Files
hyperframes/AGENTS.md
T
WaterrrForever 306a291dea fix(skills): audit descriptions — trim routing prose, fix stale facts, add missing triggers (#1990)
* fix(skills): audit descriptions — trim routing prose, fix stale facts, add missing triggers

Descriptions are the always-loaded routing tier; this audit rebuilds them on
one principle: discriminate by input shape, not pipeline internals.

- Trim creation-workflow descriptions to positive trigger + nearest-neighbor
  disambiguation + /hyperframes escape hatch; full routing prose already
  lives in each skill body's route-confirm block and the router
- Codify the workflow-vs-domain split as ownership (owns the end-to-end
  deliverable vs capability layer pulled in mid-flight) in /hyperframes,
  and widen "make me a video" framing to deck / composition port
- Fix stale facts: embedded-captions identity count (desc 32, body 17 →
  actual 36 = 10 classic + 26 themed), six→ten visual languages, retired
  RVM/Standard wording in router details, figma shader transport
  (MCP → MCP source / native export), keyframes "cursor demos" (no backing
  content), hyperframes-media scripts/audio.mjs leak
- Register missing capabilities: motion-graphics maps category (was in
  categories/ but absent from its own table, description, and router),
  asset-fusion + news triggers, slideshow page-to-deck + presenter mode,
  general-video editing, talking-head-recut 16:9/9:16/4:5 canvas,
  cli feedback + lambda sites, product demos, mood-brief BGM generation
- website-to-video: relabel promo-shaped video types to keep the promo
  boundary with /product-launch-video; drop headless-Chrome wording
- music-to-video: lyric timing via /hyperframes-media transcription or
  user-supplied lyrics, placed on the beat grid
- Sync catalogs in lockstep (CLAUDE.md, AGENTS.md, README,
  docs/guides/skills.mdx, CLI project templates): add music-to-video +
  slideshow entries, complete the domain-skill lists, and extend the
  catalog-maintenance rule to cover AGENTS.md and the templates

Validated with a 35-case description-only routing eval: 35/35 both before
and after the rewrite (including new maps / asset-fusion / news probes).

* fix(skills): post-media-v2 consistency — stale media ref, router figma wording, catalog rows

- music-to-video: lyric transcription now routes to /media-use (the
  retired /hyperframes-media was still referenced)
- router capability map: figma row gains the shaders fact (MCP source /
  native export), matching the SKILL.md source of truth
- media-use catalog rows (CLAUDE.md, README, docs/guides/skills.mdx):
  add image models + captioning, aligning with the v2 description
- catalog rule #1: root AGENTS.md carries the workflow list only (it
  has no domain-skill section) — rule wording now says so
2026-07-07 14:28:46 +08:00

5.8 KiB

Hyperframes

Open-source video rendering framework: write HTML, render video.

Skills

This repo ships AI agent skills via vercel-labs/skills. Install them before writing compositions — they encode framework-specific patterns that generic docs don't cover.

npx skills add heygen-com/hyperframes

Creation workflows route through one entry skill — read /hyperframes first: it orients you to the whole surface and maps "make me a…" intent — usually a video, but also a navigable deck (/slideshow) or a composition port (/remotion-to-hyperframes) — to a concrete workflow. Consult it before invoking a specific workflow:

  • /product-launch-video — a product URL (or a pre-written script / text brief in no-capture mode) → product launch / promo video, up to ~3 min (sweet spot ~30-90s).
  • /website-to-video — a general website / URL → a video of the site (tour / showcase / social clip from captured screenshots + assets); for a product launch / promo, use /product-launch-video.
  • /faceless-explainer — arbitrary text, no URL and no website capture → faceless explainer, up to ~3 min (sweet spot ~30-90s); every visual is LLM-invented (typography / abstract graphics / diagram / data-viz).
  • /embedded-captions — an existing talking-head video (MP4) → the same footage with captions / subtitles added (verbatim rail + embedded climax, or pure-cinematic embed); the footage itself is untouched (no NLE-style editing).
  • /talking-head-recut — an existing talking-head / interview / podcast video (MP4) → the same footage packaged with designed graphic overlays (kinetic titles, lower-thirds, data callouts, pull-quotes, side panels, pip) synced to the transcript; the clip plays unchanged underneath, footage untouched. For plain captions/subtitles → /embedded-captions.
  • /pr-to-video — a GitHub PR (URL / owner/repo#N / "this PR") → code-change explainer, up to ~3 min (changelog / feature reveal / fix / refactor). A PR link, not a product website.
  • /motion-graphics — a short (typically under 10s) design-led motion graphic, motion-is-the-message, no narration: kinetic type, a stat / number count-up, a chart, a logo sting, a lower-third / overlay, or an animated tweet / headline / captured-page highlight; rendered to MP4 or a transparent overlay. Longer / narrated / custom → /general-video.
  • /music-to-video — a music track (audio file, or video to pull audio from) → beat-synced video (lyric / slideshow / kinetic promo). Music drives pacing; user-supplied images / videos are cut onto the same beat grid.
  • /slideshow — a presentation / pitch deck / interactive deck — discrete slides, fragment reveals, branching, hotspot navigation, presenter mode. Output is a navigable deck, not a rendered video.
  • /general-video — fallback for any other video creation (title card, longer brand / sizzle reel, multi-scene montage, static loop, custom composition); the original hyperframes flow — design → plan → layout → build → validate, any length.

Porting an existing composition? /remotion-to-hyperframes translates a Remotion (React) video composition into HyperFrames HTML — a source migration, separate from the creation workflows above.

Build & Test

bun install     # Install dependencies (NOT pnpm — do not create pnpm-lock.yaml)
bun run build   # Build all packages
bun run test    # Run all tests

Linting & Formatting

Uses oxlint and oxfmt (not eslint, not prettier, not biome).

bunx oxlint <files>        # Lint
bunx oxfmt <files>         # Format
bunx oxfmt --check <files> # Check formatting (CI / pre-commit)

Always lint and format changed files before committing. Lefthook pre-commit hooks enforce this automatically.

Composition Validation

After creating or editing any .html composition:

npx hyperframes lint       # Static HTML structure check
npx hyperframes validate   # Runtime check (headless Chrome — catches JS errors, missing assets)

Both must pass before previewing or considering work complete.

Project Structure

packages/
  cli/                  → hyperframes CLI (create, preview, lint, render)
  core/                 → Types, parsers, generators, linter, runtime, frame adapters
  engine/               → Seekable page-to-video capture engine (Puppeteer + FFmpeg)
  player/               → Embeddable <hyperframes-player> web component
  producer/             → Full rendering pipeline (capture + encode + audio mix)
  shader-transitions/   → WebGL shader transitions for compositions
  studio/               → Browser-based composition editor UI
registry/
  blocks/               → Installable sub-composition scenes (50+)
  components/           → Installable effects and snippets
  examples/             → Starter project templates
docs/                   → Mintlify documentation site (hyperframes.heygen.com)
skills/                 → AI agent skill definitions

Key Conventions

  • Package manager: bun (not pnpm, not npm for workspace operations)
  • Commit format: Conventional commits (feat:, fix:, docs:, refactor:, test:)
  • TypeScript: Avoid any and as T assertions. Prefer type guards and narrowing.
  • Compositions: HTML files with data-* attributes. Clips need class="clip". GSAP timelines must be paused and registered on window.__timelines.
  • Frame Adapters: Animation runtimes plug in via the seek-by-frame adapter pattern. GSAP is the primary adapter.
  • Deterministic rendering: No Date.now(), no unseeded Math.random(), no render-time network fetches.

Documentation