ASD

Motion Graphics

Motion graphic corto donde el movimiento es el mensaje: tipografía cinética, count-up, chart, logo sting, lower-third o mapa animado; sin narración, exporta a MP4 u overlay transparente.

Reemplaza a: /general-video para piezas más largas o narradas

Estrellas
40.6k

en todo el repo

Actividad
77

0–100, la ruta de este skill

Actualizado
hace 10 días

último commit aquí

Commits
18

últimos 90 días

Contexto
3.9k tok

146 tok en reposo

Paquete
23 archivos

111 KB

Instalar

Funciona con cualquier agente que lea SKILL.md

npx -y skills add heygen-com/hyperframes --skill motion-graphics --agent claude-code

Se instala solo en este repositorio.

Este skill reads environment config.

Qué hace

  • Ejecuta el pipeline plan → source → design → build → verify → render para crear un motion graphic corto y sin narración
  • Elige categoría (kinetic-type, stat, charts, logo-reveal, lower-thirds, maps, webpage, news, tweet, asset-fusion) y decide si hace falta buscar assets
  • Compone reutilizando bloques del catálogo (`npx hyperframes add <block>`) sobre `compositions/index.html` con timeline GSAP pausada
  • Verifica con `lint`, `check` y snapshots antes de pedir aprobación para renderizar a MP4 o overlay transparente

Úsalo cuando

  • Se necesita un gráfico de movimiento corto (menos de ~10s, hasta ~30s) donde el movimiento es el mensaje: tipografía, count-up, chart, logo sting, lower-third, mapa o UI animados
  • El asset a animar viene de una URL de figma.com (primero corre /figma)
  • No hay claridad sobre qué video se necesita (deriva a /hyperframes)

No lo uses cuando

  • El video es más largo, tiene narración o múltiples escenas (usar /general-video en su lugar)

Qué lo activa

Di cualquiera de estas frases y el agente debería cargar este skill.

  • Crea un motion graphic corto con un count-up de estadística y un anillo
  • Haz un logo sting con el logo de mi marca
  • Anima este tweet como un video corto
  • Haz un mapa animado que resalte estas regiones y haga zoom a una ciudad

SKILL.md

En inglés

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.

Phase Execution Primary artifact Detailed flow
init Bash hyperframes.json Step 0
plan subagent — decide search? + classify + asset strategy shot-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.md phases/source/guide.md
design subagent — shot design around resolved assets shot-plan.json (final: block(s) + layout + motion + positions) agents/director.md (Part 2)
build subagent — reuse-first composition compositions/index.html agents/builder.md
verify Bash — lint, check, proof snapshots; repair on failure snapshots/contact-sheet.jpg Step 5
approve Ask preview or render; wait for the answer explicit render approval Step 6
render Bash — hyperframes render (MP4, or --format webm/mov for overlay) renders/video.mp4 or transparent overlay Step 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:

Category Intent Leans on
kinetic-type punchy line / quote / title, motion-first text caption-* blocks + animation rules
stat single hero number / count-up + ring apple-money-count / rules/{counting-dynamic-scale, stat-bars-and-fills}
charts bar / line / pie / race / % from data data-chart block
logo-reveal logo sting / brand lockup (user logo) logo-outro / rules/svg-path-draw
lower-thirds name / title bars, callouts, social overlays caption-* + registry overlay blocks
maps geographic 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 content Category Animation
webpage / link webpage webpage / UI animation (scroll, reveal, cursor, callouts)
news article news headline reveal + source card + key-fact callouts
tweet tweet animated tweet card
image / entity asset-fusion the 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:

Key Used for Fallback
GEMINI_API_KEY / GOOGLE_API_KEY image generation (media-use resolve) skip generate / search-only
(asset_scout / search providers) webpage/news/tweet + asset-fusion real-asset search category 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

State Continue from
no shot-plan.json Step 1 (plan)
shot-plan.json has asset_needs, no assets/ Step 2 (source)
shot-plan.json final, no compositions/index.html Step 3/4 (design+build)
compositions/index.html exists, proof snapshots absent Step 5 (verify)
checks and proof snapshots pass, no approved render Step 6 (approval)
approved render exists verify 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.

Reproducido de heygen-com/hyperframes bajo licencia Apache-2.0. Leer esta página en markdown.

Archivos

23 archivos en el paquete. Solo se lee SKILL.md al activarse — las referencias se cargan si el skill decide que las necesita.

Antes de instalar

Requiere macOS Apple Silicon o Linux x64, node y ffmpeg (`brew install node ffmpeg`), `npx hyperframes doctor`, y opcionalmente claves de generación/búsqueda para ciertas categorías.

Necesita en el PATH:nodenpx

Variables de entorno:MOTION_GRAPHICS_DIRPROJECT_DIR

Detalles

Creador
heygen-com
Categoría
Diseño y UI
Licencia
Apache-2.0
Recursos incluidos
referencias
Código fuente
Ver SKILL.md

Etiquetas

Más de heygen-com/hyperframes

Este repo incluye 25 skills. Si instalas uno, normalmente ya tienes los demás.

Agent Media OS: resuelve BGM, SFX, imágenes, iconos, logos, voz, gradación de color o LUTs en un archivo local o bloque listo para usar; genera, opera y reutiliza assets en proyectos HyperFrames.

Costo de contexto al activarse
2k tok
Tamaño del paquete
152 archivos
Última actualización
hace 4 días
herramientas desarrollo

Convierte un pull request de GitHub (URL, owner/repo#N o 'este PR') en un video explicativo del cambio de código —changelog, feature, fix o refactor— construido a partir del diff, commits y archivos.

Costo de contexto al activarse
7.9k tok
Tamaño del paquete
30 archivos
Última actualización
hace 10 días
redaccion contenido

Punto de entrada obligatorio para crear, editar, animar o renderizar video, animaciones o motion graphics con HyperFrames, así como para inspeccionar, validar o publicar proyectos existentes.

Costo de contexto al activarse
3.2k tok
Tamaño del paquete
17 archivos
Última actualización
hace 15 días
diseno ui

Convierte una URL de producto o marketing, un guion pegado o un brief en un video de lanzamiento/promoción — promos SaaS, revelaciones de funciones, demos, lanzamientos de apps y empresas.

Costo de contexto al activarse
7.9k tok
Tamaño del paquete
28 archivos
Última actualización
hace 10 días
redaccion contenido

Usa el flujo de desarrollo de la CLI de HyperFrames: init, add, catalog, capture, lint, check, snapshot, compare, preview, render, publish, cloud, lambda, feedback, doctor y más; también para diagnosticar fallos de build o render.

Costo de contexto al activarse
3.9k tok
Tamaño del paquete
11 archivos
Última actualización
hace 3 días
herramientas desarrollo

Convierte texto (artículo, notas, tema o brief) en un video explicativo faceless: sin sitio ni material que capturar, los visuales se inventan por escena (tipografía, gráficos abstractos, diagramas, data-viz).

Costo de contexto al activarse
7.1k tok
Tamaño del paquete
24 archivos
Última actualización
hace 10 días
redaccion contenido

Skills relacionados

Empaqueta un video de talking-head/entrevista/podcast existente con tarjetas gráficas superpuestas (títulos, lower-thirds, callouts, citas, PiP) sincronizadas con la transcripción, en 16:9, 9:16 o 4:5; el clip se reproduce intacto debajo.

Costo de contexto al activarse
16.3k tok
Tamaño del paquete
28 archivos
Última actualización
hace 24 días
diseno ui

Porta el código de una composición Remotion (React) existente a HTML de HyperFrames. Solo para pedidos explícitos de portar/convertir/migrar una fuente Remotion, en un único sentido.

Costo de contexto al activarse
2.4k tok
Tamaño del paquete
70 archivos
Última actualización
hace 10 días
herramientas desarrollo

Úsalo cuando el usuario o el agente necesite leer, buscar o consultar la documentación o la referencia de la API de Stripe, en vez de usar curl o WebFetch para docs.stripe.com.

Costo de contexto al activarse
225 tok
Tamaño del paquete
1 archivo
Última actualización
hace 24 días
Oficialdesarrollo apis