Agentspace So技能

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

隨時隨地查看你的 AI 代理正在做什麼。代理會持續記錄——日誌、程式碼、生成輸出、螢幕截圖、成品。一個指令就能將資料夾轉為即時網址，你（或團隊成員）可在任何瀏覽器中開啟，觀看檔案演變、就地編輯或留言——無需同步、壓縮或帳號。工作區匿名保持 24 小時即時狀態；透過一個電子郵件聲明即可永久保留。託管於 Cloudflare。觸發指令如「顯示代理在做什麼」、「打開代理的資料夾」、「分享此資料夾」……

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

我們要將提供的英文描述翻譯成繁體中文。注意事項：保留產品名稱、協議名稱、URL、數字和技術術語。不要添加聲明、解釋、Markdown、項目符號、鏈接、標籤、前綴或額外評論。目標語言是繁體中文。目錄項類型是agent skill，名稱是ai-music，但不要包含名稱除非它在源文本中出現。源文本中沒有出現ai-music，所以不用管。 翻譯內容：描述RunComfy通過runcomfy CLI生成AI音樂，是一個智能路由器，路由到ElevenLabs AI Music Generation和ACE Step / ACE Step 1.5等。需要準確翻譯，保留數字、單位、價格等。注意「~27× cheaper」要保留「約27倍便宜」或類似表達。還有「audio-inpaint」和「audio-outpaint」是技術術語，保留英文或翻譯？通常保留英文或加上中文解釋，但指示說保留技術術語，所以可以保留英文或

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

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

我們需要將提供的英文文本翻譯成繁體中文。注意要求：保留產品名稱、協議名稱、URL、數字和技術術語。不要添加聲明、解釋、Markdown、項目符號、鏈接、標籤、前綴或額外評論。只翻譯<text>內的內容，且不要包含名稱（除非名稱出現在源文本中）。源文本中提到了"face-swap"但不在<text>內，所以不翻譯。另外注意"RunComfy"、"runcomfy"、"Wan 2-2 Animate"、"GPT Image 2 Edit"、"Nano Banana Edit"、"Flux Kontext"、"Kling 2-6 Motion Control Pro"這些都是產品或技術名稱，應保留不翻譯。其他部分翻譯成繁體中文。 文本內容：描述了一個agent skill，通過runcomfy CLI在RunComfy上進行臉部/角色交換到視頻或圖像。然後列舉了幾個模型/工具。最後一句"Picks the right model for..."不完整

skills/find-skills

一次搜遍所有主要註冊庫——skills.sh、clawhub.ai 和 GitHub——來探索、審核並安裝代理技能，以各平台原生指標（安裝數/星數）呈現每個看板，並顯示每個看板的最佳條目，對頂尖候選者的實際 SKILL.md 進行安全掃描以偵測風險模式，同時標記已安裝的技能。當使用者詢問「我該如何做 X」、「找一個能做 X 的技能」、「有沒有技能可以……」、「我該安裝什麼技能來……」，或想要擴展代理功能時使用。

runcomfy-agent-skills/flux-2-klein

在 RunComfy 上使用 Flux 2 Klein（Black Forest Labs 的 Flux 2 蒸餾快速變體）生成圖像 — 內建該模型的提示模式文檔，使技能比直接對同一模型進行簡單提示能獲得更高品質的輸出。記錄了 Flux 2 Klein 的優勢（亞秒級延遲、多參考品牌風格、宣告式主體優先提示）、步數策略（快速迭代用 4–8 步，精修用約 25 步）、9B 與 4B 變體的取捨，以及何時應轉向 Flux 2 Pro /...

runcomfy-agent-skills/flux-kontext

在 RunComfy 上使用 Flux 1 Kontext Pro（Black Forest Labs 的精確局部圖像編輯模型）編輯圖片——該技能內建了模型文檔中的提示模式，因此相較於對同一模型進行簡單提示，能獲得更精準的輸出。記錄了 Flux Kontext 的優勢（單一參考精確局部編輯、強大的提示控制、一致的高保真輸出）、架構（單一圖片 + 提示），以及何時應改用 Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein。調用...

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

在 RunComfy 上使用 HappyHorse 1.0 生成文字轉影片

runcomfy-agent-skills/image-edit

在 RunComfy 上編輯圖片——此技能為智能路由器，能將用戶意圖匹配至 RunComfy 目錄中的正確編輯模型。可選用 Nano Banana Edit（批次最多 20 張，預設保留身份）、OpenAI GPT Image 2 Edit（多語言圖內文字重寫、多參考合成、佈局精準）、Flux Kontext Pro（單參考高保真局部編輯）或 Z-Image Turbo Inpaint（遮罩驅動精確區域編輯）。整合各模型的提示模式文檔，使技能能...

runcomfy-agent-skills/image-inpainting

We need to translate the given text from English to Traditional Chinese. The text describes an agent skill for image inpainting. We must preserve product names, protocol names, URLs, numbers, technical terms. The name "image-inpainting" is to be preserved but not included unless it appears in source text. The source text does not include the name "image-inpainting" as a standalone; it appears as part of "image inpainting" in the first sentence. But the instruction says "Do not include the name unless it appears in the source text." The name "image-inpainting" is the directory item type name, but it's not in the source text. So we should not add it. However, the source text has "image inpainting" (without hyphen) which is a common term. We should translate that as "影像修補" or similar. But careful: "image inpainting" is a technical term; we can translate it. 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

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, Wan 2.7 with `audio_url` for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal animation from image + reference video + reference audio. Bundles each model's documented prompting patterns so the caller gets sharper output without burning...

runcomfy-agent-skills/kling-3-0

在 RunComfy 上進行 Kling 3.0 影片生成。Kling 3.0（也稱為 Kling V3.0）是快手科技第三代多鏡頭影片模型，具備原生同步音訊及跨鏡頭一致的角色身份。此技能涵蓋所有六個 Kling 3.0 端點，橫跨三種渲染層級（標準、專業、4K）與兩種模式（文字轉影片、圖片轉影片）。透過本地 RunComfy CLI 執行 runcomfy run kling/kling-3.0/ /。觸發詞為「kling」、「kling 3.0」、「kling v3」、「kling pro」等。

runcomfy-agent-skills/lipsync

Lip-sync a face to a specific audio track on RunComfy via the `runcomfy` CLI. Routes across ByteDance OmniHuman (audio-driven full-body avatar from a portrait + audio), Sync Labs sync v2 / Pro (state-of-the-art mouth sync onto a video), Kling lipsync (audio-to- video and text-to-video with synced speech), and Creatify lipsync. The skill picks the right endpoint for the user's actual intent — portrait still + audio (avatar-style), source video + audio (mouth- swap on existing footage), or...

runcomfy-agent-skills/nano-banana-2

使用 RunComfy 上的 Google Nano Banana 2（Gemini 系列 flash 層級文字轉圖像）生成圖片——內建該模型的提示模式，使技能輸出比直接對同一模型進行簡單提示更為精準。記錄 Nano Banana 2 的優勢（快速迭代、圖像內文字渲染、可預測構圖、可選網路接地上下文）、解析度層級定價、安全容忍度調節，以及何時轉向 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 Traditional Chinese. The text describes an agent skill for editing images using Google Nano Banana 2 on RunComfy. It mentions strengths, schema, routing alternatives, and CLI command. The name "nano-banana-edit" is preserved as per instruction, but it's not in the source text. The source text has "Nano Banana Edit" etc. We should preserve product names like "Google Nano Banana 2", "RunComfy", "GPT Image 2 edit", "Flux Kontext", "Nano Banana 2 t2i", "runcomfy run google/nano-banana-2/edit", "nano banana edit", "edit with nano banana", "image edit nano...". Also preserve numbers like 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 (preserve subject identity, swap background, localize edits with spatial language, multi-image batch edits up to

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 text from English to Traditional Chinese. 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 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 CLI" (with space) not "runcomfy-cli". But the name to preserve is "runcomfy-cli". I think we should preserve the exact name as given, but only if it appears. Since it doesn't appear, we should not add it. However, the instruction says "Name to preserve: runcomfy-cli" and "Do not include the name unless it appears in the source text." So we should not add it. But the source text has

runcomfy-agent-skills/seedance-v2

使用 ByteDance Seedance 2.0 Pro 在 RunComfy 上生成電影級短影片。說明 Seedance 2.0 Pro 的優勢（多模

runcomfy-agent-skills/video-edit

在 RunComfy 上編輯現有影片 — 此技能為智慧路由器，可將使用者意圖匹配至 RunComfy 目錄中的正確編輯模型。選用 Wan 2.7 Edit-Video（通用風格重製 / 背景替換 / 包裝替換，保留身份與動作）、Kling 2.6 Pro Motion Control（將參考影片的精確動作轉移至目標角色），或 Lucy Edit Restyle（輕量級身份穩定風格重製 / 服裝替換）。整合各模型的提示模式，使技能...

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,...