Agent skill · Testing & QA

hyperframes-video-composition

Provider-independent production workflow for AI agents assembling generated or source media into HyperFrames HTML/CSS/JS videos. Use for HyperFrames composition planning, scene architecture, media custody, animation/timing, captions/audio, deterministic preview/render QA, accessibility/flashing checks, provenance ledgers, and delivery handoff.

Calesthio43,316★ · +2,384/wk · 2 repos on radarProfile →
claude-codecodexcopilotcursorships scriptsMIT
Install
npx skills add calesthio/generative-media-skills --skill hyperframes-video-composition --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 6
SKILL.md size: 28 KB
Bundled scripts: yes
Path: skills/production/runtime-assembly/hyperframes-video-composition/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 112 · +8 this week
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Instructs the agent to assemble approved assets (images, clips, narration, music, captions, UI captures, generated assets, or brand material) into a finished HyperFrames video. It treats HyperFrames as a production composition runtime, where the agent owns intake, frame/design spec, media custody, timing, QA, provenance, and handoff.

How it works

  • Guides intake and design of a frame before coding, specifying canvas properties (width, height, fps, aspect ratio, safe regions, bleed).
  • Defines a visual system, typography, layout grammar, scene density, motion grammar, and audio grammar for the composition.
  • Requires planning scene architecture as timed scenes/layers with scene_id, start, duration, end, purpose, visual, text, media, audio, animation, accessibility, qa.
  • Specifies HyperFrames authoring contract details: HTML-based timing via data-start, data-duration, data-track-index; ensure class="clip" on timed elements; enable preview via npx hyperframes preview and render via npx hyperframes render.
  • Describes media import and custody with an asset manifest containing asset_id, type, source, path, rights_status, generation_metadata, transformations, technical, scene_links, provenance; includes empirical checks like ffprobe and local asset paths.
  • Covers timeline, duration, aspect, and fps decisions, frame-bound conversion, and safe-area considerations with production heuristics.
  • Outlines animation principles (entrance, emphasis, transition, exit) and limits on motion (no random seeds, no infinite loops, no distracting motion).
  • Details typography, captions, accessibility per WCAG 2.2, including caption strategies (open vs sidecar), contrast requirements, and flashing limits.

When to use it

Use when the job is to assemble images, clips, narration, music, captions, UI captures, generated assets, or brand material into a finished HyperFrames video. Apply when you need to plan frames, enforce media custody, timing, QA, provenance, and delivery handoff as part of a production workflow.

What it can touch

  • Asset manifest fields: asset_id, type, source, path, rights_status, generation_metadata, transformations, technical, scene_links, provenance.
  • HTML/CSS/JS HyperFrames composition structure, including examples with data-start, data-duration, data-track-index attributes and class="clip" timings.
  • Tools: npx hyperframes (for preview and render) and ffprobe for asset checks.

Caveats

  • Volatile facts note: HyperFrames CLI commands, package names, Node/FFmpeg requirements, registry block names, cloud render support, browser capture behavior, platform delivery specs, and social platform safe areas can change. Re-check installed package docs, npx hyperframes --help, npx hyperframes doctor, and target-platform delivery docs at production time.
  • Production stance emphasizes separating documented facts, empirical observations, and production heuristics; escalate rights/licensing and provenance concerns as needed.
From the SKILL.md

# HyperFrames video composition Use this skill when the job is to assemble images, clips, narration, music, captions, UI captures, generated assets, or brand material into a finished HyperFrames video. Treat HyperFrames as a production composition runtime, not just a code target: the agent owns intake, the frame/design spec, media custody, timing, QA, provenance, and handoff. This skill is provide

More from generative-media-skills
All skills →
About this skill
What does the hyperframes-video-composition skill do?

Provider-independent production workflow for AI agents assembling generated or source media into HyperFrames HTML/CSS/JS videos. Use for HyperFrames composition planning, scene architecture, media custody, animation/timing, captions/audio, deterministic preview/render QA, accessibility/flashing checks, provenance ledgers, and delivery handoff.

How do I install it?

Run `npx skills add calesthio/generative-media-skills --skill hyperframes-video-composition --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going