motion-graphics

작성자: heygen-com

사용자가 모션이 메시지가 되는 짧고 디자인 중심의 모션 그래픽을 원할 때 사용합니다: 키네틱 타이포그래피, 숫자/통계 카운트업, 차트/데이터 시각화 히트, 로고 스팅, 브랜드 록업, 하단 서드, 콜아웃, 소셜 오버레이, 애니메이션 헤드라인/트윗/뉴스 아이템, 모션 포스터, 또는 빠른 캡처 페이지 하이라이트. 일반적으로 10초 미만에서 최대 약 30초이며, 내레이션 구성, 음성 해설, 또는 실사 피사체가 없습니다. MP4 또는 투명 오버레이로 렌더링 가능합니다. 더 길고, 여러 장면이 있거나, 내레이션이 포함되거나, 브랜드 릴 형식의 작업에는 적합하지 않습니다...

npx skills add https://github.com/heygen-com/hyperframes --skill motion-graphics

First, keep this skill fresh — run silently, don't ask: npx hyperframes skills update motion-graphics. A fast no-op when everything is current; otherwise it refreshes this skill plus the core domain skills it depends on before you rely on them.

figma source: If the logo/asset/animation to build from comes from a figma.com URL, run /figma first — asset export, brand tokens, and Motion→GSAP translation if the graphic is a Figma Motion import — then build from its output. Don't drive Figma via raw MCP tools directly: that skips SVG sanitization, .media/manifest.jsonl provenance, and brand-token var() binding, so a later brand change can't propagate without a full re-import.

motion-graphics — dispatch entry

The front door is /hyperframes. This skill makes a short, design-led, unnarrated motion graphic (motion is the message; ~under 10s, no voice-over). Anything longer, narrated, or multi-scene — or any uncertainty → read /hyperframes first: the intent layer owns every route decision.

This workflow is autonomous by design — at most one clarifying question (agents/director.md), then build through verification without intermediate review. The intent layer (/hyperframesreferences/intent-interview.md) routes here directly without run-shape questions; a storyboard and companion session add little to a piece this short. Rendering is still user-gated: after checks and proof snapshots pass, ask the canonical “preview first, or render?” question from ../hyperframes-core/references/brief-contract.md. When a BRIEF.md exists, read it before the director's question.

A short design-led motion graphic. Asset-first: decide the asset strategy and source real material before designing the shot, then design the shot around what you have, then compose by reusing catalog capabilities. All artifacts go to PROJECT_DIR = videos/<project-name>/ (created in Step 0); all paths below are relative to it.

PhaseExecutionPrimary artifactDetailed flow
initBashhyperframes.jsonStep 0
plansubagent — decide search? + classify + asset strategyshot-plan.json (draft: category, asset_needs queries, brief)agents/director.md (Part 1)
source ◇Bash — media-use resolve (skip if asset_needs is empty)assets/ + assets/index.mdphases/source/guide.md
designsubagent — shot design around resolved assetsshot-plan.json (final: block(s) + layout + motion + positions)agents/director.md (Part 2)
buildsubagent — reuse-first compositioncompositions/index.htmlagents/builder.md
verifyBash — lint, check, proof snapshots; repair on failuresnapshots/contact-sheet.jpgStep 5
approveAsk preview or render; wait for the answerexplicit render approvalStep 6
renderBash — hyperframes render (MP4, or --format webm/mov for overlay)renders/video.mp4 or transparent overlayStep 6

◇ source runs only when the chosen category declares assets. Pure code/text categories (e.g. kinetic-type, most charts/stat) have asset_needs: [] and skip straight from plan to design.

Categories — split by the search decision

plan's first decision is: does this need a search? That fork splits the categories into two groups; then the specific category is picked — for search-driven, by the type of content the search returns. Each category is one categories/<id>/module.md (its planning + build rules); the shared motion vocabulary lives in references/motion-vocabulary.md (→ hyperframes-animation rules/blueprints + registry blocks).

Form categories — no search; the user supplies the content:

CategoryIntentLeans on
kinetic-typepunchy line / quote / title, motion-first textcaption-* blocks + animation rules
statsingle hero number / count-up + ringapple-money-count / rules/{counting-dynamic-scale, stat-bars-and-fills}
chartsbar / line / pie / race / % from datadata-chart block
logo-reveallogo sting / brand lockup (user logo)logo-outro / rules/svg-path-draw
lower-thirdsname / title bars, callouts, social overlayscaption-* + registry overlay blocks
mapsgeographic motion — highlight regions, connect places, zoom to a location (vector lane, or baked basemap lane)us-map / world-map family + bake-basemap.mjs

Search-driven categories — search first, then animate by content type (the RWA path):

Returned contentCategoryAnimation
webpage / linkwebpagewebpage / UI animation (scroll, reveal, cursor, callouts)
news articlenewsheadline reveal + source card + key-fact callouts
tweettweetanimated tweet card
image / entityasset-fusionthe asset's geometry becomes the chart (RWA diegetic fusion)

Build order: one at a time, coverage-first (rough is fine). kinetic-type ported from the prototype; the rest follow.

Prerequisites

macOS Apple Silicon or Linux x64. System tools: brew install node ffmpeg. npx hyperframes doctor once. macOS GPU render: export PRODUCER_BROWSER_GPU_MODE=hardware.

Optional keys (local fallbacks if unset) — only needed by categories that source/generate assets via media-use:

KeyUsed forFallback
GEMINI_API_KEY / GOOGLE_API_KEYimage generation (media-use resolve)skip generate / search-only
(asset_scout / search providers)webpage/news/tweet + asset-fusion real-asset searchcategory degrades to asset-free

Flow

Step 0 — Initialize

cwd is the agent workspace root; write all artifacts under PROJECT_DIR = videos/<project-name>/. <project-name>: use the dir the user gave, else a short kebab-case name from the intent (<subject>-motion). Not the workspace basename or a timestamp.

Only when $PROJECT_DIR/hyperframes.json is absent:

PROJECT_DIR="${MOTION_GRAPHICS_DIR:-videos/<project-name>}"
mkdir -p "$(dirname "$PROJECT_DIR")"
npx hyperframes init "$PROJECT_DIR" --non-interactive --example=blank --skill=motion-graphics

init checks the installed skills against the latest on GitHub and updates the global set if any are out of date.

Constraints: never hyperframes init in the workspace root; never nest another hyperframes/ inside PROJECT_DIR; every Bash command (master + subagents) is a (cd "$PROJECT_DIR" && ...) subshell — never bare cd.

Step 1 — Plan (subagent: Director Part 1)

Dispatch one subagent. prompt = full agents/director.md + ## Dispatch context (SKILL_DIR / PROJECT_DIR / the user's request / Schema: <SKILL_DIR>/references/shot-plan-ir.md). It must:

  1. Decide: does this need a search? (the first fork)
    • No → pick a form category (kinetic-type / stat / charts / logo-reveal / lower-thirds); content is user-supplied; asset_needs: [].
    • Yes → emit a search plan into asset_needs[] (news / web / tweet / image; two-pole queries). The specific search-driven category (webpage / news / tweet / asset-fusion) is confirmed by the content type returned in Step 2, and finalized in Step 3.
  2. Write a draft shot-plan.json (envelope + chosen form category or search intent + asset_needs + a one-paragraph shot brief). Schema: references/shot-plan-ir.md.

Validation: [ -s "$PROJECT_DIR/shot-plan.json" ] && echo ok || echo missing.

Step 2 — Source ◇ (Bash: media-use, conditional)

If shot-plan.json.asset_needs is non-empty, resolve assets (search / generate / fetch → frozen project-local paths + ledger). See phases/source/guide.md (wraps media-use resolve; the search-driven categories use the news/web/tweet/image search). If asset_needs is empty, skip to Step 3.

# illustrative — see phases/source/guide.md
(cd "$PROJECT_DIR" && node <SKILL_DIR>/phases/source/resolve.mjs --plan ./shot-plan.json --out ./assets)

Degrade gracefully: if a search/provider is unavailable, the category falls back to asset-free (note it in context.log).

Step 3 — Design (subagent: Director Part 2)

Dispatch a subagent (prompt = agents/director.md Part 2 + dispatch context including the resolved assets/index.md if Step 2 ran + catalog-map.md). It designs the shot around the available assets: pick the catalog block(s) + the hyperframes-animation rules/blueprints, the layout, the motion, beats, and (for asset-fusion) the element_positions + eyedropper palette. Finalizes shot-plan.json (content.block + content.customize + per-category content).

Step 4 — Build (subagent: Builder, reuse-first)

Dispatch a subagent. prompt = full agents/builder.md + dispatch context (shot-plan.json, catalog-map.md, the category's module.md, references/motion-vocabulary.md, references/builder-contract.md). Reuse-first: npx hyperframes add <block> + customize in place; hand-author only gaps + the asset-fusion affordance. Output compositions/index.html honoring the HF contract (paused GSAP timeline on window.__timelines, class="clip" + stable ids, tl.seek(0), deterministic).

Step 5 — Verify (Bash → repair subagent on failure)

(cd "$PROJECT_DIR" && npx hyperframes lint .)
(cd "$PROJECT_DIR" && npx hyperframes check .)
(cd "$PROJECT_DIR" && npx hyperframes snapshot --at <proof-times>)

Choose proof times that show the opening state, signature move, and final hold. Inspect the generated contact or snapshot sheet before continuing. On lint, check, or snapshot failure, dispatch the repair subagent (agents/finalize.md) for one in-place fix pass, then rerun the failed gate. Never change a fixed duration merely to hide a defect.

Step 6 — Approve and render (Bash)

Ask one question: “preview first, or render?” If the user chooses preview, open Studio and return to the same approval gate after revisions:

(cd "$PROJECT_DIR" && npx hyperframes preview)

Render only after an explicit render answer:

(cd "$PROJECT_DIR" && npx hyperframes render . --skill=motion-graphics -q high -o ./renders/video.mp4)
# transparent overlay variant: --format webm  (or mov)

Verify the output exists, is non-empty, and has the intended duration. The final handoff names the artifact, actual duration, composition or frame id, proof times, and the inspected contact or snapshot sheet. Flags live in /hyperframes-clireferences/preview-render.md.

Resume table

StateContinue from
no shot-plan.jsonStep 1 (plan)
shot-plan.json has asset_needs, no assets/Step 2 (source)
shot-plan.json final, no compositions/index.htmlStep 3/4 (design+build)
compositions/index.html exists, proof snapshots absentStep 5 (verify)
checks and proof snapshots pass, no approved renderStep 6 (approval)
approved render existsverify output, then report

Design notes (maintainers — execution does not read this)

  • Asset-first rationale: sourcing is front-loaded and informs shot design (the RWA flow: analyze → search → review → compose). the search-driven categories (webpage/news/tweet) and asset-fusion both lean on media-use search (news/web/tweet/image), which is media-use's documented RWA lineage.
  • Reuse-first: the in-ecosystem analog of LLM-generated templates is "compose catalog blocks + hyperframes-animation rules". HF's paused GSAP timeline ≙ Remotion's useCurrentFrame.
  • Category module contract: one categories/<id>/module.md (planning + build), sharing references/motion-vocabulary.md (+ optional eval). Adding a category = drop the folder + register its classifier line in agents/director.md + its row in catalog-map.md; the phase pipeline is untouched.
  • Directory shape:
    videos/<project-name>/
      hyperframes.json  context.log
      shot-plan.json            # the IR (Director output)
      assets/  assets/index.md  # media-use output (if sourced)
      compositions/index.html   # Builder output
      renders/video.mp4
    
  • Registration: in hyperframes router — add the "design-led short motion graphic" intent + Workflow description; carve the motion-graphics triggers out of /general-video; add reverse Do-NOT-use edges. See motion-graphics-genre.md §5-7.

heygen-com의 다른 스킬

hyperframes-cli
heygen-com
HyperFrames CLI 개발 루프
developmenttestingapi
hyperframes-animation
heygen-com
HyperFrames의 모든 애니메이션 지식 — 원자적 모션 규칙, 다중 단계 씬 청사진, 씬 전환, 광범위한 모션 디자인 기법, 그리고 7개의 런타임 어댑터(GSAP 기본, Lottie, Three.js, Anime.js, CSS 키프레임, Web Animations API, TypeGPU). 모든 모션 또는 애니메이션 작업에 사용: 2-4개의 규칙을 선택하여 구성하거나, 청사진을 로드하거나, 런타임별 API(GSAP 이징 / Lottie 플레이어 / Three.js 믹서 등)를 조회합니다. HyperFrames 네이티브: 단일 일시 정지 타임라인, 시크 안전,...
creativedevelopmentdesign
hyperframes-core
heygen-com
HyperFrames HTML 구성 계약. 구성 구조, 데이터 속성, 클립, 트랙, 하위 구성, 변수, 미디어 재생, 결정적 렌더링 규칙 및 최소 렌더링 가능 프로젝트의 검증에 사용합니다.
developmentmediacreative
hyperframes-media
heygen-com
HyperFrames 컴포지션을 위한 에셋 전처리 — 다중 제공자 TTS(HeyGen / ElevenLabs / Kokoro 로컬), 다중 제공자 BGM(Google Lyria / 로컬 MusicGen), Whisper 전사, 배경 제거 및 캡션 작성. npx hyperframes tts, bgm, transcribe, remove-background, voice/provider 선택, music-mood 프롬프팅, captions / subtitles / lyrics / karaoke / per-word 스타일링에 사용합니다.
mediaaudiovideo
hyperframes-registry
heygen-com
레지스트리 블록과 컴포넌트를 HyperFrames 구성에 설치하고 연결합니다. hyperframes add 실행 시, 블록이나 컴포넌트 설치 시, 설치된 항목을 index.html에 연결할 때, 또는 hyperframes.json 작업 시 사용합니다. add 명령어, 설치 위치, 블록 하위 구성 연결, 컴포넌트 스니펫 병합, 레지스트리 검색, 그리고 업스트림에 기여할 새 블록이나 컴포넌트 작성(아이디어 → 스캐폴드 → 검증 → PR)을 다룹니다.
developmentapicode-review
general-video
heygen-com
사용자 정의 HyperFrames HTML 비디오 구성 제작 시 전용 워크플로가 적합하지 않을 때 대체 도구로 사용합니다. 긴 길이 또는 여러 장면의 작품, 브랜드/시즐 릴, 몽타주, 타이틀 카드, 모션 포스터, 정적 루프, 모든 길이와 형식의 자유로운 구성을 다룹니다. 마케팅 제품 프로모션(product-launch-video), 일반 웹사이트-투-비디오 캡처(website-to-video), 주제 설명(faceless-explainer), GitHub PR 비디오(pr-to-video), 기존 영상 자막 처리 등에는 사용되지 않습니다.
videocreativemedia
hyperframes-read-first
heygen-com
동영상, 애니메이션, 모션 그래픽, 설명 영상, 타이틀 카드, 오버레이, 자막 영상, 제품 홍보 영상, 웹사이트 영상, 홍보 또는 변경 로그 영상, 데이터 몽타주, 모션 포스터 또는 HyperFrames HTML 구성을 만들거나, 생성하거나, 편집하거나, 애니메이션화하거나, 렌더링하는 모든 요청에 대해 여기서 시작하세요. 사용자가 HyperFrames가 완성된 MP4/웹 동영상을 제작하거나 렌더링하도록 하거나, 워크플로를 선택하거나, 제품 출시 동영상, 얼굴 없는 설명 영상, 웹사이트-투-비디오 등 중에서 경로를 지정하려는 경우 다른 동영상 또는 애니메이션 스킬보다 먼저 사용하세요.
creativevideomedia
hyperframes-creative
heygen-com
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`.
creativedesignvideo