Agentspace So Skills

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...

Sehen Sie, was Ihr KI-Agent tut, von überall aus. Der Agent schreibt kontinuierlich – Logs, Code, generierte Ausgaben, Screenshots, Artefakte. Ein Befehl verwandelt den Ordner in eine Live-URL, die Sie (oder ein Teammitglied) in jedem Browser öffnen können, um Dateien beim Entwickeln zu beobachten, direkt zu bearbeiten oder zu kommentieren – kein Synchronisieren, kein Zippen, kein Konto. Arbeitsbereiche bleiben 24 Stunden anonym live; eine E-Mail-Anmeldung macht sie dauerhaft. Gehostet auf Cloudflare. Auslöser: „Zeig mir, was der Agent tut“, „Öffne den Ordner des Agenten“, „Teile diesen Ordner“, …

We need to translate the given English text into German, preserving the specified name "ai-avatar-video" and other technical terms. The instruction says: "Do not include the name unless it appears in the source text." The name "ai-avatar-video" does not appear in the source text, so we should not include it. Also, preserve product names, protocol names, URLs, numbers, technical terms. So "RunComfy", "runcomfy CLI", "ByteDance OmniHuman", "Wan-AI Wan 2-7", "HappyHorse 1.0", "Seedance v2 Pro" should remain as is. Also "UGC voiceover", "virtual presenter", "dubbed product demo", "lip-synced" are technical terms; translate "UGC" (user-generated content) as "UGC" or "nutzergenerierte Inhalte"? Probably keep "UGC" as it's an acronym. "voiceover" -> "Voiceover" or "Sprachaufnahme"? "virtual presenter

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 German. The text describes a Codex Pet generator skill. We must preserve the name "codex-pet" but it's not in the text, so ignore. Preserve product names: Codex, RunComfy, OpenAI GPT Image 2. Preserve technical terms: spritesheet.webp, pet.json, ${CODEX_HOME:-$HOME/.codex}/pets/ /, 1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states, idle, running-right, running-left, waving, jumping, failed, waiting, running, review. Also preserve URLs? None. Numbers and technical terms. Translate the rest naturally. The text is a description of what the skill does. Output only the translation, no extra commentary. Let me translate: "Codex Pet Generator auf RunComfy. Erstelle ein Codex-kompatibles Codex Pet Spritesheet.webp + pet.json aus einem einzelnen Referenzbild,

We need to translate the given English text into German. The text describes a pose-conditioned generation system on RunComfy via CLI, mentioning various routes: Kling 2-6 Motion Control Pro/Standard, community Wan 2-2 Animate, and Z-Image Turbo ControlNet LoRA. It also mentions picking the right route based on video vs still and stylized vs photoreal. The instruction says to preserve product names, protocol names, URLs, numbers, technical terms. So we keep "RunComfy", "runcomfy CLI", "Kling 2-6 Motion Control Pro / Standard", "Wan 2-2 Animate", "Z-Image Turbo ControlNet LoRA", "OpenPose / DWPose / canny / depth control image". Also "pose-conditioned" is a technical term, but we can translate it as "posengesteuert" or "pose-basiert"? The instruction says preserve technical terms, but "pose-conditioned" is a common term in AI. However, the target language is German

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...

We need to translate the given text from English to German, preserving the name 'face-swap' and other technical terms like 'runcomfy', 'Wan 2-2 Animate', 'GPT Image 2 Edit', 'Nano Banana Edit', 'Flux Kontext', 'Kling 2-6 Motion Control Pro'. Also preserve URLs, numbers, etc. The instruction says: "Do not include the name unless it appears in the source text." The name 'face-swap' appears in the source? Actually the source text starts with "Swap a face / character..." but the name to preserve is 'face-swap'. The source does not contain 'face-swap' as a word; it says "Swap a face". But the directory item type is agent skill and name is 'face-swap'. The instruction says "Translate only the text inside <text>. Do not include the name unless it appears in the source text." So we should not add 'face-swap' if it's not in the source. The source text is: "Swap a

Entdecke, prüfe und installiere Agenten-Skills, indem du gleichzeitig in allen wichtigen Registries suchst – skills.sh, clawhub.ai und GitHub – und jedes Board mit seiner eigenen nativen Metrik (Installationen / Sterne) darstellst, den Top-Eintrag pro Board anzeigst, die echten SKILL.md der Top-Kandidaten auf riskante Muster sicherheitsprüfst und bereits installierte kennzeichnest. Verwende dies, wenn der Benutzer fragt: „Wie mache ich X“, „Finde einen Skill für X“, „Gibt es einen Skill, der …“, „Welchen Skill sollte ich für … installieren“ oder den Agenten mit einem … erweitern möchte.

Generiere Bilder mit Flux 2 Klein (Black Forest Labs' destillierte schnelle Variante von Flux 2) auf RunComfy – gebündelt mit den dokumentierten Prompting-Mustern des Modells, sodass der Skill schärfere Ergebnisse liefert als naives Prompting mit demselben Modell. Dokumentiert die Stärken von Flux 2 Klein (Latenz unter einer Sekunde, Multi-Referenz-Markenstyling, deklarative Subjekt-zuerst-Prompts), die Schrittanzahl-Strategie (4–8 für schnelle Iteration, ~25 für Verfeinerung), den Kompromiss zwischen der 9B- und 4B-Variante sowie die Entscheidung, wann zu Flux 2 Pro /... weitergeleitet werden sollte.

Bilder mit Flux 1 Kontext Pro (Black Forest Labs' präzises lokales Bildbearbeitungsmodell) auf RunComfy bearbeiten – gebündelt mit den dokumentierten Prompting-Mustern des Modells, sodass die Fertigkeit schärfere Ergebnisse liefert als naives Prompting mit demselben Modell. Dokumentiert die Stärken von Flux Kontext (präzise lokale Bearbeitungen mit einer Referenz, starke Prompt-Kontrolle, konsistente hochtreue Ausgaben), das Schema (einzelnes Bild + Prompt) und wann stattdessen zu Nano Banana Edit / GPT Image 2 Edit / Flux 2 Klein weitergeleitet werden sollte. Ruft...

We need to translate the given text from English to German, preserving the name "gpt-image-2" 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 "gpt-image-2" appears in the source text, so it should be preserved. Also preserve "RunComfy", "Flux 2", "Nano Banana Pro", "Seedream", "CLI", "openai/gpt-image-2/text-to-image", "/edit", etc. The text is a description of an agent skill. Translate naturally to German. Let's break down the source: "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

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 English text into German, preserving the name "happyhorse-1-0" and other technical terms. The text describes a skill for generating text-to-video with HappyHorse 1.0 on RunComfy. It mentions strengths, schema, alternatives, and CLI command. We must not add any extra commentary or labels. Just translate the text inside <text> tags. Let me translate: "Generate text-to-video with HappyHorse 1.0 on RunComfy." -> "Generieren Sie Text-zu-Video mit HappyHorse 1.0 auf RunComfy." "Documents HappyHorse 1.0's strengths (#1 on Artificial Analysis Video Arena, native 1080p with in-pass synchronized audio, multi-shot character consistency, 6-language prompt support), the duration / aspect-ratio / resolution schema, and when to route to Wan 2.7 / Seedance 2 / LTX 2 instead." -> "Dokumentiert die Stärken von HappyHorse 1.0

Bilder auf RunComfy bearbeiten – diese Fertigkeit ist ein intelligenter Router, der die Absicht des Nutzers mit dem passenden Bearbeitungsmodell im RunComfy-Katalog abgleicht. Wählt Nano Banana Edit (Stapelverarbeitung bis zu 20, standardmäßig identitätserhaltend), OpenAI GPT Image 2 Edit (mehrsprachige Textumschreibung im Bild, Multi-Referenz-Komposition, Layout-Präzision), Flux Kontext Pro (Einzel-Referenz, hochgetreue lokale Bearbeitung) oder Z-Image Turbo Inpaint (maskengesteuerte präzise Bereichsbearbeitung). Bündelt die dokumentierten Eingabeaufforderungsmuster jedes Modells, sodass die Fertigkeit...

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...

Animieren Sie jedes Standbild auf RunComfy – dieser Skill ist ein intelligenter Router, der die Absicht des Nutzers mit dem passenden i2v-Modell im RunComfy-Katalog abgleicht. Wählt HappyHorse 1.0 I2V (Arena #1, nativer

Kling 3.0 Videogenerierung auf RunComfy. Kling 3.0 (auch Kling V3.0 genannt) ist das Multi-Shot-Videomodell der dritten Generation von Kuaishou Technology mit nativem synchronisiertem Audio und konsistenter Charakteridentität über mehrere Aufnahmen hinweg. Diese Fähigkeit deckt alle sechs Kling 3.0-Endpunkte ab, die drei Rendering-Stufen (Standard, Pro, 4K) und zwei Modi (Text-zu-Video, Bild-zu-Video) umfassen. Aufrufe runcomfy run kling/kling-3.0/ / über die lokale RunComfy-CLI. Auslöser bei "kling", "kling 3.0", "kling v3", "kling pro",...

We need to translate the given English text into German, 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: "Do 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 as "Lippensynchronisation" or similar? But the instruction says "Preserve product names, protocol names, URLs, numbers, and technical terms." "lipsync" is a technical term? It's a skill name. The instruction says "Name to preserve: lipsync". So we should preserve the word "lipsync" as is when it appears. In the source, it's "Lip-sync" (capitalized, hyphenated). Should we keep that exact form? Probably

Generieren Sie Bilder mit Google Nano Banana 2 (Gemini-Familie Flash-Stufe Text-zu-Bild) auf RunComfy – gebündelt mit den dokumentierten Prompt-Mustern des Modells, sodass die Fertigkeit schärfere Ergebnisse liefert als naives Prompting mit demselben Modell. Dokumentiert die Stärken von Nano Banana 2 (schnelle Iteration, In-Bild-Typografie-Rendering, vorhersagbare Bildkomposition, optionaler webgestützter Kontext), die Preisgestaltung nach Auflösungsstufen, den Sicherheitstoleranz-Regler und wann an Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream weitergeleitet werden sollte...

We need to translate the given text from English to German, preserving the name "nano-banana-edit" and other technical terms. The text describes an agent skill for editing images with Google Nano Banana 2 on RunComfy. It mentions strengths, schema, routing alternatives, and CLI command. We must not add any extra commentary or labels. Just translate the text inside <text> tags. Let's translate carefully: "Edit images with Google Nano Banana 2 (image-to-image edit endpoint) on RunComfy." -> "Bearbeiten Sie Bilder mit Google Nano Banana 2 (Bild-zu-Bild-Bearbeitungs-Endpunkt) auf RunComfy." "Documents Nano Banana Edit's strengths (preserve subject identity, swap background, localize edits with spatial language, multi-image batch edits up to 20 inputs), the schema, and when to route to GPT Image 2 edit / Flux Kontext / Nano Banana 2 t2i instead." -> "Dokumentiert die Stärken von Nano Banana Edit (Subjektidentität bewahren,

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 German. 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. Preserve: "seedance-v2" (name to preserve), but note instruction: "Do not include the name unless it appears in the source text." The name "seedance-v2" appears in the source text as part of the CLI command "bytedance/seedance-v2/pro". So we should preserve that exact string. Also preserve "ByteDance Seedance 2.0 Pro", "RunComfy", "HappyHorse 1.0", "Wan 2.7", "Kling", "runcomfy run bytedance/seedance-v2/pro", "seedance", "seedance 2", "seedance v2", "seedance..." (the last is truncated). Also preserve numbers, URLs (none), technical terms.

Vorhandenes Video auf RunComfy bearbeiten – diese Fähigkeit ist ein intelligenter Router, der die Absicht des Benutzers mit dem richtigen Bearbeitungsmodell im RunComfy-Katalog abgleicht. Wählt Wan 2.7 Edit-Video (allgemeines Restyling / Hintergrundtausch / Verpackungstausch, Identitäts- und Bewegungserhaltung), Kling 2.6 Pro Motion Control (präzise Bewegungsübertragung von einem Referenzvideo auf eine Zielperson) oder Lucy Edit Restyle (leichtgewichtiges, identitätsstabiles Restyling / Outfitwechsel). Bündelt die dokumentierten Eingabeaufforderungsmuster jedes Modells, sodass die Fähigkeit...

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,...

We need to translate the given text from English to German. 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. "9:16", "16:9" are numbers/aspect ratios. "hero delivery" might be a term? Possibly keep as is or translate? "hero delivery" likely refers to main subject delivery

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...