Communitygithub.com

hoodini/ai-agents-skills

Yuval 的全合一 AI 影片管道。將一個想法或腳本轉變為完成、符合品牌的 MP4,通過協調 HyperFrames、Lottie、ManimCE 和轉錄→批准字幕流程,全部包裝在 YUV.AI Neon Phoenix 品牌中。

ai-agents-skills 是什麼?

這個技能是一個全方位的 AI 影片製作指揮家,專為 Yuval 的 YUV.AI 品牌設計。它能將任何想法、腳本或文字描述,自動規劃成完整的影片敘事,並根據每個「節拍」(如概念解釋、品牌動畫、數學展示)路由到最合適的引擎:HyperFrames 負責最終渲染,Lottie 提供品牌動態圖形,ManimCE 用於數學和神經網路動畫,GSAP 處理文字和過場效果,Three.js 用於 3D 空間場景。技能的核心原則是「可搜尋的適配器 vs. 預渲染素材」:任何能以時間驅動的視覺效果(如 GSAP、Lottie)都在渲染時即時生成,而無法被搜尋的(如 Manim 動畫)則先離線渲染成剪輯再嵌入。最終,所有元素會被整合到一個統一的 HyperFrames 合成中,套用 YUV.AI Neon Phoenix 品牌規範(粉紅 #FF1464、青藍 #00E5FF、黑白色調、Anton+Inter+JetBrains Mono 字體),並自動進行自我驗證(lint、validate、跨時間軸抽檢 5 幀)後輸出為 16:9 或 9:16 的 MP4 影片。它支援從純文字指令觸發,例如「製作一個關於神經網路的影片」、「把這個解說變成影片」、「promo」、「reel」,甚至希伯來語指令。依賴環境包括 Node 22+、FFmpeg、Python 3.11+(Manim 安裝需使用 `py` 而非 `python`),若 Manim 不可用則會優雅地跳過數學相關節拍,而不會導致整個影片失敗。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/hoodini/ai-agents-skills/tree/HEAD/skills/yuv-video-director

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

yuv-video-director

YUV.AI 影片的指揮。你(代理)決定每個節拍需要什麼,將其路由到正確的引擎,將所有內容組合成一個 HyperFrames 組合,包裹上 YUV.AI Neon Phoenix 品牌,自我驗證,並渲染為 MP4。此技能是路由器和工作參考實作;僅在該引擎啟用時載入參考檔案。

設計真相來源: yuv-design-system 技能(Neon 模式 — 粉紅色 #FF1464、青色 #00E5FF、深黑/白色、Anton+Inter+JetBrains Mono、神經網路鳳凰圖案)。其影片形式為 frame.md — 請參閱 references/frame-md.md。捆綁模板:assets/FRAME.md。將其放入專案根目錄;HyperFrames 會讀取它。

唯一法則(決定一切)

HyperFrames 透過在無頭 Chrome → FFmpeg 中尋找每個影格來渲染(frameIndex = floor(t·fps),相同輸入 → 相同輸出)。因此,每個視覺元素分為兩類:

模式運行方式…引擎規則
即時可尋找適配器在渲染內部,每個影格驅動至時間 tGSAP、Lottie(window.__hfLottie)、Three.js、由 GSAP 代理 onUpdate 驅動的畫布必須是時鐘驅動 — 無 Date.now()、Math.random()(種子化 mulberry32)、setTimeout 或 .play()
預渲染資產離線,輸出檔案,作為剪輯匯入ManimCE(Python→MP4/alpha)、TTS 音訊、背景移除先渲染,然後作為 <video>/資產剪輯放入

如果可以尋找,就是適配器。如果不能,就預渲染。 Manim 始終是預渲染剪輯 — 它有自己的渲染器並在 Python 中執行;永遠不能成為即時適配器。

將每個節拍路由到引擎

"以 TEASER/宣傳片解釋 X(FOMO、懸念、快速)"              → references/teaser-explainer.md(公式)
"解釋概念 / 數學 / 神經網路 / 演算法 / 訓練"  → ManimCE   (預渲染剪輯 — 為宣傳片切割成 BURSTS)
"品牌動態:標誌閃現 · 統計數據揭示 · 圖示彈出 · 脈衝"        → Lottie    (即時,lottie-web)
"動態字幕 · 標題 · 揭示 · 轉場 · 數據標註"  → GSAP      (即時)← 預設
"3D / 空間"                                                       → Three.js  (即時)   (不使用 Babylon)
語音 → 字幕                                                    → 轉錄 + 核准網頁應用(參閱 video-edit 技能)
未提供旁白                                                → TTS(Kokoro:npx hyperframes tts)
品牌顏色 / 字型 / 圖案                                        → frame.md  (前端提取)

GSAP 是文字/動態的可靠預設項。對於設計的品牌圖形,使用 Lottie;對於解釋想法,使用 Manim。

工作流程

  1. 規劃節拍。 敘事弧線 + 每個節拍所需的引擎。選擇 16:9 和/或 9:16。
  2. 設定品牌。 確保專案根目錄中有 FRAME.md(複製 assets/FRAME.md)。所有顏色/字型/圖案都來自它 — 絕不發明。每個影片的三個品牌必備要素(參閱 references/brand-kit.md + references/cinematic.md):在揭示和結束卡上使用真實鳳凰標誌(assets/logo-phoenix.png)、真實特色 Lottie(生成一個 — assets/lottie-burst-generator.py),以及連結結束卡(標誌 + "LET'S FLY HIGH" + 完整連結集 + CTA)。對於宣傳片/社交節奏,參閱 references/editing.md;對於心理/懸念/FOMO 剪輯,參閱 references/cinematic.md。
  3. 首先預渲染資產節拍(使它們作為剪輯存在):
    • Manim → references/manim.md + assets/manim-scene-template.py。執行 py -m manim render -qh --fps 30 scene.py SceneName,將 MP4 複製到 assets/。
    • 字幕/TTS → 重複使用 video-edit 技能(轉錄 → 核准網頁應用 → 同步)和 npx hyperframes tts。
  4. 搭建框架 + 組合。 執行 npx hyperframes init <slug> --non-interactive。編寫 index.html(hyperframes 技能是合約)。使用:
    • 可尋找的神經網路場背景 → assets/neural-net-field.js
    • Lottie 品牌方式 → references/lottie.md + assets/neural-pulse.json
    • Manim 渲染作為 <video class="clip" muted playsinline> 主體剪輯
    • 每個場景的 GSAP 入場、邊界的霓虹閃光轉場、僅在最終場景淡出
    • 對於宣傳片 / 社交節奏(快速硬剪輯、動態文字撞擊、鉤子蒙太奇、故障/色度刺擊) → references/editing.md — 像製片人而非幻燈片一樣剪輯
  5. 自我驗證(閘門)。 references/gates.md:執行 npx hyperframes lint(0 錯誤) → 執行 validate(0 控制台錯誤,WCAG AA) → 渲染 → 在時間軸上抽查 5 個影格。修復 → 重新執行。Lottie 必須透過螢幕截圖驗證(Skottie 與 lottie-web 的陷阱)。
  6. 渲染。 執行 npx hyperframes render --fps 30 --output renders/<name>_FINAL.mp4。對於垂直格式,使用 1080×1920 佈局複製(參閱 video-edit)。

先決條件(先檢查;優雅降級)

參閱 references/prereqs.md。需要 Node 22+、FFmpeg、Python 3.11+ 含 pip(Manim/字幕)。在此機器上:真實 Python 是 py → C:\Python313(裸機 python 是 Hermes 的虛擬環境,沒有 pip — 不要使用它)。ManimCE 透過 py -m pip install manim 安裝(如果使用 Text()/MarkupText 而非 Tex/MathTex,則不需要 LaTeX)。如果 Manim 不可用 → 跳過數學節拍或提供安裝選項;絕不硬性失敗整個影片。

此技能捆綁的內容(通過 lint 和渲染的參考實作)

檔案說明
assets/FRAME.mdYUV.AI Neon Phoenix 影片影格規格(從 HeyGen 的 Coral 包重新品牌)
assets/neural-net-field.js確定性、可尋找的神經網路鳳凰畫布背景
assets/neural-pulse.json手寫的 Bodymovin Lottie(在 lottie-web 中渲染,不僅僅是 Skottie)
assets/gen_content_lotties.py生成器,用於 6 個生產級內容 Lottie(WhatsApp-collapse、decode-beam、eye-read、ghost-line hero、orb-extract、brain-fire)— 透明、持久+連續、經 lottie-web 驗證
assets/{wa-collapse,decode-beam,eye-read,ghost-line,orb-extract,brain-fire}.json6 個生成的內容 Lottie,可直接放入
assets/manim-scene-template.pyManimCE 場景模板,霓虹品牌樣式,僅文字(無 LaTeX)
assets/what_is_nn.py"什麼是神經網路" ManimCE 場景(神經元 → 網路 → 訓練,34.5 秒)
assets/Anton-Regular.woff2本地 Anton(渲染器不會自動解析;需宣告 @font-face)
references/composition-pattern.md完整的多引擎 index.html 模式(場 + Lottie + Manim 剪輯 + GSAP + 閃光)
references/teaser-explainer.md電影宣傳片解釋公式:冷開場撞擊 → manim BURSTS → 對峙 → FOMO 蒙太奇 → 懸念;內容同步的透明 Lottie 節拍;尋找模數修復;宣傳片音樂合成

配套技能

hyperframes(組合合約 — 編寫時始終調用)、hyperframes-cli、lottie、video-edit(轉錄 + 核准網頁應用)、yuv-design-system(品牌)。此技能協調它們。

Individual skills in this repo

This repo contains 9 individual skills — each has its own dedicated page.

hoodini/ai-agents-skills

Edit any selfie or screen-share footage into a viral short-form video in YUV.AI's signature style — Apple-style liquid-glass cards (real CSS backdrop-filter), dark-mode polish, MrBeast-paced cuts, video-title karaoke captions, premium GSAP motion graphics, no fake content, never covering the speaker's face. Hebrew is rendered in Rubik Black, English in Anton uppercase. Always renders BOTH 9:16 and 16:9 and always saves with _V<N> suffix for backups. Trigger when the user drops a path to an .mp4/.mov/.mkv and says "edit this", "make it viral", "turn this into a short", or any Hebrew equivalent (ערוך סרטון, סרטון ויראלי, להפוך לוויראלי, ריל, שורט). The pipeline is the COMBINATION of two skills: video-use (transcription + word-snapped cuts + base extraction) and hyperframes (HTML/CSS/GSAP visual composition + render). Do NOT use for podcast-only audio edits.

hoodini/ai-agents-skills

Turn any video into a cinematic scroll-driven landing page — Apple-style hero where scrolling progresses the visible frame through the video. Use when the user provides a video file and asks for "a landing page from this video", "scroll-frame website", "Apple-style scroll site", "hero that scrubs the video", "like the GitHub Copilot landing", or any equivalent. Extracts N evenly-spaced frames via ffmpeg, builds a self-contained HTML page with a sticky hero + JS scroll listener that swaps the visible frame as you scroll, plus headline, sections and CTA below. For YUV.AI projects, applies the yuv-design-system skill in Neon mode (pink/cyan/white, default for YUV.AI web) — Decks (purple/yellow) is reserved for slides only. For generic / non-YUV.AI projects, picks an appropriate palette per the source video. Output is one folder with `index.html` and a `frames/` directory — drop on any static host.

hoodini/ai-agents-skills

Yuval Avidani's YUV.AI brand and design system. Apply ONLY when YUV.AI-branded output is requested — presentations, decks, keynotes, portfolio, brand site, profile, speaker bio, brand assets, or any prompt mentioning YUV.AI / "my brand" / "my deck" / "my site" / "for me". Do NOT auto-trigger on generic "build a game / web app / dashboard / landing page" without YUV.AI context — those use whatever palette fits. Three modes; NEON (hot pink #FF1464 + neon cyan #00E5FF + white, DEFAULT for YUV.AI web, apps, games, dashboards, social, general visual work); DECKS (Fly High purple/yellow/grey, presentations and slides ONLY); Warm Editorial (pink/yellow/bone for Hope, Marcus, bigcats.ai, practical.yuv.ai). Universal Fly High throughline across all modes; flight/progress motifs (HUD strips, dials, "Let's Fly High" tagline, phoenix mark). Anton + Inter (EN), Rubik + Assistant (HE), letter-spacing 0 default. Bundled brand assets, canonical socials, credentials. Project brand wins if specified.

hoodini/ai-agents-skills

Build a premium cinematic landing page with mouse-scrub video hero and brand-driven narrative-arc sections. Use whenever the user provides a hero video plus a product / subject / brand and wants a landing page, promo site, product showcase, marketing page, or storytelling site. Works for any language (RTL or LTR — Hebrew, English, Arabic, Spanish, French, Japanese, etc.) and any subject (food, tech, animals, fashion, services, SaaS, wildlife campaigns, music releases, books, real estate). The signature effect is mouse-driven video scrubbing — the hero video lives across the entire page as a fixed backdrop, and moving the mouse left-right scrubs the video timeline so the subject responds to the cursor. Below the hero, 4-5 fully-opaque sections each carry their own brand identity (color, typography emphasis, layout pattern) and walk the viewer through a narrative arc (e.g. longing → joy → nostalgia → contemplation → action). Triggers on phrases like "build a landing page from this video", "cinematic landing ...

hoodini/ai-agents-skills

Build a scroll-driven cinematic landing page from a short video. The user provides a 5–15 second video (often AI-generated); this skill extracts every frame at HD JPEG quality, then produces a single-hero HTML page where the user's scroll gesture scrubs the frames in place (the page itself never scrolls) and 5 dramatic text overlays crossfade in/out — Google Anton headlines, Caveat handwritten accents, locked body, virtual scroll. Use this skill whenever the user wants to "turn this video into a landing page", "make a scroll-scrub landing page", "build a parallax hero from this clip", "add a new landing page to the parasites showcase", "do the same as github/lion/hope for this new video", or any variant that pairs a short clip with dramatic scroll-triggered storytelling. Trigger even if the user only says "use my video for a landing page" — that is this skill.

hoodini/ai-agents-skills

Edit any video into a captioned showcase — transcribe (any language, defaults to large-v3), present a transcript_review.txt for the user to fix mishears BEFORE rendering, then build a HyperFrames composition with liquid-glass caption pills, liquid blob background, liquid morph wipes, optional behind-subject text via background removal, and render the final video. Use whenever the user provides a video file and asks to edit it, caption it, add subtitles, fix existing captions, make a reel/promo/captioned tutorial, or "do the same" pattern as a prior captioned video. Supports English, Hebrew, and any Whisper-supported language. **Renders both 16:9 (YouTube / horizontal) and 9:16 (TikTok / Instagram Reels / YouTube Shorts) from the SAME 16:9 source** — vertical mode uses a centered footage strip with a blurred backdrop + liquid blobs and a vertical-tuned caption pill, no need to re-shoot. THE PIPELINE PAUSES FOR USER APPROVAL on the transcript before final render — this is the support mechanism for getting ca...

hoodini/github-trending

Fetch and display GitHub trending repositories and developers. Use when building dashboards showing trending repos, discovering popular projects, or tracking GitHub trends. Triggers on GitHub trending, trending repos, popular repositories, GitHub discover.

hoodini/mongodb

Work with MongoDB databases using best practices. Use when designing schemas, writing queries, building aggregation pipelines, or optimizing performance. Triggers on MongoDB, Mongoose, NoSQL, aggregation pipeline, document database, MongoDB Atlas.

hoodini/owasp-security

Implement secure coding practices following OWASP Top 10. Use when preventing security vulnerabilities, implementing authentication, securing APIs, or conducting security reviews. Triggers on OWASP, security, XSS, SQL injection, CSRF, authentication security, secure coding, vulnerability.

相關技能