Agentspace So 스킬

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

AI 에이전트가 어디서나 무엇을 하고 있는지 확인하세요. 에이전트는 로그, 코드, 생성된 출력물, 스크린샷, 아티팩트를 계속 기록합니다. 하나의 명령으로 폴더를 실시간 URL로 전환하여, 사용자(또는 팀원)가 브라우저에서 파일 변화를 보고, 직접 편집하거나 댓글을 달 수 있습니다 — 동기화, 압축, 계정이 필요 없습니다. 워크스페이스는 24시간 익명으로 유지되며, 이메일 인증 한 번으로 영구 보관됩니다. Cloudflare에서 호스팅됩니다. "에이전트가 무엇을 하고 있는지 보여줘", "에이전트 폴더 열어줘", "이 폴더 공유해줘" 등의 명령어로 실행됩니다.

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

We need to translate the given text from English to Korean. The text describes an agent skill for generating AI music via RunComfy CLI. It mentions specific product names: RunComfy, ElevenLabs AI Music Generation, ACE Step, ACE Step 1.5, StepFun-AI. Also technical terms: CLI, 44.1 kHz stereo, vocal tracks, tag-driven composition, multilingual lyrics, audio-inpaint, audio-outpaint. Also numbers and prices. We must preserve all these. The text ends with "Picks the right..." which is incomplete. We should translate that as is. The instruction says: "Translate only the text inside <text>. Do not include the name unless it appears in the source text." The name "ai-music" is given as the name to preserve, but it does not appear in the source text, so we don't include it. Also do not add labels. We'll produce a natural Korean translation that preserves all proper nouns, URLs (none here), numbers, prices, and technical terms. Use appropriate Korean phrasing.

runcomfy-agent-skills/ai-video-generation

We need to translate the given text from English to Korean, preserving the specified name 'ai-video-generation' and other technical terms, product names, protocol names, URLs, numbers, etc. The instruction says: "Do not include the name unless it appears in the source text." The name 'ai-video-generation' does not appear in the source text, so we should not add it. Also, do not add labels like "description" or "skill name". Just translate the text inside <text>. The text describes generating AI videos on RunComfy via the runcomfy CLI, listing various models and capabilities. We need to translate naturally into Korean while keeping all proper nouns and technical terms as is. For example, "HappyHorse 1.0", "Wan-AI Wan 2-7", etc., should remain unchanged. Also, terms like "text-to-video (t2v)", "image-to-video (i2v)" should be kept as is or with Korean parentheses? Probably keep the English abbreviations. The instruction says "Preserve product

runcomfy-agent-skills/codex-pet

We need to translate the given text from English to Korean. The text describes a Codex Pet generator skill on RunComfy. It explains how to build a Codex-compatible spritesheet and json from a single reference image, and then drop it into a specific directory. It mentions the exact specifications: 1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states. It also mentions calling OpenAI GPT Image 2. We must preserve product names, protocol names, URLs, numbers, technical terms. Do not add any extra commentary or labels. The target language is Korean. The name "codex-pet" is to be preserved but not included unless it appears in source text. The source text does not include "codex-pet" as a separate word; it appears as "Codex Pet" multiple times. "Codex" is a product name, so preserve as is. "RunComfy" is a name, preserve. "OpenAI GPT Image 2" preserve. Numbers and

runcomfy-agent-skills/controlnet-pose

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...

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

We need to translate the given text from English to Korean, preserving the name 'face-swap' and other technical terms like 'runcomfy', 'Wan 2-2 Animate', 'GPT Image 2 Edit', 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 'face-swap' appears in the source text? Actually the source text starts with "Swap a face / character..." so 'face-swap' is not directly in the text; it's the name of the skill. But the instruction says "Do not include the name unless it appears in the source text." The name 'face-swap' does not appear in the source text. So we should not add it. However, the directory item type is 'agent skill' and the name is given as 'face-swap' but we are to translate only the text inside <text>. So we just translate the description. Let's translate carefully. The text: "Swap a face / character into video or images

skills/find-skills

여러 주요 레지스트리(skills.sh, clawhub.ai, GitHub)를 한 번에 검색하여 에이전트 스킬을 발견, 검증, 설치합니다. 각 보드를 고유 지표(설치 수/별점)로 표시하고, 보드별 상위 항목을 제시하며, 상위 후보의 실제 SKILL.md를 보안 스캔하여 위험 패턴을 탐지하고, 이미 설치된 항목을 표시합니다. 사용자가 "X를 어떻게 하죠", "X를 위한 스킬 찾아줘", "X를 하는 스킬 있나요", "X를 위해 어떤 스킬을 설치해야 하나요"라고 묻거나 에이전트를 확장하려 할 때 사용합니다.

runcomfy-agent-skills/flux-2-klein

RunComfy에서 Flux 2 Klein(Black Forest Labs의 Flux 2 경량 고속 변형)으로 이미지를 생성합니다. 모델의 문서화된 프롬프트 패턴이 함께 제공되어, 동일 모델에 단순 프롬프트를 사용하는 것보다 더 정교한 결과를 얻을 수 있습니다. Flux 2 Klein의 장점(서브초 지연 시간, 다중 참조 브랜드 스타일링, 선언적 주제 우선 프롬프트), 단계 수 전략(빠른 반복 시 4~8단계, 정교화 시 약 25단계), 9B 대 4B 변형 간의 트레이드오프, 그리고 Flux 2 Pro로 전환해야 하는 경우 등을 설명합니다.

runcomfy-agent-skills/flux-kontext

RunComfy에서 Flux 1 Kontext Pro(Black Forest Labs의 정밀 로컬 이미지 편집 모델)로 이미지를 편집하세요 — 이 스킬은 모델의 문서화된 프롬프트 패턴과 함께 제공되어, 동일한 모델에 단순 프롬프트를 사용하는 것보다 더 선명한 결과를 얻을 수 있습니다. Flux Kontext의 강점(단일 참조로 정밀한 로컬 편집, 강력한 프롬프트 제어, 일관된 고품질 출력), 스키마(단일 이미지 + 프롬프트), 그리고 Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein으로 전환해야 하는 경우를 설명합니다. 호출...

runcomfy-agent-skills/gpt-image-2

RunComfy에서 OpenAI GPT Image 2(ChatGPT Images 2.0)로 이미지를 생성하고 편집합니다. GPT Image 2의 강점(내장 텍스트, 로고, 다국어 타이포그래피, 명령 정밀도),

runcomfy-agent-skills/gpt-image-edit

We need to translate the given text from English to Korean, preserving the name "gpt-image-edit" as instructed. The text describes an agent skill for editing images using OpenAI GPT Image 2 on RunComfy. We must not add any extra commentary, labels, or formatting. Just the translation of the text inside <text>. The name "gpt-image-edit" is not in the source text, so we don't include it. The source text mentions "GPT Image 2", "ChatGPT Images 2.0", "RunComfy", "Nano Banana Edit", "Flux Kontext", "GPT Image 2 t2i" - these should be preserved as is. Also "preservation language" might be a term, keep as is or translate? It says "preservation language" - likely a feature name. I'll keep it as "preservation language" or translate? The instruction says preserve technical terms. I'll keep it as "preservation language" but in Korean context, maybe it's better to translate? The instruction says

runcomfy-agent-skills/happyhorse-1-0

We need to translate the given text from English to Korean. The text describes an agent skill for generating text-to-video with HappyHorse 1.0 on RunComfy. It mentions strengths, schema, routing alternatives, and CLI command. The instruction says to preserve product names, protocol names, URLs, numbers, technical terms. So "HappyHorse 1.0", "RunComfy", "Artificial Analysis Video Arena", "1080p", "Wan 2.7", "Seedance 2", "LTX 2", "runcomfy run happyhorse/happyhorse-1-0/text-to-video", "CLI", "happyhorse", "happy horse" should remain as is. Also preserve the name "happyhorse-1-0" if it appears, but it's not in the text except in the CLI path. The text inside <text> is what we translate. We must not add labels or extra commentary. Just the translation. Let's translate sentence by sentence: "Generate text-to-video with HappyHorse

runcomfy-agent-skills/image-edit

RunComfy에서 이미지 편집 — 이 스킬은 사용자의 의도를 RunComfy 카탈로그 내 적절한 편집 모델에 매칭하는 스마트 라우터입니다. Nano Banana Edit(최대 20개 배치, 정체성 보존 기본값), OpenAI GPT Image 2 Edit(다국어 이미지 내 텍스트 재작성, 다중 참조 구성, 레이아웃 정밀도), Flux Kontext Pro(단일 참조 고충실도 로컬 편집), 또는 Z-Image Turbo Inpaint(마스크 기반 정밀 영역 편집)를 선택합니다. 각 모델의 문서화된 프롬프트 패턴을 번들로 제공하여 스킬이...

runcomfy-agent-skills/image-inpainting

We need to translate the given English text into Korean, preserving the specified names and technical terms. The text describes a mask-driven image inpainting skill on RunComfy via the runcomfy CLI. It mentions routes to specific models: Tongyi MAI Z-Image Turbo Inpainting, Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro. Also mentions use cases: object removal, watermark removal, region replacement, blemish cleanup, etc. We must not include the name "image-inpainting" unless it appears in the source text. It does appear in the first sentence: "Mask-driven image inpainting on RunComfy..." So we should translate that part including the name? The instruction says: "Do not include the name unless it appears in the source text." It does appear, so we include it in translation. But careful: "Name to preserve: image-inpainting" means we should preserve that exact term in the translation? The instruction says "Preserve product names, protocol names, URLs, numbers, and technical terms

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 Korean. 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 says "Animate any still image on RunComfy — this skill is a smart router..." The skill name is not explicitly given as "image-to-video" in the text; the directory item type is "agent skill" and the name to preserve is "image-to-video". But the instruction says "Do not include the name unless it appears in the source text." The name "image-to-video" does not appear in the source text. So we should not add it. We just translate the text inside <text>. The 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 (A

runcomfy-agent-skills/kling-3-0

RunComfy에서의 Kling 3.0 비디오 생성. Kling 3.0(또는 Kling V3.0)은 Kuaishou Technology의 3세대 멀티샷 비디오 모델로, 기본 동기화 오디오와 샷 간 일관된 캐릭터 정체성을 제공합니다. 이 스킬은 세 가지 렌더링 등급(Standard, Pro, 4K)과 두 가지 모드(텍스트-투-비디오, 이미지-투-비디오)에 걸친 모든 6개의 Kling 3.0 엔드포인트를 다룹니다. 로컬 RunComfy CLI를 통해 runcomfy run kling/kling-3.0/ / 을 호출합니다. "kling", "kling 3.0", "kling v3", "kling pro" 등에서 트리거됩니다.

runcomfy-agent-skills/lipsync

We need to translate the given English text into Korean. The text describes a skill for lip-syncing a face to an audio track using RunComfy CLI, mentioning various services: ByteDance OmniHuman, Sync Labs sync v2/Pro, Kling lipsync, Creatify lipsync. The skill picks the right endpoint based on user intent. We must preserve product names, protocol names, URLs, numbers, technical terms. No extra commentary. The name "lipsync" is not in the source 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" is given as the item name, but the source text includes "Lip-sync" as a verb. We should translate that as part of the text. Also preserve "RunComfy", "runcomfy CLI", "ByteDance OmniHuman", "Sync Labs sync v2 / Pro", "Kling lipsync", "Creatify lipsync". Translate

runcomfy-agent-skills/nano-banana-2

Google Nano Banana 2(Gemini 계열 플래시 등급 텍스트-투-이미지)로 RunComfy에서 이미지를 생성합니다. 이 스킬은 모델의 문서화된 프롬프트 패턴과 함께 제공되어, 동일한 모델에 단순 프롬프트를 사용하는 것보다 더 정교한 출력을 얻을 수 있습니다. Nano Banana 2의 강점(빠른 반복, 이미지 내 타이포그래피 렌더링, 예측 가능한 프레임 구성, 선택적 웹 기반 컨텍스트), 해상도 등급별 가격, 안전 허용 범위 조절, 그리고 Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream으로 전환해야 하는 경우를 설명합니다.

runcomfy-agent-skills/nano-banana-edit

Edit images with Google Nano Banana 2 (image-to-image edit endpoint) on 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. Calls `runcomfy run google/nano-banana-2/edit` through the local RunComfy CLI. Triggers on "nano banana edit", "edit with nano banana", "image edit nano...

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

We need to translate the given English text into Korean. The text describes a CLI tool called runcomfy-cli. The instruction says to preserve the name "runcomfy-cli" but only if it appears in the source text. The source text mentions "runcomfy" and "runcomfy CLI" but not "runcomfy-cli" exactly. However, the directory item type is "agent skill" and the name to preserve is "runcomfy-cli". The instruction says "Do not include the name unless it appears in the source text." The source text has "runcomfy" and "runcomfy CLI", not "runcomfy-cli". So we should not add "runcomfy-cli" if it's not there. But the instruction says "Name to preserve: runcomfy-cli" - that might mean we should keep that name if it appears, but it doesn't. So we just translate the text as is. We need to translate the description accurately, preserving product names, protocol names, URLs, numbers, technical

runcomfy-agent-skills/seedance-v2

ByteDance Seedance 2.0 Pro를 사용하여 RunComfy에서 시네마틱 단편 영상을 생성

runcomfy-agent-skills/video-edit

RunComfy에서 기존 비디오 편집 — 이 스킬은 사용자의 의도를 RunComfy 카탈로그 내 적절한 편집 모델에 매칭하는 스마트 라우터입니다. Wan 2.7 Edit-Video (일반 리스타일 / 배경 교체 / 패키징 교체, 아이덴티티 및 모션 보존), Kling 2.6 Pro Motion Control (참조 비디오의 정밀한 모션을 대상 캐릭터로 전송), 또는 Lucy Edit Restyle (경량 아이덴티티 안정 리스타일 / 의상 교체)을 선택합니다. 각 모델의 문서화된 프롬프팅 패턴을 번들로 제공하여 스킬이...

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,...