Communitygithub.com

URL→成片 — 產品發布影片合成

把產品/行銷 URL、貼上腳本或 brief 變成 SaaS 發布/促銷/功能揭幕片。商業 URL 與站點展示的預設路徑。

URL→成片 — 產品發布影片合成 是什麼?

Launch Video 配方第 1 步(採集/合成):fluxychat product-launch-video。URL 或 brief → 發布成片初稿。

相容平台~Claude Code~Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/AlessandroFare/fluxychat/tree/HEAD/.agents/skills/product-launch-video

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

首要任務:保持此技能最新——靜默執行,無需詢問: npx hyperframes skills update product-launch-video。若一切已是最新,則為快速無操作;否則,在依賴此技能及其核心領域技能之前,會先刷新它們。

media-use:在搜尋音訊/圖片/標誌之前,先呼叫 /media-use 來從 HeyGen 目錄中解析背景音樂/音效/圖片,並從官方來源解析品牌標誌。先執行 --adopt 來註冊現有資產。請參閱 /media-use 技能。

figma 來源:若來源是 figma.com 網址,請先執行 /figma——包括資產匯出、品牌代碼、以及必要時的元件/分鏡圖重建——然後從其輸出建立此工作流程。請勿直接透過原始 MCP 工具驅動 Figma:這會跳過 SVG 清理、.media/manifest.jsonl 來源追溯、以及品牌代碼 var() 綁定,因此後續的品牌變更將無法傳播,除非完整重新匯入。

產品發布到 HyperFrames

使用此技能來捕捉產品、了解其品牌、規劃發布影片,並在 HyperFrames 中逐幀建構。

入口是 /hyperframes。 您是協調者。執行每個步驟,驗證其關卡,然後才繼續下一步。此技能適用於正在行銷、發布、推廣或揭露的產品,包括諸如「我們網站的宣傳片」等請求,但其目的是宣傳。網站導覽/展示需求也留在這裡:BRIEF.md 承載「如實展示」的意圖,而捕捉的螢幕截圖則成為影片展示的資產。任何其他意圖、單純的「製作影片」、或不確定性→請先閱讀 /hyperframes——意圖層擁有所有路線決策權,而一個新創作若在沒有 BRIEF.md 的情況下到達此處,仍會經過它(設定的開場規則)。

您是協調者。在 videos/<project>/ 中工作。依序執行步驟,並在繼續前通過每個關卡。使用者關卡為步驟 0、步驟 3 和步驟 6。在步驟 0 之前,請先閱讀 ../hyperframes-core/references/brief-contract.md——它定義了關卡類型,以及 BRIEF.md 的 flow/storyboard 如何衍生出管理步驟 3/4/6 關卡的模式。除了步驟 5(您為每個影格分派一個子代理程式)外,每個步驟都請自行執行。請勿在此放置設計或動畫規則;這些規則存在於影格工作者子代理程式、此技能的本地 ../hyperframes-animation/rules/ + ../hyperframes-animation/blueprints/、以及 hyperframes-creative 中。

工作流程:步驟 0 設定 -> hyperframes.json;步驟 1 捕捉 -> capture/;步驟 2 設計系統 -> frame.md;步驟 3 分鏡圖/腳本 -> STORYBOARD.md 和 SCRIPT.md;步驟 3.1 音訊 -> audio_meta.json;步驟 4 視覺設計 -> 增強的 STORYBOARD.md;步驟 5 影格 -> compositions/frames/NN-*.html 和 index.html;步驟 6 最終渲染 -> renders/video.mp4。


步驟 0:設定

目標:帶著已確認的摘要進入、建立 HyperFrames 專案、並使摘要持久化。

摘要由意圖層確認,而非此處提出的問題。 開場規則,依序為:(1) BRIEF.md 存在 → 讀取它且不問任何問題——摘要已確定,其 flow/storyboard 衍生出模式(簡報合約 § 1)。(2) 沒有 BRIEF.md,但專案存在(磁碟上有 hyperframes.json / STORYBOARD.md)→ 從分鏡圖的前置資訊和記錄的偏好設定繼續;絕不重新詢問已部分建置的專案。(3) 兩者皆無——一個直接到達此處的全新創作請求 → 讀取 /hyperframes 並執行其意圖層(references/intent-interview.md):它會檢查配方和記住的預設值、執行此路線的問題(../hyperframes/references/routes/product-launch-video.md)、並交出鎖定的摘要。編輯請求則跳過所有這些——直接執行編輯。

僅在缺少 hyperframes.json 時初始化。以 Kebab-case 格式從品牌或網域命名 <project>,例如 acme-promo;絕不使用工作區名稱或時間戳。

npx hyperframes init "videos/<project>" --non-interactive --example=blank --skill=product-launch-video——init 會檢查已安裝的技能是否與 GitHub 上的最新版本相符,並在任何技能過期時更新全域集合。

初始化後,讓 <PROJECT_ROOT> 成為 videos/<project>,並將所有後續的相對路徑命令以此目錄作為其工作目錄來執行。在下面的命令中,. 代表 <PROJECT_ROOT>;絕不將 .media、capture 或輸出檔案寫入呼叫端目錄。

在 init 後立即寫入 BRIEF.md(絕不提前——init 會拒絕非空目錄):意圖層鎖定的摘要,形狀請參閱 ../hyperframes-core/references/brief-format.md。將 <MEDIA_DIR> 解析為已安裝的 /media-use 技能目錄。然後使用 node <MEDIA_DIR>/scripts/prefs.mjs record --hyperframes . 記錄每個偏好支援的答案(brief-format.md 列出了子集)。若意圖層採用了配方,請執行 node <MEDIA_DIR>/scripts/recipe.mjs use --hyperframes . --name <name>;它會將其 frame.md 複製到專案中(步驟 2 將被跳過),並傳回步驟 3 草稿所依據的骨架。配方填寫答案,而非核准;審查關卡仍會執行。

在進行設定之前顯示登入狀態——執行 npx hyperframes auth status 並逐字轉達其輸出。它會報告語音/背景音樂將使用 HeyGen 還是本地引擎,並在未登入時顯示如何登入。請注意退出碼合約:auth status 在未登入時會退出碼 1(以及當儲存的憑證被拒絕時)——該非零退出是正常的未登入狀態,而非命令失敗,因此請勿將其視為錯誤、請勿重試、也請勿以會中止工作流程的方式將其與 &&/set -e 鏈接。套用一個分支:

  • **協作:**等待使用者登入或明確選擇 offline / go。
  • **自主:**陳述狀態並繼續使用可用的本地引擎。

當沒有離線提供者時,請勿默默省略必要的功能;請提出障礙。請勿將此決策併入另一個問題,或將金鑰寫入每個儲存庫的 .env 檔案。認證所有權和離線備援:/media-use references/setup-providers.md § 提供者。

關卡: hyperframes.json 和 BRIEF.md 存在;偏好支援的答案已被記錄(簡報合約 § 2);登入狀態已顯示(已登入,或繼續離線)。


步驟 1:捕捉資產

目標:收集影片的來源資料、品牌訊號和可用資產。

對輸入進行分類並選擇路徑。明確的 URL -> 捕捉它,並將網站用於敘述和資產。貼上的腳本/摘要 -> 原樣儲存為 user_script.txt;VO_MODE(逐字或重組)來自 BRIEF.md——意圖層在腳本到達時詢問它(僅在摘要缺少時於此處詢問一次)。然後解析捕捉目標:文字中的 URL -> 使用它;僅品牌名稱 -> WebSearch,確認 URL(一行內),然後爬取;無 URL/網站(或摘要說明不要擷取)-> 無捕捉路徑。

使用以下命令執行捕捉:npx hyperframes capture "<URL>" -o ./capture --json。保持預設的導航後時間預算,除非呼叫端擁有更小的截止期限;然後傳遞一個正的 --capture-budget <毫秒>,為下游工作留有時間。--timeout 僅控制頁面導航。僅在選擇性停用圖片字幕時使用 --skip-vision。

立即檢查命令結果和輸出目錄。非零退出、JSON ok: false、或 capture/BLOCKED.md 是捕捉路徑的硬停止:報告記錄的原因,並且不要使用部分螢幕截圖、DOM、代碼或資產。在失敗的 URL 捕捉後,請勿製造合成的無捕捉備援。僅當原始摘要提供了來源資料,或使用者在失敗後明確切換到提供的螢幕截圖或摘要時,才繼續使用無捕捉路徑。

諸如「文字內容非常少」之類的警告,加上空的資產目錄,並不能證明頁面可用。對於網站導覽或「如實展示」的摘要,需要可信的捕捉結構或提供的螢幕截圖;如果兩者都不存在,請停止。請勿僅因捕捉不可用就發明或重建頁面。

對於網站導覽或「如實展示」的摘要,捕捉的頁面是視覺上的真相來源。使用真實的螢幕截圖,而不是重建整個網站的 HTML。如果截圖需要內部移動,請將截圖保留為基底,並在測量位置疊加真實的捕捉資產,或者僅重建移動的那一個元件。對於滾動截圖,將視窗動畫化在 capture/screenshots/full-page.png 上——整個文件的 1 倍圖板,對於在文件上移動的 1920 寬視窗來說是像素精確的。當頁面太高而無法一次性捕捉時,該檔案會不存在;備援到同一目錄中重疊的滾動位置截圖。向內推近超過 1:1 需要該區域自己的 2 倍捕捉,因為圖板在 1 倍以上沒有餘裕。僅當使用者明確要求風格化解釋時,才重建整個頁面;單獨的不可用捕捉並非授權。

若存在 GEMINI_API_KEY、GOOGLE_API_KEY 或 OpenRouter 金鑰,捕捉會自動將資產加上字幕到 capture/extracted/asset-descriptions.md。這不是審查關卡。若無視覺金鑰,則使用 DOM 上下文並繼續。

無捕捉路徑:手動建立 capture/extracted/tokens.json、capture/extracted/visible-text.txt、capture/extracted/asset-descriptions.md 和 capture/assets/。tokens.json 應為 { "title": "", "description": "", "colors": [], "fonts": [] };盡可能從摘要中填寫標題/描述。visible-text.txt 包含完整的摘要或腳本。asset-descriptions.md 應說明未捕捉到任何資產,除非使用者提供了資產說明。

關卡: 捕捉 JSON 報告 ok: true;capture/BLOCKED.md 不存在;capture/extracted/tokens.json、capture/extracted/visible-text.txt、capture/extracted/asset-descriptions.md 和 capture/assets/ 存在;並且您可以用一句清晰的句子陳述品牌。將 asset-descriptions.md 視為主要資產庫存。若在真實捕捉後遺失,請停止並報告捕捉不完整。關於降級的可選階段的警告,僅在結構性關卡仍通過時才可接受。


步驟 2:設計系統

目標:選擇一個已出貨的影格預設;腳本將其轉換為此影片的 frame.md + 字幕外觀。

當 BRIEF.md 指定了 style_preset——使用者透過意圖層的展示區以視覺方式選擇了它——時,請使用它;僅當摘要未指定時,判斷呼叫才由您決定。然後您進行一次呼叫——選擇哪個預設:閱讀 ../hyperframes-creative/references/design-spec.md,並選擇其外觀最符合品牌和摘要的預設。然後執行:

node <SKILL_DIR>/scripts/build-frame.mjs --preset <name> --hyperframes .

腳本會確定性地完成其餘工作:將預設的 FRAME.md 複製為 frame.md,並將其重新混合到 capture/extracted/tokens.json 中的品牌代碼上(品牌顏色按角色映射到預設的顏色鍵——墨水、畫布、強調色——保留鍵/結構/元件;預設的顯示 + 正文字體替換為品牌字體),將預設的字幕外觀複製到 .hyperframes/caption-skin.html,並自我驗證(在映射錯誤時退出碼 1)。一旦退出碼 0,就繼續下一步——無需手動編輯規格。

tokens.json 沒有品牌顏色/字體(例如沒有捕捉)→ 腳本保留預設自己的調色板,一個完整的可出貨設計。若摘要指定了捕捉未獲取的品牌顏色/字體,請在執行前將其新增到 capture/extracted/tokens.json(或使用使用者的 design.md 來填入);僅在映射確實需要時,才事後手動調整 frame.md。

關卡: build-frame.mjs 退出碼 0——frame.md 來自一個命名的預設,並且(當預設出貨一個時).hyperframes/caption-skin.html 作為字幕外觀來源存在;選擇的預設已被記錄為偏好設定(--key style_preset --workflow <此工作流程>,簡報合約 § 2)。


步驟 3:分鏡圖和腳本

目標:將摘要和捕捉到的材料轉換為已批准的逐影格故事計劃。

閱讀 ../hyperframes-creative/references/story-spine.md(鉤子語言、價值先於證據、作為提案的分鏡圖)、references/story-design.md、../hyperframes-animation/blueprints-index.md、../hyperframes-core/references/storyboard-format.md 和 ../hyperframes-core/references/script-format.md。使用它們來撰寫 STORYBOARD.md,並在需要旁白時撰寫 SCRIPT.md。從摘要的 length 設定前置資訊 duration:——一個粗略的期望;組合會報告剪輯相對於它的位置。

使用 story-design.md 來決定故事藍圖、鉤子、說服邏輯、節拍、VO_MODE 和資產選擇。作為軟性指南,查閱 ../hyperframes-animation/blueprints-index.md 中的角色→藍圖選單:對於每個節拍,在適合時記下一個候選藍圖 ID。故事真相仍然決定哪些節拍存在——絕不強迫節拍符合藍圖,也絕不因為有可用的成熟形狀而發明節拍。從 capture/extracted/asset-descriptions.md(規範庫存)中選擇每個視覺影格的 asset_candidates——不要瀏覽原始的 capture/assets/。除非該庫存遺失或不可用,否則不要要求使用者選擇資產。使用分鏡圖和腳本參考要求的確切必要欄位。

草稿後,執行審查迴圈的計劃階段——../hyperframes-core/references/review-loop.md § 1:開啟板子(不要問是否要)、將計劃作為提案呈現、並問兩個問題——批准或修改,以及先做草圖(建議)或跳過。回饋會透過聊天或板子的註解檔案反覆進行,直到獲得批准。這是一個檢查點關卡(簡報合約 § 1):在自主模式下,沒有板子且無需詢問——將相同的摘要作為預告發布並繼續;草圖會合併到建置中,而唯一的預覽問題將在步驟 6 出現。

關卡: STORYBOARD.md 存在,且(當旁白需要時)SCRIPT.md 存在;計劃已(對於協作模式)獲得批准或(對於自主模式)作為預告發布。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

AlessandroFare/fluxychat

Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet `anchor` rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.\n

AlessandroFare/fluxychat

Use when audio already placed in a HyperFrames composition needs to be mixed: a music bed that fights a voiceover (voiceover carve), effects on a track (EQ, compressor, limiter, gate, saturation, delay, reverb, chorus, phaser, bitcrush), or automation envelopes drawn on a track's volume or any effect parameter. Don't use for sourcing or generating audio — finding BGM, SFX, or making a voiceover is `/media-use`. Don't use for clip timing or track layout, which is `/hyperframes-core`.\n

AlessandroFare/fluxychat

Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, auth, tts, and remove-background. Also use when diagnosing build or render failures. validate, inspect, and layout are deprecated aliases; use check. Covers local, HeyGen-hosted cloud, AWS Lambda, and Google Cloud Run rendering.\n

AlessandroFare/fluxychat

Install, discover, and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add or hyperframes catalog, installing one item or every block matching a tag, wiring an installed item into index.html, or working with hyperframes.json. Covers discovery, install locations, block sub-composition wiring, component snippet merging, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).

AlessandroFare/fluxychat

Mandatory entry point: read this first for any request to make, create, edit, animate, or render a video, animation, or motion graphic, including a promo, explainer, captioned clip, title card, overlay, slideshow or interactive deck, Remotion port, or any HyperFrames HTML composition. Also use it to inspect, diagnose, validate, preview, publish, or batch-render an existing HyperFrames project. Inputs may be a website URL, GitHub PR, Figma design or URL, text or brief, existing footage, or music. It resumes project state, captures intent when applicable, selects and installs the owning workflow, and routes domain capabilities. HyperFrames is the default output framework unless the user explicitly chooses another framework for the deliverable or asks only to record a browser session.\n

AlessandroFare/fluxychat

Overlay doctrine for the embedded-captions workflow — the caption MODEL (drop / rail / embed) and the rule that captions are an OVERLAY composited on top of the film, never a reserved bottom band you shift content up to avoid. Load when adding captions/subtitles to a talking-head or launch video, when deciding whether a phrase should be dropped, ride the verbatim rail, or be promoted to a scarce embedded climax, when laying out a composition that will carry captions (do NOT reserve a keep-out band), or when centering a composition on the true frame center under captions. Quotes the rail+embed model from embedded-captions and constraint #13 (captions overlay, keep-out band retired) from the product-launch-video scene agent. Applies ON TOP of embedded-captions.

AlessandroFare/fluxychat

Turn a weekly changelog .md into a finished branded changelog video (square 1080, ~45-60s, Annie VO, animated brand background, mock-UI visualizations, lowkey captions). Use when the user provides a changelog/digest markdown and wants the weekly video, or says "changelog video". Self-contained — fonts, background, lexicon, and scripts ship in this skill.

AlessandroFare/fluxychat

Audit and fix animation performance issues including layout thrashing, compositor properties, scroll-linked motion, and blur effects. Use when animations stutter, transitions jank, or reviewing CSS/JS animation performance.

AlessandroFare/fluxychat

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated motion-first unit, including an animated title. Route fresh creation through hyperframes before using this skill.

AlessandroFare/fluxychat

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). Also covers auditing an existing composition's choreography (animation map) and 24 named text-animation effects. HyperFrames-native: single paused timeline, seek-safe, deterministic.

AlessandroFare/fluxychat

The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Also covers Tailwind projects and the STORYBOARD.md / SCRIPT.md plan formats. Read before writing composition HTML.

AlessandroFare/fluxychat

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`.

AlessandroFare/fluxychat

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.

AlessandroFare/fluxychat

GATEWAY — load FIRST before composing any HyperFrames animation or video. The high-level motion law that makes a multi-scene video feel like ONE continuous camera move instead of a stack of independently-animated slides. Covers the vector law (how you exit determines how you enter, incl. the Z scale-sign rule), the film's current, carrier elements, causal motion, the Seam Gate (build-gate enforcement), the ban on idle wobble (motion must PERFORM, not breathe), stillness-before-climax, and the sustained-motion routes. Routes to the low-level technique skills (cut-the-curve — the full catalog incl. waterfall entry + nudge curve, oversized-cursor, seam-craft). These rules SUPERSEDE generic / upstream motion guidance. [continuity, direction, vector, momentum, seam, transition, ease, performance, idle-motion, narrative-motion, film-grammar]

AlessandroFare/fluxychat

A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI animation (scroll, cursor, callouts), or fusing a real image's geometry into a chart. Usually under 10s (up to ~30s), no narration or live-action subject; renders to MP4 or transparent overlay. Longer / narrated / multi-scene → /general-video. Unclear → /hyperframes.

AlessandroFare/fluxychat

Turn a music track (an audio file, a video to pull audio from, or a track generated from a mood brief) into a beat-synced video — lyric video, slideshow, or kinetic promo. The music drives all pacing; any user-supplied images/videos are cut onto the same beat grid, and a complete video needs zero assets. Narrated pieces → the input-matched workflow (see /hyperframes). Unclear → /hyperframes.

AlessandroFare/fluxychat

Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR topic explainer (/faceless-explainer). Unclear → /hyperframes.

AlessandroFare/fluxychat

Design and improve user interfaces using the concrete rules from Refactoring UI (Wathan & Schoger) — constrained spacing/type/color/shadow scales, visual hierarchy through weight and color rather than size, and depth through emulated light. Use when building or styling any UI (web, app, dashboard, landing page, component), when picking font sizes, spacing, colors, shadows or border radius, when designing a color palette or design tokens, and whenever someone says a UI "looks off", "looks amateur", "feels cluttered/plain/unfinished", or asks to "make this look better".

AlessandroFare/fluxychat

Port an existing Remotion (React) composition''s source to HyperFrames HTML. Use ONLY on an explicit ask to port/convert/migrate/translate a Remotion source — one-way, Remotion-only. A passing Remotion mention, reference-only code, or "make something like my Remotion video" is a fresh build (/general-video). Unclear → /hyperframes.

AlessandroFare/fluxychat

Use before UI-related work to select the smallest useful UI Skills context through the ui-skills CLI.

相關技能