (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when prose lighting language is enough. Use for product relighting (studio softbox → window light), portrait mood shift (overcast → golden hour), or color-grade change....

runcomfy-agent-skills/runcomfy-cli

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...

runcomfy-agent-skills/seedance-v2

We need to translate the given text from English to French. The text describes a skill for generating cinematic short-form video using ByteDance Seedance 2.0 Pro on RunComfy. It mentions strengths, duration schema, and routing alternatives. Also mentions CLI command and trigger keywords. We must preserve product names, protocol names, URLs, numbers, technical terms. So "ByteDance Seedance 2.0 Pro", "RunComfy", "HappyHorse 1.0", "Wan 2.7", "Kling", "seedance-v2", "runcomfy run bytedance/seedance-v2/pro" should remain as is. Also "4–15s" is a number range, keep as is. "multi-modal references", "in-pass audio", "lip-sync", "cinematic motion refinement" are technical terms; translate if possible but keep meaning. "CLI" is an acronym, keep. Trigger keywords: "seedance", "seedance 2", "seedance v2", "seedance...

runcomfy-agent-skills/video-edit

Modifier une vidéo existante sur RunComfy — cette compétence est un routeur intelligent qui associe l'intention de l'utilisateur au bon modèle d'édition dans le catalogue RunComfy. Sélectionne Wan 2.7 Edit-Video (restylage général / échange d'arrière-plan / échange d'emballage, préservation de l'identité et du mouvement), Kling 2.6 Pro Motion Control (transférer un mouvement précis d'une vidéo de référence à un personnage cible), ou Lucy Edit Restyle (restylage léger avec préservation de l'identité / échange de tenue). Regroupe les schémas de sollicitation documentés de chaque modèle afin que la compétence...

runcomfy-agent-skills/video-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...

runcomfy-agent-skills/video-inpainting

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,...