Communitygithub.com

bassam1998new-ops/hyperframes-students

Construye un vídeo con el estilo Hatch Cosmos: un mundo dibujado a lápiz con un bloc de personajes que camina, mira, parpadea y hace ^ ^, y un plano secuencia que entra por su ojo hacia una galaxia hatchada.

¿Qué es hyperframes-students?

Este skill permite generar vídeos animados en el estilo visual «Hatch Cosmos», que combina un acabado dibujado a lápiz (hatching diagonal) con personajes bloc (mascotas) y un movimiento de cámara característico: la inmersión a través del ojo de la mascota hacia una galaxia hatchada. Está diseñado para plataformas como Claude Code, Cursor o Codex, y se basa en un kit de herramientas JavaScript (`HATCH.kit`) que gestiona la construcción de formas, la animación con GSAP y la composición de escenas. El skill incluye pautas estrictas sobre el uso del color (según la marca), la disposición en formatos 9:16 y 16:9, el rigging de la mascota (caminar, mirar, parpadear, saludar) y un bucle de revisión de calidad («judge loop») que compara fotogramas con referencias mediante herramientas CLI (`hyperframes`). Es ideal para intros conceptuales con mascota, bumpers de canal o vídeos musicales de tipo «journey inside». No está pensado para vídeos de cabezas parlantes, grabaciones reales de pantalla, explicaciones densas o looks fotográficos.

Compatible con~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/bassam1998new-ops/hyperframes-students/tree/HEAD/.claude/skills/style-hatch-cosmos

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

Documentación

Estilo: Hatch Cosmos

Un cálido cosmos dibujado a mano: rellenos planos bajo un sombreado diagonal corto a lápiz, delineados a tinta, un bloc de mascota que actúa, y UN movimiento característico: la cámara se sumerge en el ojo de la mascota, el ojo se convierte en una ventana con forma de teléfono, y la siguiente escena aparece. Tarjeta: video-projects/_library/styles/hatch-cosmos/style.md (estado borrador — díselo al propietario hasta que lo apruebe en el tablero).

Primero mira (en la carpeta de estilos): frames/01-pair-happy-eyes.png · frames/02-eye-window-dive.png · frames/03-deep-galaxy.png · frames/04-paper-walk.png. Referencia (solo visual): refs/ref-contact-sheet.jpg (no en el repo público), refs/ref-dive-30fps.jpg (no en el repo público). Los colores siguen la marca: tests/2026-10-02-themes-and-looks.jpg (no en el repo público).

0. Aplica primero la tarjeta

node tools/vid.mjs style apply hatch-cosmos <project> [--mode calm|punchy]
node tools/vid.mjs style show hatch-cosmos

Luego lee el README del kit: video-projects/_library/assets/kits/hatch/README.md. No dibujes a mano lo que ya tiene el kit.

1. Colores = roles (la marca asigna el hex)

El estilo es calidad y movimiento. Nunca envíes el naranja / espacio de referencia a menos que la marca lo indique. HATCH.kit({ theme: "<name>" | { …tokens } }):

TokenRolDe la marca
canvas / haloespacio, halo de la galaxialienzo / superficie
inkcontornos, ojos, lápiz oscurotext-strong (el más oscuro)
paper / lighthoja de papel, líneas de lápiz pálidolienzo claro / blanquecino
hero / buddylos dos cuerpos de la mascotaprimary / surface o secondary
a1..a6anillos, puntos, planetas, rayos — a2 hace las masas GRANDESacentos de marca; a2 = uno tranquilo, nunca el color de "puntuación"
cloudsrellenos de nebulosaomitir → derivado (nunca se asigna manualmente)
Guardados: cosmos (referencia, solo pruebas), midnight. El sombreado / luz / brillo de la mascota se derivan del color del cuerpo.

2. Constrúyelo

  • Empieza desde un bloque de demostración (copia hatch.js, GSAP, el whoosh):
    node tools/vid.mjs use hatch-cosmos-9x16 <project>    # _library/compositions/portrait/hatch-cosmos-9x16.html (6 s)
    node tools/vid.mjs use hatch-cosmos-16x9 <project>    # _library/compositions/hatch-cosmos-16x9.html (6 s)
    
    Conecta el <div … data-composition-src=…> impreso con data-variable-values='{"theme":"<brand>","look":"space|paper"}'. vid use conserva los archivos existentes — después de una actualización del kit, copia hatch.js de nuevo. Renders de demostración: styles/hatch-cosmos/tests/demo-9x16-20261002.mp4, demo-16x9-20261002.mp4.
  • Una nueva escena con el kit (un <canvas class="clip" data-layout-allow-overflow> por composición):
    1. var K = HATCH.kit({ w, h, seed, theme }) — luego construye CADA forma una vez, en un orden fijo (el rng se consume en el orden de construcción): K.blob, K.planet, K.stars, K.galaxy(), K.travel({ ys, xs, look }), K.mascot(...), K.speed().
    2. Un proxy tween de GSAP {t:0→DUR} con onUpdate → draw(t); registra window.__timelines[id] en línea en el HTML (el linter debe verlo).
    3. draw(t) busca el canvas de forma perezosa (el bundler puede mover los scripts), dibuja solo a partir de t, termina con K.lift(ctx, 3).
    4. Montaje de escenas = nuevas funciones draw sobre las mismas partes del kit (blobs, anillos, planetas, destellos, contornos K.wobble); cámbialas con cortes duros o una inmersión.
  • Rig de la mascota: var m = K.mascot({ role: "hero", radius: 7, mark(c, BW, BH) }); K.drawMascot(c, m, x, y, scale, state) con state = { walk: t, walkAmt, legWiggle, look -1..1, eyes: "open"|"happy"|"blink", wave, waveSide, zoom: camScale, glowAmt }. Actúa en ventanas pequeñas (HATCH.win, HATCH.sstep): mira al compañero → ^ ^ (~0.6 s) → parpadeo → saludo. glowAmt: 0 sobre papel. Logos en la mascota solo cuando la marca lo indique.
  • La inmersión: var D = K.dive({ z0, z1, smax: 160, eyeScale, centre, target: t => K.eyePoint(x, y, scale, -1), inner: { start, end, zEnd, fitK, roll: -0.9 } }), luego por fotograma D.frame(ctx, t, drawOuter, drawInner, K.speed(), grain). Los valores por defecto coinciden con la referencia: estabiliza la caminata 0.45 s antes de z0, empuja ~0.85 s, la ventana cubre ~0.8 s dentro, la escena interior se estabiliza al final. Whoosh sfx/el/whoosh-tonal.mp3 en z0 − 0.15.
  • Diseño 9:16 (1080×1920): par centrado en la zona segura (510, 860), escala 1.2, separados 410 px; centre: [510, 860] para que el ojo y el núcleo de la galaxia caigan dentro de x 60–960, y 220–1500; travel ys 1.6, xs 0.6. El 20% inferior solo fondo.
  • Diseño 16:9: par en (CX ∓ 270, CY + 10), escala 1.35; galaxy zEnd 1.35.
  • Ritmo: introducción tranquila 4–6 s, inmersión 1.2 s, montaje cada 1–2 s, una pausa de 3–5 s, zoom de salida hacia la mascota para terminar (el JSON de la tarjeta tiene los tokens de movimiento).
  • Sonido: liderado por música — una base ligera y juguetona del catálogo de música / bgm de _library (nunca generar música); whoosh en cada inmersión; voz a −14 LUFS si la hay.

3. El bucle de juez (el propietario quiere "exactamente la misma calidad")

  1. npx hyperframes lint + npx hyperframes check dentro del proyecto — 0 errores.
  2. npx hyperframes snapshot --at <walk, mid-dive, window, settled> — Lee cada fotograma.
  3. npx hyperframes render --quality draft → node tools/vid.mjs judge <mp4> → Lee sheet.jpg y safe-sheet.jpg; busca fotogramas planos (hubo una vez un fallo de captura puntual — vuelve a renderizar, no toques el código si las instantáneas se ven bien).
  4. Contra la referencia: pares a tamaño completo coincidentes (caminata, inmersión intermedia, galaxia) + recortes al 100% (sombreado sobre un blob, anillo + planeta, destellos, contornos, la mascota) + una tira de 10 fps de la inmersión para ambas. Muestra los colores con ffmpeg (medianas por región), no a ojo.
  5. Escribe tests/<date>-judge-round-N.md — una línea por elemento, veredicto igual / diferente / no se puede comparar (por qué). Arregla cada "diferente", vuelve a renderizar, vuelve a juzgar (máximo 5 rondas). Porcentaje de coincidencia honesto para look y movimiento en el informe.

Hacer / No hacer

  • Hacer: roles de marca; construir una vez, dibujar desde t; sombreado fijo a las formas y fino al hacer zoom; actuar antes de cada inmersión; zona segura en 9:16; recortes al 100% en el juez.
  • No hacer: colores de referencia en una marca que no los usa; texto dibujado dentro del canvas (las palabras van fuera, enteras, nunca divididas por letra); Math.random / Date.now; sombreado hirviente o grueso; créditos en este look; aprobar la tarjeta tú mismo.

Después del trabajo: node tools/vid.mjs style comment hatch-cosmos "<lo que funcionó o no>".

Individual skills in this repo

This repo contains 14 individual skills — each has its own dedicated page.

bassam1998new-ops/hyperframes-students

Make a new video with a beginner, start to finish — a few easy questions, pick a look from this repo's styles, build it with HyperFrames, check the frames, render and show it. Use when the student says "new video", "make a video", "اعمل فيديو", "عايز فيديو", "reel", "animation", or asks how to start a video. Hands the technical HyperFrames rules to the official hyperframes skills.

bassam1998new-ops/hyperframes-students

First-time setup for the HyperFrames student studio. Checks the computer (Git, Node.js, FFmpeg, the render browser), explains in plain words what is missing, recommends what to install, asks before installing anything, then makes a 3-second test video to prove it all works. Use when the student says "setup", "install", "اعمل setup", "نزّل البرامج", "it doesn't work", "command not found", when node_modules is missing, or when `npx hyperframes doctor` shows a red item. Safe to run again any time — it skips what is already done.

bassam1998new-ops/hyperframes-students

Build a video in the Amber Grid Newsroom look (style card amber-grid-newsroom) — a hot "breaking news" desk: near-black grid field, the real screen recording in a framed window with instant reframes, an English title over an Arabic title line, and karaoke captions where the spoken word turns hot. Use when the director picked this card, or the owner says "make it in the amber newsroom style", "news desk", "breaking news look", "زي ريل opus 5.5", "ستايل الأخبار", or the video is AI news or a build show-off cut from his OBS screen recording with an Egyptian Arabic voice-over. 9:16 reels. Not for lecture clips or direct offers.

bassam1998new-ops/hyperframes-students

Build a video in the Cream Caret Type look (style card cream-caret-type) — Arabic words typed with a coloured caret on a flat two-colour page (night and paper that swap on hard cuts), select-highlight → delete → retype, a flat profile silhouette, one coloured dot that match-cuts into a flat vector eye, a zoom-through the iris, a fixed noun with a bold verb swapping every 16 frames, a pixel-art icon on the sign-off and a monogram end card — one sound per event, silence between. Use when the director picked this card, or the owner says "the typing intro", "caret type", "cream caret", "زي فيديو الكتابة", "الكلام اللي بيتكتب", "intro بالكتابة", or the video is a channel / "who am I" intro, a course or service intro hook, a short opener before a talking head, a word-play promise line or a bumper. 9:16 only, Arabic-first. Not for talking heads the whole time, screen-recording proof, data-heavy explainers or full spoken subtitles. DRAFT — untested.

bassam1998new-ops/hyperframes-students

Build a video in the Floating Desk Zoom look (style card floating-desk-zoom) — real app windows float as cards on warm paper, a virtual camera hard-cuts in on the action, follows the typing and glides back out. Use when the director picked this card, or the owner says "make it in the floating desk style", "paper desk", "zoom on the screen like the launch video", "اعمله على الورق", or the video is a build show-off, quick tutorial or AI news made from his OBS screen recording with a voice-over. Arabic or English; 9:16 reels. Not for lecture clips or talking heads.

bassam1998new-ops/hyperframes-students

Build a video in the Horizon Prompt One-shot look (style card horizon-prompt-oneshot) — one continuous camera on a near-black stage lit by a soft planet-horizon glow; a glass app bar, a cursor and a prompt box morph into each other, a prompt is typed, the send button grows into a tile that blooms into a full-frame result, then a light wipe to a logo end card, every beat hit-synced to a UI sound. Use when the director picked this card, or the owner says "horizon prompt", "the prompt one-shot", "the ChatGPT-style promo", "زي فيديو البرومبت", "الكيرسر اللي بيكتب البرومبت", or the video is an AI tool show-off / prompt-to-result demo, a course or service promo opener, a launch teaser or a channel bumper. Not for talking heads, real screen-recording proof, data-heavy explainers or long tutorials. DRAFT — untested.

bassam1998new-ops/hyperframes-students

Remix 2+ existing style cards of the Hyperframes video workspace into one NEW draft style card, layer by layer (palette roles, type, texture, grade, camera, light, edit rhythm, transitions, motion, sound, prompt parts), then let the owner pick the skills for the video and start the director. Use when the owner says "hybrid style", "remix styles", "mix two styles", "combine styles", "اعمل هايبرد", "ادمج الستايلين", or ticks cards and presses "Remix these" on the Styles board.

bassam1998new-ops/hyperframes-students

Build a video in the Midnight Kinetic Type look (style card midnight-kinetic-type) — clean motion type on a flat dark field, word-by-word mask rises, one accent word that lands alone, icon strokes that draw on, and hard cuts on the music's beat grid. Use when the director picked this card, or the owner says "make it in the kinetic type style", "midnight type", "like an earlier project", "تايبوجرافي متحركة", or the video is a direct offer, proof / results reel or AI news told with type, music and SFX (no face, no footage). Arabic (Cairo, per-word) and English (Inter) versions; 9:16 reels. Not for lecture clips or quick tutorials.

bassam1998new-ops/hyperframes-students

Build a video in the Midnight Screen Desk look (style card midnight-screen-desk) — a calm, organised news desk in three fixed zones: an Arabic info card on top, the real screen recording in a glowing band with punch-ins in the middle, and word-by-word captions (dim → bright) below. Use when the director picked this card, or the owner says "make it in the screen desk style", "three zones", "like the AI releases reel", "كارت فوق والشاشة في النص", or the video is AI news, a build show-off or a quick tutorial cut from his screen recording with an Egyptian Arabic voice-over. 9:16 reels. Not for lecture clips or direct offers.

bassam1998new-ops/hyperframes-students

Build a video in the Mint Lecture Room look (style card mint-lecture-room) — a calm classroom cut of a real lesson: one long take with slow zooms that follow the point, a topic lower third, a quiz card that asks, counts down think-time and then answers, and karaoke captions that light the current word. Use when the director picked this card, or the owner says "make it in the lecture room style", "lecture clip", "course cut", "quiz card", "قص من المحاضرة", "سؤال وجواب", or the video is a lecture clip or quick tutorial cut from his AI course recordings (Egyptian Arabic). 9:16 reels. Not for AI news or direct offers.

bassam1998new-ops/hyperframes-students

Build a video in the Neon Node Explainer look (style card neon-node-explainer) — a plain stage, one headline per spoken sentence, and one small glowing diagram (tiles, lines, packets, checks, terminal, tool list) that builds itself part by part. Use when the director picked this card, or the owner says "make it in the neon node style", "node explainer", "API vs MCP style", "اعمله زي فيديو الـ MCP", or the video is an AI explainer, concept explainer, quick tutorial or AI news with a voice-over and no face. Arabic headlines + English mono labels; 9:16 and 16:9 both built. Not for talking heads, warm stories, real screen-recording demos or music-only hype reels.

bassam1998new-ops/hyperframes-students

Build a video in the Swiss Motion Reel look (style card swiss-motion-reel) — a Swiss-grid "instrument panel" with a constant thin HUD, flat 2-colour blocks, word slams, shape match-cuts and hard cuts on a 128 BPM beat. Use when the director picked this card, or the owner says "make it in the Swiss style", "motion reel", "like the motion designer reel", "HUD reel", "ستايل سويسري", or the video is a brand sizzle, product intro, "what we do" reel, launch teaser or any no-person, graphics-only, music-led video. Latin display type with Arabic in a clean geometric sans; built and tested in 16:9, 9:16 still to build. Not for talking heads, screen-recording tutorials or long voice-led explainers.

bassam1998new-ops/hyperframes-students

Build a video in the Warm Glass Face-cam look (style card warm-glass-facecam) — the presenter talks to camera while frosted-glass panels with one warm glow land exactly where he points; blur-punch text, a karaoke pill, small charts, and a shrink into a rounded picture-in-picture for the demo part. Use when the director picked this card, or the owner says "make it in the warm glass style", "glass panels over my face", "face-cam with glass cards", "PiP intro", "كروت زجاج وأنا بتكلم", or the video is a build show-off or quick tutorial with the owner on camera. Source is English 16:9; the 9:16 and Arabic versions still have to be built at the first job. Not for lecture clips or AI news.

bassam1998new-ops/hyperframes-students

Build a video in the <Style name> look (style card <slug>). Use when the director picked this style card, when the owner says "make it in the <Style name> style", "<slug>", "استايل <Style name>", or the video type is <video types from use_when>. Works for Arabic (Egyptian) and English, 9:16 reels<, and 16:9 if supported>. Not for <avoid_when>.

Skills relacionados