Communitygithub.com

oyi77/1ai-skills

Create short, unnarrated, design-led motion graphics (~under 10s) using HyperFrames. Use when the user wants kinetic type, stat/chart hits, logo stings, lower-thirds, animated tweets/headlines, or transparent overlay motion graphics. MP4 or transparent overlay output. Teaches seek-safe keyframe authoring and the 2-3 transition budget rule.

What is 1ai-skills?

1ai-skills is a Claude Code agent skill that create short, unnarrated, design-led motion graphics (~under 10s) using HyperFrames. Use when the user wants kinetic type, stat/chart hits, logo stings, lower-thirds, animated tweets/headlines, or transparent overlay motion graphics. MP4 or transparent overlay output. Teaches seek-safe keyframe authoring and the 2-3 transition budget rule.

Works with~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/oyi77/1ai-skills/tree/HEAD/content/hyperframes-motion-graphics

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Overview

This skill produces motion-graphics sequences — animated titles, transitions, and kinetic elements — as HyperFrames compositions. Use it for brand stings, intro cards, or animated data callouts. It renders frame-accurate MP4 output from the HTML/CSS animation timeline.

HyperFrames — Motion Graphics

Short, unnarrated, design-led motion graphics (~under 10s). Kinetic type, stat hits, logo stings, lower-thirds, animated headlines. MP4 or transparent overlay.

When to Use

  • User wants a kinetic type animation (text that moves with energy)
  • User wants a stat/chart hit (animated number or data visualization)
  • User wants a logo sting (short brand animation, <5s)
  • User wants a lower-third (news-style name/title overlay)
  • User wants an animated tweet/headline (social media motion graphic)
  • User wants a transparent overlay (video overlay with alpha channel)

When NOT to Use

  • User wants a full video with narration (use hyperframes-product-launch-video)
  • User wants an explainer with voiceover (use hyperframes-faceless-explainer)
  • User wants a talking-head video (use hyperframes-embedded-captions)
  • User wants a product showcase (use hyperframes-product-launch-video)

Workflow

1 · Plan (≤10s total)

  • Single concept: one stat, one logo, one headline
  • Budget: entry ≈ 1-2s, hold ≈ 5-7s, exit ≈ 1-2s
  • Pick a transition vocabulary: only 2-3 inter-scene transitions per film (repeat them)

2 · Author seek-safe keyframes

All animations must be seekable — same frame at same time, every render. No wall-clock dependencies.

GSAP (recommended):

const tl = gsap.timeline({ paused: true });
tl.fromTo("#stat-number", { scale: 0.5, opacity: 0 }, { scale: 1, opacity: 1, duration: 0.8, ease: "back.out(1.7)" }, 0);
tl.to("#stat-number", { scale: 1.1, duration: 0.3, ease: "power2.out" }, 1.0);
window.__timelines = { main: tl };

CSS keyframes:

@keyframes countUp {
  from { opacity: 0; transform: translateY(20px); }
  to { opacity: 1; transform: translateY(0); }
}
.stat { animation: countUp 0.6s cubic-bezier(0.16, 1, 0.3, 1) forwards; }

3 · Stage ground

#root must be opaque (background: var(--canvas-deep, var(--canvas, #000))) — the mid-window cut opens a summed-opacity < 1 window that flashes white otherwise.

4 · Transitions (the 2-3 budget)

Default boundary: cut-the-curve in the current's direction (LEFT). Use only 2-3 transition types per film.

TechniqueScopeAxisTravel
Cut the CurveBetween scenesX/Y~12% frame (±230px at 1920)
Zoom-ThroughWithin-scene text swapZ (toward)scale 1→1.2 then 0.75→1
Inverse ZoomArrival/payoffZ (away)scale 1→0.8 then 1.25→1
Waterfall CutText-to-text seamX, per-word±230px stagger

5 · Render

npx hyperframes render --output motion-gif.mp4 --fps 30

For transparent overlay:

npx hyperframes render --output overlay.mp4 --format prores_4444

Anti-Rationalization Table

RationalizationReality
"I'll use 5 different transitions"Budget is 2-3 per film — repetition creates cohesion
"I'll add bounce/elastic to everything"Forbidden eases: bounce.out / elastic.out as sustained motion
"I'll start each element from rest"Entry must be mid-flight (≥50% through notional path)
"I'll use idle animations to fill time"Every phase performs — staged reveals, camera with intent, or sequenced UI
"I'll center at 42% to leave room for captions"Captions are overlay — center on true center (y = H/2)
"I'll use a white background for transparency"Transparent overlay needs alpha channel, not white

Verification

  • Total duration ≤ 10s
  • Only 2-3 transition types used
  • All animations are seekable (deterministic)
  • Stage ground is opaque
  • No idle wobble — every phase performs
  • Text-scale blur ≤ 10px (not 20px)
  • Output format matches use case (MP4 vs ProRes 4444)

Individual skills in this repo

This repo contains 9 individual skills — each has its own dedicated page.

oyi77/1ai-skills

Turn a weekly changelog .md into a finished branded changelog video using HyperFrames. Use when the user provides a changelog/digest markdown and wants the weekly video, or says 'changelog video'. Self-contained — fonts, background, lexicon, and scripts ship in the skill. Produces square 1080, ~45-60s videos with animated brand mock-UIs.

oyi77/1ai-skills

The transition technique catalog for HyperFrames videos — five velocity-matched SEAMS (zoom-through, inverse zoom-through, cut-the-curve, waterfall cut, rack-focus blur-cut) plus in-scene techniques (waterfall entry, nudge curve). Covers partial-travel velocity matching, Z scale-sign rule, size-scaled blur, the 10/65/25 slide ratio, and the 2-3 transition budget. Read before authoring any transition, text-beat handoff, or kinetic text entry.

oyi77/1ai-skills

Add captions/subtitles to talking-head or launch videos using HyperFrames. Use when the user wants embedded captions, verbatim caption rails, or cinematic text behind the subject. Covers the drop/rail/embed caption model, the overlay law (captions are NOT a reserved band), matte occlusion for embedded climaxes, and word-timestamp alignment from TTS output.

oyi77/1ai-skills

Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video using HyperFrames. Use when the user wants a topic explainer, concept breakdown, how-to, or listicle with no product/website to capture. Every visual is invented per scene (typography, abstract graphics, diagrams, data-viz). Not a video built from a website (use hyperframes-product-launch-video).

oyi77/1ai-skills

The fallback HyperFrames workflow for anything that doesn't fit other skills — longer multi-scene pieces, brand/sizzle reels, title cards, static loops, freeform compositions. Input- and length-agnostic. Also the home of companion mode (co-create with the full toolbox). Use when no other HyperFrames skill matches, or when the user wants a freeform video.

oyi77/1ai-skills

Turn a music track into a beat-synced HyperFrames video — lyric, slideshow, or kinetic promo. Use when the user provides an audio file, a video to pull audio from, or a mood brief for generated music. Music drives pacing. Teaches beat-map extraction, section-based scene planning, and audio-reactive visuals.

oyi77/1ai-skills

Create product launch videos from a URL, brief, or script using HyperFrames (HTML→MP4). Use when the user wants a product launch video, site tour, social clip featuring a product's own visuals, or marketing/promoting a product. Up to ~3 min (sweet spot 30-90s). Teaches the HyperFrames production loop: plan → write HTML → wire seekable animations → add media → lint → preview → render.

oyi77/1ai-skills

The Video Production Manager — manages ALL video production under 1ai-content. Delegates to HyperFrames, Remotion, AI video, and FFmpeg based on the task. Has memory via 1ai-hub brain, follows 1ai-rules, and reports to Content Director. Use when the user says 'make a video', 'create video', 'edit video', 'video strategy', or needs any video production work.

oyi77/1ai-skills

Agent skill at content/video/gen/SKILL.md

Related Skills