Skills Agentes

Hyperframes

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.

Reemplaza a: Remotion (para composiciones portadas explícitamente a HyperFrames)

Estrellas
52.1k

en todo el repo

Actividad
98

0–100, la ruta de este skill

Actualizado
hace 2 meses

último commit aquí

Commits
46

últimos 90 días

Contexto
3.2k tok

198 tok en reposo

Paquete
17 archivos

61 KB

Instalar

Funciona con cualquier agente que lea SKILL.md

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

Se instala solo en este repositorio.

Qué hace

  • Actúa como punto de entrada obligatorio para crear, editar, animar o renderizar video, animaciones o motion graphics con HyperFrames
  • Resume el estado del proyecto a partir de BRIEF.md, hyperframes.json o STORYBOARD.md antes de decidir qué hacer
  • Ejecuta la capa de intención (intent-interview) para capturar el brief cuando se trata de una creación nueva
  • Selecciona e instala el workflow adecuado (slideshow, embedded-captions, talking-head-recut, music-to-video, motion-graphics, pr-to-video, product-launch-video, faceless-explainer, general-video, remotion-to-hyperframes)
  • Carga skills de dominio bajo demanda (hyperframes-core, hyperframes-animation, hyperframes-keyframes, hyperframes-creative, media-use, hyperframes-cli, hyperframes-registry, figma)

Úsalo cuando

  • Cualquier solicitud para hacer, crear, editar, animar o renderizar un video, animación, motion graphic, promo, explainer, clip con subtítulos, title card, overlay, slideshow o deck interactivo
  • Para inspeccionar, diagnosticar, validar, previsualizar, publicar o renderizar en lote un proyecto HyperFrames existente
  • Para portar un proyecto Remotion existente a HyperFrames
  • Cuando el input es una URL de sitio, un PR de GitHub, un diseño o URL de Figma, un brief de texto, footage existente o música

No lo uses cuando

  • El usuario elige explícitamente otro framework de salida distinto de HyperFrames
  • El usuario pide únicamente grabar una sesión de navegador

Qué lo activa

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

  • “Quiero hacer un video promocional de mi sitio web a partir de esta URL”
  • “Añade subtítulos a este clip de talking-head sin cambiar el footage”
  • “Convierte esta composición de Remotion a HyperFrames”
  • “Diagnostica por qué falla el render de este proyecto HyperFrames”
  • “Crea una presentación interactiva tipo pitch deck con HyperFrames”

SKILL.md

En inglés

HyperFrames entry point

HyperFrames renders video from HTML — a composition is an HTML file whose DOM declares timing with data-* attributes, whose animation runtime is seekable, and whose media playback is owned by the framework. The full authoring contract lives in /hyperframes-core; read it before writing composition HTML.

1. Start from project state

Apply the first matching row; do not evaluate lower state rows:

State Action
Explicit port of existing Remotion source to HyperFrames Read references/routes/remotion-to-hyperframes.md, then route directly to that workflow. Skip the intent layer.
Specific operation on an existing HyperFrames project: inspect, diagnose, validate, preview, render, publish, or batch-render Perform only that operation. Skip intent and workflow routing; load /hyperframes-cli and any required domain skills.
Specific edit to an existing project Make the edit. Do not run the intent layer.
BRIEF.md exists Read workflow and flow. Execute that workflow; flow: companion always executes in /general-video. Ask no brief questions.
No brief, but hyperframes.json or STORYBOARD.md exists Resume from project files and recorded preferences. Infer the owning workflow from existing artifacts. If it cannot be determined uniquely, ask one routing-only question; do not run the intent interview.
Fresh creation Run the intent layer — references/intent-interview.md — then route once using § 2's table.

If a fresh request does not identify the subject or input, ask what the video is about before routing. Check preferences and recipes before asking anything (references/intent-interview.md, step 1). A figma.com input or a named recipe changes intake, not routing — the interview's "Adapt orthogonal inputs" section handles both.

Keep the project's CLI current

A scaffolded project pins hyperframes@<version> in its package.json scripts so renders stay reproducible; the pin never advances on its own, and a pinned run of an older CLI prints no warning about it. When resuming a project whose scripts carry a pin, probe once before the first render-affecting command:

npx hyperframes@latest upgrade --project . --check

The probe is read-only and reports the pin against the latest release; keep the explicit . — on older CLI releases a bare --project followed by another flag consumes that flag as its directory value. When it reports the project behind — or any CLI output already shows it (the stderr notice This project pins hyperframes@… (latest …), or _meta.updateAvailable: true in a --json result from a pinned script) — apply with npx hyperframes@latest upgrade --project ., then verify with npx hyperframes check. A passing check confirms the project's compositions still validate on the new version — not that rendered output is frame-identical to the old pin — so a successful bump is never silent: name the old and new version in the run's summary. A project with no composition yet needs no verification. If the check fails, revert the package.json change, continue on the pinned version, and report which version the project stays on and why. Act on the signal rather than relaying it to the user; never leave a bumped pin unverified.

2. Route fresh creation

Use the first matching row. Match the requested deliverable, not a word or file type mentioned in passing.

Priority Request Workflow
1 Explicitly port an existing Remotion source /remotion-to-hyperframes
2 Author a presentation, pitch deck, or navigable interactive deck /slideshow
3 Add plain captions or subtitles to existing talking-head footage without changing it /embedded-captions
4 Add designed graphic overlays to existing talking-head, interview, or podcast footage without changing the footage /talking-head-recut
5 Build a beat-synced video from a music track, with no narration or website capture /music-to-video
6 Create an explicitly short, unnarrated, motion-first unit, typically under 10s /motion-graphics
7 Explain a GitHub pull request or code change from a PR reference /pr-to-video
8 Market or showcase a website, product site, app, or company from a URL or site-specific brief /product-launch-video
9 Explain a topic, article, or notes with invented visuals and no product or site capture /faceless-explainer
10 Any other custom video or composition /general-video

Before finalizing the route, read references/routes/<workflow>.md — one small file per route: the canonical input/output/trigger contract (available before lazy-installed workflow skills are present) plus that route's interview entry. If the candidate does not satisfy its contract, continue routing instead of forcing the match. Read only the matched route's file.

Resolve common ambiguities

  • A short animated title, logo sting, stat hit, chart hit, map hit, or standalone lower-third is /motion-graphics when it is unnarrated and motion is the message. A static title card, narrated sequence, longer montage, or custom loop is /general-video.
  • An explicitly short motion graphic may use a URL, tweet, article, or screenshot as source material. A generic "make a video from this site" request is /product-launch-video.
  • Existing footage with captions routes to /embedded-captions; footage with designed information cards routes to /talking-head-recut. Retiming, reordering, recoloring, reframing, or remixing footage is a custom edit and falls through to /general-video.
  • A music file selects /music-to-video only when its beat grid drives the piece. Music used as a bed does not override the subject-matched route.
  • "I want a storyboard" changes the review process, not the workflow. With no other routing signal, use /general-video. A confirmed sketched board may itself be the requested deliverable; the review loop defines that stop point.
  • Specialized narrative workflows support up to about 3 minutes and are strongest around 30–90s. Route a clearly longer piece to /general-video. Length never overrides an explicit port, deck, caption, overlay, or music-driven deliverable.

3. Route once, then leave

For fresh creation the intent layer (references/intent-interview.md) runs the full conversation — memory, triage, pitch round, must-haves, run-shape, hand-off — and ends by writing BRIEF.md. The brief is the only routing artifact the workflow reads; nothing later re-opens this skill or the interview. Answer every later "what did the route require?" from BRIEF.md.

4. Install and enter the workflow

Before reading the selected workflow, install or refresh it and the core domain skills:

npx hyperframes skills update <workflow-name>

Use the bare name without /. If the command fails, surface the error; do not reconstruct the workflow from memory. Everything else about installation — the core-vs-lazy split, what init refreshes, diagnosis, CI opt-out, and the no-CLI fallback — lives in references/skill-lifecycle.md.

5. Load domain skills on demand

Need Skill
Composition structure, timing attributes, tracks, variables, determinism /hyperframes-core
Motion rules, scene blueprints, transitions, runtime adapters /hyperframes-animation
Seek-safe GSAP, CSS, Anime.js, WAAPI, FLIP, paths, masks, SVG, 3D keyframes, or hyperframes keyframes diagnostics /hyperframes-keyframes
Design specs, concept, palette, typography, narration, beat planning /hyperframes-creative
Images, icons, logos, audio, captions, grades, LUTs, reusable media /media-use
Init, lint, check, snapshots, compare, batch render, Studio, render, publish, or diagnostics /hyperframes-cli
Registry blocks and components /hyperframes-registry
Figma assets, tokens, components, or storyboard frames as reconstructed motion /figma

Broad feedback about how photographic media looks or behaves also routes to /media-use, even when the user never says “color grading” or “effect”: fix dark/flat/boring footage, stylize a clip, hide a face, or improve a media reveal. Read ../media-use/references/media-treatments.md before editing a treatment; it governs how footage is treated, never whether media may be used. Do not substitute a generic LUT, CSS filter/overlay, or opacity tween for an existing canonical treatment primitive. Keep text/layout/motion-only edits in their owning domain. During a build with important photographic media, include one grounded media-polish scan in the final quality pass; leaving suitable media unchanged is a valid result.

Domain skills never take ownership of the end-to-end deliverable. Load only what the active workflow needs.

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

Archivos

17 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 el CLI de hyperframes (npx hyperframes) y, según el workflow, artefactos del proyecto como BRIEF.md, hyperframes.json o STORYBOARD.md.

Necesita en el PATH:npx

Detalles

Creador
heygen-com
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. Ver el pack hyperframes entero y su comando de instalación

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
el mes pasado
video

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 2 meses
video

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 2 meses
video

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
el mes pasado
video

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 2 meses
video

El contrato de composición de HyperFrames: cómo construir un proyecto renderizable con atributos `data-*`, `class="clip"`, tracks, sub-composiciones, variables y reglas de renderizado determinista.

Costo de contexto al activarse
2.6k tok
Tamaño del paquete
19 archivos
Última actualización
hace 2 meses
video

Skills relacionados

Doctrina de overlay para captions embebidos: el modelo drop/rail/embed y la regla de que los captions son un overlay compuesto sobre el film, nunca una banda inferior reservada.

Costo de contexto al activarse
1.5k tok
Tamaño del paquete
1 archivo
Última actualización
hace 2 meses
video

Convierte un changelog .md semanal en un video de marca terminado (cuadrado 1080, ~45-60s, voz de Annie, fondo animado, mock-UI, captions lowkey). Autocontenido: fuentes, fondo, léxico y scripts incluidos.

Costo de contexto al activarse
3.3k tok
Tamaño del paquete
15 archivos
Última actualización
hace 2 meses
video

Añade subtítulos o captions a un vídeo de un solo sujeto hablando a cámara sin editar el metraje, usando el catálogo de 35 identidades visuales.

Costo de contexto al activarse
8.1k tok
Tamaño del paquete
138 archivos
Última actualización
el mes pasado
video