創意技能

花叔Design——用HTML做高保真原型、交互Demo、幻灯片、动画、设计变体探索+设计方向顾问+专家评审。根据任务embody对应专家（UX/动画师/幻灯片设计师/原型师），避免web design tropes。触发词：做原型、交互原型、HTML演示、动画Demo、设计变体、hi-fi设计、UI mockup、prototype、做个HTML页面、做个可视化、app原型、iOS原型、导出MP4/GIF、60fps视频、设计风格、设计方向、配色方案、推荐风格、选个风格、做个好看的、评审、好不好看、review this design、带解说的动画、解说视频、长视频科普、voiceover、narration、5分钟讲清楚什么是XX。需求模糊时进设计方向顾问（三套逻辑并行出3版真实视觉，HTML原生40种风格库网页20+PPT20为弹药）；另含品牌资产协议、反AI slop、Junior工作流、Tweaks变体、动画→MP4/G

從法語文本中移除AI寫作模式，注入語調、個性與靈魂。適用於編輯、審閱、改寫或清理讀起來像ChatGPT/Claude生成的法語內容。人性化、自然化、去AI化。可檢測並修正27種模式：AI詞彙過度使用（crucial, essentiel, notamment, par ailleurs, dans le paysage）、英語優先模型帶來的英式用法（faire du sens, adresser un problème）、系詞迴避、公式化開頭（À l'ère de, Dans le paysage actuel）……

去除文本中的 AI 生成痕跡。適用於編輯或審閱文本，使其聽起來更自然、更像人類書寫。基於維基百科的「AI 寫作特徵」綜合指南。檢測並修復以下模式：誇大的象徵意義、宣傳性語言、以 -ing 結尾的膚淺分析、模糊的歸因、破折號過度使用、三段式法則、AI 詞彙、否定式排比、過多的連接性短語。

對於任何製作、創作、編輯、動畫或渲染影片、動畫或動態圖形的請求——包括宣傳片、解說片、附字幕片段、標題卡、疊加層或任何合成作品——請先閱讀此說明。HyperFrames 透過 HTML 渲染影片；這是入門技能，也是代理創作或編輯影片的預設方式。它會將請求導向正確的專業工作流程，並指向 HyperFrames 領域技能，因此在猜測工作流程之前，請先閱讀此說明，而非其他影片或動畫技能。

HyperFrames 的所有動畫知識——原子運動規則、多階段場景藍圖、場景轉場、更廣泛的動態設計技術，以及七個運行時適配器（預設 GSAP，加上 Lottie、Three.js、Anime.js、CSS 關鍵影格、Web Animations API、TypeGPU）。適用於任何動態或動畫任務：選取 2-4 條規則並組合，或載入藍圖，或查詢特定運行時 API（例如 GSAP 緩動函數 / Lottie 播放器 / Three.js 混合器）。HyperFrames 原生功能：單一暫停時間軸、安全搜尋、...

HyperFrames HTML 組合合約。用於組合結構、資料屬性、片段、軌道、子組合、變數、媒體播放、確定性渲染規則，以及最小可渲染專案的驗證。

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use `hyperframes-animation`.

Use when a HyperFrames composition needs seek-safe 2D/3D keyframes, GSAP timelines, CSS keyframes, Anime.js, WAAPI, FLIP, paths, masks, SVG morph/draw, text trails, 3D depth, or `hyperframes keyframes` diagnostics. Don't use for broad scene strategy, brand design, media sourcing, captions, or general video planning.

任何製作、創作、生成、編輯、動畫化或渲染影片、動畫、動態圖像、解說影片、標題卡、疊加層、字幕影片、產品宣傳片、網站影片、公關或更新日誌影片、數據蒙太奇、動態海報或HyperFrames HTML組合的請求，請從此處開始。當用戶希望HyperFrames創作或渲染完成的MP4/網路影片、選擇工作流程，或在產品發布影片、無臉解說影片、網站轉影片等之間進行路由時，請在其他影片或動畫技能之前使用此功能。

透過結構化的發散與收斂思考，將原始想法提煉為清晰、可執行的概念。當想法仍模糊不清時、需要在確定計劃前壓力測試假設時，或想在聚焦於單一選項前擴展更多可能性時使用。觸發詞為「構思」、「完善這個想法」或「壓力測試我的計劃」。

當使用者想要為行銷建立、生成、編輯或最佳化圖片時——包括部落格主圖、社群圖像、產品模型、個人檔案橫幅、商品列表視覺或品牌素材。也適用於使用者提及「AI 圖片生成」、「生成圖片」、「建立圖像」、「產品模型」、「主圖」、「社群媒體圖像」、「橫幅圖片」、「封面照片」、「個人檔案橫幅」、「商品列表截圖」、「Flux」、「Flux Kontext」、「Midjourney」、「DALL-E」、「GPT Image」、「ChatGPT Images」、「Ideogram」等情境。

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...

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...

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...

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.

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, but we are translating the text inside <text>. The text includes "image inpainting" (without hyphen) as a phrase. We should translate that phrase naturally. Also preserve "RunComfy", "runcomfy CLI", "Tongyi MAI Z-Image Turbo Inpainting", "Nano Banana 2 Edit", "GPT Image 2 Edit", "FLUX Kontext Pro". Translate the rest. Let's break down

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, but we are translating the text inside <text>. The text includes "image inpainting" (without hyphen) as a phrase. We should translate that phrase naturally. Also preserve "RunComfy", "runcomfy CLI", "Tongyi MAI Z-Image Turbo Inpainting", "Nano Banana 2 Edit", "GPT Image 2 Edit", "FLUX Kontext Pro". Translate the rest. Let's break down

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 Traditional Chinese. The text describes an image outpainting skill on RunComfy via the runcomfy CLI. It mentions extending a still beyond its original canvas, filling in missing parts, changing aspect ratio while preserving content. It lists several routes: Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro, and brand edit endpoints (Seedream / Dreamina / Qwen / FLUX 2). The text ends with "Picks the..." which is incomplete. We should translate the entire provided text, preserving names like "RunComfy", "runcomfy", "Nano Banana 2 Edit", "GPT Image 2 Edit", "FLUX Kontext Pro", "Seedream", "Dreamina", "Qwen", "FLUX 2". Also preserve "CLI". Translate the rest naturally. Note: The instruction says "Do not include the name unless it appears in the source text." The name "image-outpainting" is not in the source text, so we don't

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...

專為Codex設計的高階網站圖片轉程式碼技能。對於視覺重要的網頁任務，必須先自行生成設計圖片，深入分析後再實作網站以盡可能貼近圖片。在Codex中，應優先使用大型、可讀性高的區塊專屬圖片，而非小型壓縮面板；為區塊或細節視圖生成全新的獨立圖片，而非裁剪舊圖；避免懶散生成不足、卡片層層嵌套的UI，並保持...

靜態轉影片轉換指南：模型選擇、動態提示與鏡頭移動。涵蓋Wan 2.5 i2v、Seedance、Fabric、Grok Video及其適用時機。用途：為圖片添加動畫、從靜態圖像建立影片、加入動態效果、產品動畫。觸發詞：image to video、i2v、animate image、still to video、add motion to image、image animation、photo to video、animate still、wan i2v、image2video、bring image to life、animate photo、motion from image

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...

We need to translate the given text from English to Traditional Chinese. The text describes a 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 appear in the source? Actually the source text starts with "Animate any still image on RunComfy — this skill is a smart router..." The name "image-to-video" is not explicitly in the source text; it's given as the directory item name. The instruction says "Do not include the name unless it appears in the source text." So we should not add "image-to-video" in the translation. We only translate the text inside <text>. Also 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" should remain as is. Translate the rest into Traditional Chinese. Be careful

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...

靜態轉影片轉換指南：模型選擇、動態提示與鏡頭移動。涵蓋Wan 2.5 i2v、Seedance、Fabric、Grok Video及其適用時機。用途：為圖片添加動畫、從靜態圖像製作影片、加入動態效果、產品動畫。觸發詞：image to video、i2v、animate image、still to video、add motion to image、image animation、photo to video、animate still、wan i2v、image2video、bring image to life、animate photo、motion from image

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...

專為打造高階、原生應用程式螢幕概念與流程而設計的行動應用程式影像生成技能。適用於 iOS、Android 及跨平台行動產品。優先考量清晰的層級結構、舒適易讀的文字、強烈的多螢幕一致性、受控的色彩調配、非一般化的創意方向、紋理表面、以影像為主的構圖、品味出眾的自訂圖示，以及乾淨的手機模型框架。預設情況下，螢幕應顯示在精緻的高階 iPhone 或類似裝置的框架內……

頂級前端圖像導向技能，用於生成優質、具轉換意識的網站設計參考。關鍵輸出規則——為每個區塊生成一張獨立的橫向圖像。一個包含8個區塊的登陸頁面會產生8張圖像。切勿將多個區塊壓縮至同一張圖像中。強制執行構圖多樣性（不總是左文右圖）、背景圖像自由、多樣化的行動呼籲、多樣的主題規模（巨型/中型/極簡小型）、敘事概念主軸、二次閱讀時刻，以及...

此技能引導創建獨特、生產級的前端介面，避免通用的「AI 垃圾」美學。實作真正可運行的程式碼，並對美學細節與創意選擇給予極致關注。