Skills de Agentspace So

Gere

Veja o que seu agente de IA está fazendo, de qualquer lugar. O agente continua escrevendo — logs, código, saídas geradas, capturas de tela, artefatos. Um comando transforma a pasta em uma URL ao vivo que você (ou um colega) abre em qualquer navegador para ver arquivos evoluindo, editar no local ou comentar — sem sincronização, sem zip, sem conta. Os espaços de trabalho permanecem ativos 24 horas anonimamente; uma reivindicação por e-mail os mantém permanentes. Hospedado na Cloudflare. Aciona com "mostre-me o que o agente está fazendo", "abra a pasta do agente", "compartilhe esta pasta",...

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...

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,...

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...

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...

We need to translate the given text from English to Brazilian Portuguese. The text describes a skill called "codex-pet" but the instruction says not to include the name unless it appears in the source text. The name "codex-pet" does appear in the source? Actually, the source text starts with "Codex Pet generator on RunComfy." The name "codex-pet" is not explicitly in the text; it's the directory item name. The instruction says "Do not include the name unless it appears in the source text." The name "codex-pet" does not appear in the source text, so we should not add it. The source text mentions "Codex Pet" multiple times, which is a product name, so we preserve that. Also preserve "RunComfy", "spritesheet.webp", "pet.json", "Codex", "PNG/WebP", "OpenAI GPT Image 2". Translate the rest naturally to Brazilian Portuguese. The text: "Codex Pet generator on RunComfy. Build a Codex

Pose-conditioned generation on RunComfy via the `runcomfy` CLI. Routes across Kling 2-6 Motion Control Pro / Standard (transfer the motion / blocking of a reference video onto a target character), community Wan 2-2 Animate (audio-driven character animation with pose conditioning), and Z-Image Turbo ControlNet LoRA (pose-conditioned image generation from an OpenPose / DWPose / canny / depth control image). Picks the right route based on video vs still and stylized vs photoreal. Triggers on...

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...

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...

Descubra, avalie e instale skills de agente pesquisando em todos os registros principais de uma só vez — skills.sh, clawhub.ai e GitHub — apresentando cada quadro com sua métrica nativa (instalações / estrelas), exibindo a melhor entrada por quadro, escaneando a segurança do SKILL.md real dos principais candidatos em busca de padrões arriscados e sinalizando o que já está instalado. Use quando o usuário perguntar "como faço X", "encontre uma skill para X", "existe uma skill que…", "qual skill devo instalar para…" ou quiser estender o agente com um...

Gere imagens com Flux 2 Klein (variante rápida destilada do Flux 2 da Black Forest Labs) no RunComfy — incluindo os padrões de prompt documentados do modelo para que a skill produza resultados mais precisos do que prompts ingênuos no mesmo modelo. Documenta os pontos fortes do Flux 2 Klein (latência abaixo de um segundo, estilização de marca com múltiplas referências, prompts declarativos com foco no sujeito), a estratégia de contagem de passos (4–8 para iteração rápida, ~25 para refinamento), a compensação entre as variantes 9B e 4B, e quando direcionar para o Flux 2 Pro /...

Edite imagens com Flux 1 Kontext Pro (modelo de edição local precisa de imagens da Black Forest Labs) no RunComfy — incluído com os padrões de prompt documentados do modelo para que a habilidade obtenha resultados mais nítidos do que prompts ingênuos contra o mesmo modelo. Documenta os pontos fortes do Flux Kontext (edições locais precisas com referência única, forte controle de prompt, saídas consistentes de alta fidelidade), o esquema (imagem única + prompt) e quando redirecionar para Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein. Chama...

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...

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...

We need to translate the given text from English to Brazilian Portuguese. The text describes an agent skill for generating text-to-video with HappyHorse 1.0 on RunComfy. We must preserve the name "happyhorse-1-0" and any technical terms, 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 "happyhorse-1-0" appears in the source text? Actually, the source text mentions "HappyHorse 1.0" and "happyhorse-1-0" in the command. So we should preserve those as is. Also preserve "RunComfy", "Wan 2.7", "Seedance 2", "LTX 2", "CLI", etc. The translation should be natural Brazilian Portuguese. Let's break down the text: "Generate text-to-video with HappyHorse 1.0 on RunComfy. Documents HappyHorse 1.0's strengths (#1 on Artificial

Edite imagens no RunComfy — esta skill é um roteador inteligente que combina a intenção do usuário com o modelo de edição correto no catálogo do RunComfy. Seleciona Nano Banana Edit (lote de até 20, preservação de identidade padrão), OpenAI GPT Image 2 Edit (reescrita multilíngue de texto em imagem, composição multi-referência, precisão de layout), Flux Kontext Pro (edição local de alta fidelidade com referência única) ou Z-Image Turbo Inpaint (edição precisa de região orientada por máscara). Agrupa os padrões de prompt documentados de cada modelo para que a skill obtenha...

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...

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...

We need to translate the given text from English to Brazilian Portuguese. The text describes a skill called "image-to-video" but the instruction says not to include the name unless it appears in the source text. The name "image-to-video" does appear in the source? Actually, the source text starts with "Animate any still image on RunComfy — this skill is a smart router..." The name is not explicitly written as "image-to-video" in the source text. The instruction says "Name to preserve: image-to-video" but also "Do not include the name unless it appears in the source text." Since it does not appear, we should not add it. We just translate the text inside <text>. We need to preserve product names: RunComfy, HappyHorse 1.0 I2V, Wan 2.7, Seedance 2.0 Pro, and terms like i2v, audio_url, etc. Also preserve numbers and technical terms. Translate "Animate any still image on RunComfy" -> "Anime

Geração de vídeo Kling 3.0 no RunComfy. O Kling 3.0 (também chamado de Kling V3.0) é o modelo de vídeo multi-tomada de terceira geração da Kuaishou Technology, com áudio sincronizado nativo e identidade de personagem consistente entre as tomadas. Esta skill cobre todos os seis endpoints do Kling 3.0, abrangendo três níveis de renderização (Standard, Pro, 4K) e dois modos (texto para vídeo, imagem para vídeo). Chamadas executam runcomfy run kling/kling-3.0/ / através da CLI local do RunComfy. Aciona com "kling", "kling 3.0", "kling v3", "kling pro",...

We need to translate the given text from English to Brazilian Portuguese. The text describes a skill for lip-syncing. We must preserve product names, protocol names, URLs, numbers, technical terms. The name "lipsync" is not in the text? Actually it appears at the beginning: "Lip-sync a face..." but the instruction says "Do not include the name unless it appears in the source text." The name "lipsync" appears as part of the first word "Lip-sync". That is a verb, not the skill name. The skill name is "lipsync" but it's not explicitly in the text as a standalone name. The instruction says "Name to preserve: lipsync" but we only translate text inside <text>. The text starts with "Lip-sync a face..." So we should translate that as "Sincronize os lábios de um rosto..." preserving the technical terms like "RunComfy", "runcomfy CLI", "ByteDance OmniHuman", "Sync Labs sync v2 / Pro",

Gere imagens com o Google Nano Banana 2 (texto-para-imagem de nível flash da família Gemini) no RunComfy — acompanhado dos padrões de prompt documentados do modelo, para que a habilidade produza resultados mais precisos do que prompts ingênuos com o mesmo modelo. Documenta os pontos fortes do Nano Banana 2 (iteração rápida, renderização de tipografia em imagem, enquadramento previsível, contexto opcional baseado na web), os preços por nível de resolução, o ajuste de tolerância de segurança e quando direcionar para Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream...

We need to translate the given text from English to Brazilian Portuguese. The text describes an agent skill for editing images using Google Nano Banana 2 on RunComfy. We must preserve product names, protocol names, URLs, numbers, technical terms. Do not add any extra commentary, labels, or formatting. The name "nano-banana-edit" is given but not to be included unless it appears in the source text. The source text includes "Nano Banana Edit's" and "nano banana edit" etc. So we translate the text, keeping those names as is. Also keep "RunComfy", "Google Nano Banana 2", "GPT Image 2 edit", "Flux Kontext", "Nano Banana 2 t2i", "runcomfy run google/nano-banana-2/edit", "RunComfy CLI". Numbers: 2, 20. Translate the rest naturally. The text: "Edit images with Google Nano Banana 2 (image-to-image edit endpoint) on RunComfy. Documents Nano Banana Edit's strengths (pres

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....

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 Brazilian Portuguese. The text describes a skill for generating cinematic short-form video using ByteDance Seedance 2.0 Pro on RunComfy. It mentions strengths, duration schema, routing alternatives, and CLI command. The name "seedance-v2" is to be preserved, but it appears in the text as "seedance-v2" in the CLI command. Also note the text ends with "seedance..." which is incomplete. We should translate everything inside <text> except 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", "runcomfy run bytedance/seedance-v2/pro" are technical terms/names to preserve. Also "4–15s" is a number range, preserve. "multi-modal references", "in-pass audio", "lip-sync", "cinematic motion refinement

Edite vídeo existente no RunComfy — esta skill é um roteador inteligente que combina a intenção do usuário com o modelo de edição correto no catálogo do RunComfy. Seleciona Wan 2.7 Edit-Video (reestilização geral / troca de fundo / troca de embalagem, preservação de identidade e movimento), Kling 2.6 Pro Motion Control (transferir movimento preciso de um vídeo de referência para um personagem alvo) ou Lucy Edit Restyle (reestilização leve com preservação de identidade / troca de roupa). Agrupa os padrões de prompt documentados de cada modelo para que a skill...

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,...

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 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