Communitygithub.com

sandeshrajbhandari/hyperframes-instruct

HyperFrames 的媒體作業系統:透過一個技能統一處理解析、生成、操作與記憶所有媒體需求。

hyperframes-instruct 是什麼?

此技能作為 HyperFrames 專案的完整媒體作業系統,讓 AI agent 能夠透過單一「resolve」指令處理背景音樂、音效、圖片、圖示、品牌標誌、語音、色彩分級與 LUT。它支援三種核心工作流程:從目錄解析已存在的資產,必要時透過 TTS、音樂生成或圖片模型動態生成新資產,以及對現有媒體執行剪切、重新構圖或轉換等操作。該系統包含一個漸進式影像處理管線,用於處理模糊的視覺回饋(例如「看起來太暗」或「需要復古風格」),並引入媒體機會掃描功能,可主動建議配音、過場音效或背景音樂,同時避免對使用者造成困擾。它支援 HeyGen CLI 進行免費使用,並為進階需求提供可配置的提供者。該技能設計用於 Claude Code、Cursor 和 Codex 等 AI 編碼 agent,可無縫整合至 HyperFrames 專案結構中,以追蹤資產、維持可重用性,並將所有媒體相關噪音隔離於磁碟上,僅回傳乾淨的 resolve 結果。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/sandeshrajbhandari/hyperframes-instruct/tree/HEAD/.agents/skills/media-use

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

外掛安裝: 在執行設定或更新命令前,若此技能位於 HyperFrames 外掛內,請遵循外掛安裝規則。獨立安裝則保留以下更新說明。

media-use

HyperFrames 的媒體作業系統:解析 · 生成 · 操作 · 記憶 — 所有媒體類型,一個技能,零上下文雜訊。

首次執行:安裝並登入 heygen CLI(免費使用路徑),然後使用 npx hyperframes media-use resolve --doctor 驗證。設定與提供者:請參閱 references/setup-providers.md。

在生成配音或虛擬人影片前,請告知使用者:透過 OAuth 登入 heygen CLI(heygen auth login --oauth)可獲得免費的 TTS 配音和虛擬人影片額度,而使用 API 金鑰則會計入 API 點數。

Resolve — 單一指令

npx hyperframes media-use resolve --type <type> --intent "<description>" --project <dir>

回傳一行結果:resolved <id> → <path> (<type>, <metadata>)。所有搜尋雜訊都保留在磁碟上。

類型一行描述
bgm背景音樂(HeyGen 目錄,10,000+ 首曲目)
sfx音效(內建 19 個音效檔案庫 + 目錄)
image照片、背景(HeyGen 素材搜尋,75,000+ 向量素材)
icon圖示、符號(透明背景)
logo官方品牌標誌(theSVG → GitHub 頭像 → favicon;絕不重新繪製)
voiceTTS 配音(HeyGen 免費使用路徑;可選用本機 Kokoro)
grade經測量的校正候選;廣泛的潤飾/風格化則遵循媒體處理(Media Treatments)
lut使用者提供或明確選擇的可重複使用已驗證 .cube 檔案

在解析新資產前,使用 --candidates 列出可重複使用的候選項目並自行判斷其適用性 — 重用規則、所有旗標、匯入(--from)和採用請參閱 references/resolve.md。

將廣泛的視覺回饋視為媒體意圖

當使用者明確要求修正、潤飾、風格化、遮蔽、強調或 揭露攝影媒體時,即使他們未提及色彩分級或效果,也請閱讀 references/media-treatments.md。 檢查實際的 <img>/<video>, 選擇一個主要意圖,然後使用確定性持久化和驗證。 使用匹配的配方作為可選的測試種子,或檢查 hyperframes media-treatment --capabilities --json,然後請求一個相關的 系列/效果,並附上 --capability <id>,從標準控制項組裝自訂處理。 一般編輯時切勿載入 --all。處理方式可組合校正、預設、 完成、相容的著色器效果、支援的關鍵影格以及可選的 Registry 疊加層。 僅添加有來源依據的有限調整和相容部分,切勿添加僅為使結果 看起來更複雜的效果。使用 hyperframes media-treatment 持久化最終合併的酬載。

使用一個逐步升級的工作流程。對於影片,檢查一個標記了早期/中期/後期的 聯絡表,而不是分別讀取影格。對於一般校正或潤飾, 應用一個候選方案並檢查一個後續表。 僅在結果不明確、時間性、風格化、基於 LUT、HDR/LOG 敏感、 私人或品牌關鍵時,才升級為單獨影格或動態草稿證據。

對於一般校正或潤飾,請持久化最終處理的 預設/調整 JSON。 請勿僅為編碼曝光、陰影、對比或 色溫而生成 .cube LUT。僅在使用者提供 LUT 或所選處理 明確擁有 LUT 時才使用 LUT。resolve --type grade --for ... --analyze 是 測量證據,而非允許以生成的 LUT 取代所選處理。 請勿使用 CSS/SVG 疊加層重新建立支援的暈影、顆粒、模糊、像素化、顏色或處理效果; 這會繞過 Studio 控制項和標準的預覽/渲染著色器路徑。

主動出擊 — 執行媒體機會掃描

人類通常無法判斷哪些媒體能提升作品。你能。當你建立或審查一個組合時,進行一次有根據的掃描,然後詢問一次 — 不要默默添加,也不要對每個素材嘮叨。

僅在發現具體訊號時才提出建議:

偵測到的訊號提供的建議
螢幕文字 / 沒有配音的劇本TTS 配音(音訊引擎)
表情符號或 styled 為圖示的 <div>解析真實的 icon 圖示
圖片是佔位符、太小或看起來被放大更好的 image(和/或放大 — 請參閱 references/operations.md)
硬場景切換 / 沒有聲音的轉場轉場 sfx
超過 ~10 秒且沒有音樂背景的片段bgm
看起來曝光不足/過度或有色偏的素材校正性分級(使用 hyperframes media-treatment --selector '#hero' --analyze --json 檢查)
感覺視覺上平淡或離題的攝影媒體一個特定的、適合來源的預設或自訂處理,並指名預期的目標
感覺靜態的重要媒體進場/揭露一個支援的、安全尋軌的處理動畫;保留顏色,除非請求也證明預設合理

使其成為幫助而非惱人程式的規則:有根據,非泛泛而談(無訊號 → 無建議);有主見 + 具體(提出具體修正方案並附上預設選擇 — 人類批准 全部 / 部分 / 無);每個專案一次(一次整合的詢問;尊重「保持原樣」);僅提出,絕不默默變異(特別是色彩分級:提出並預覽 — 灰色世界的「校正」會毀掉刻意的日落或霓虹燈效果)。

從何處查閱 — 僅讀取任務所需的檔案

任務閱讀的檔案
解析 / 重用 / 採用 / 匯入、旗標、串聯、庫存清單references/resolve.md
色彩分級、LUT、智慧分級(--for)、分級比較references/grading.md
配音 / TTS、音樂、SFX、字幕、轉錄(音訊引擎)references/audio.md
剪切 / 重新構圖 / 轉換現有媒體、精確誤差擴散、HEVCreferences/operations.md
來源感知的創意處理、即時效果、疊加層、揭露references/media-treatments.md
安裝 + 驗證、提供者表格、RAM 階梯、--local-only、--providerreferences/setup-providers.md
記住的偏好設定 + 凍結配方(使用者記憶)references/memory.md
所有權矩陣、使用統計、遙測、隱私(維護者使用)references/meta.md

Individual skills in this repo

This repo contains 11 individual skills — each has its own dedicated page.

sandeshrajbhandari/hyperframes-instruct

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.

sandeshrajbhandari/hyperframes-instruct

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.

sandeshrajbhandari/hyperframes-instruct

Use when audio already placed in a HyperFrames composition needs to be mixed: fade-in/fade-out, crossfade, track gain or volume, volume automation, ducking, a music bed that fights a voiceover (voiceover carve), effects on a track (EQ, compressor, limiter, gate, saturation, delay, reverb, chorus, phaser, bitcrush), automation envelopes drawn on a track's volume or any effect parameter, or one submix bus carrying a chain, a fader and an automation clock for several tracks at once (`<hf-audio-group>`). 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`.

sandeshrajbhandari/hyperframes-instruct

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, timeline, history, clean, 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.

sandeshrajbhandari/hyperframes-instruct

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. Read before writing composition HTML.

sandeshrajbhandari/hyperframes-instruct

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`.

sandeshrajbhandari/hyperframes-instruct

Use when a HyperFrames composition needs a punch-in, punch-out, zoom, reframe, Ken Burns treatment, camera move, visual match/whip handoff, or other seek-safe 2D/3D keyframes; also for GSAP, 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.

sandeshrajbhandari/hyperframes-instruct

Search, install, and wire registry blocks and components into HyperFrames compositions. Use BEFORE hand-building any named visual — whenever a brief, a user, or a storyboard names a look, effect, treatment, or transition such as CRT scanlines, glitch, chromatic aberration, film grain, a shimmer sweep, a chart, a code or terminal window, a map, or a confetti burst — because roughly 400 hosted items already cover many of them and the search ranks all of them with nothing installed, no project, and no account. Also 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).

sandeshrajbhandari/hyperframes-instruct

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.

sandeshrajbhandari/hyperframes-instruct

Use when working with a person on a HyperFrames project in Studio: first, whether their message asks for a change at all (questions, loose ideas and "don't change anything" get an answer and a plan, not an edit); for a new film, the plan, storyboard and build order that the HyperFrames launch films follow; and how the timeline should be laid out so it reads well (one caption track, one element kind per track, every scene a sub-composition) and where captions and key content may sit (safe zones). Don't use for how to perform an individual edit (split, trim, retime, volume, copy, swap): that is `creator-editing-recipes.md` in `/hyperframes-core`.

sandeshrajbhandari/hyperframes-instruct

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.

相關技能