git:20260707.53e71e7 to git:20260820.56c099a

---

name: hyperframes

---

# HyperFrames — start here

Below: a **capability map** (the domain skills, loaded on demand) and the **intent router** (pick a workflow for any "make me a video" request).

## Capability map — the domain skills

---

# Intent routing — pick a workflow

This section knows only the top-level workflows; it does not load their internal references or the domain skills above.

## Before routing — confirm the input, not the spec

Routing needs to know **what the video is about** — its input and subject. If that's unspecified ("make a video about our thing" with no URL, product, topic, or asset), ask before entering any workflow — committing to a workflow IS the routing decision. At most two questions:

- **Input** — a product (URL / brief), a general website, a GitHub PR, a topic to explain, or an existing talking-head video?

**Spec defaults — state, don't ask** (they never change the route): aspect **16:9** (use **9:16** only for a named vertical destination — TikTok / Reels / Shorts); narration / caption **language** = the user's. The chosen workflow re-confirms its own specifics at its first step.

## Workflow cheat-sheet

| Workflow | Use it for |

| -------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

| `/product-launch-video` | **Selling a product** (SaaS, app, company / product site) — from a URL, brief, or script → a **promo**. The default for any commercial URL, even if the site is only named. |

| `/website-to-video` | **Showing a site itself** — a tour / showcase built from the site's own screenshots. For non-commercial sites (portfolio, blog, docs, personal, event), or when the user wants a tour, not a promo. |

| `/faceless-explainer` | **Explaining a topic / concept** from text — no product, no URL; every visual is LLM-invented |

| `/pr-to-video` | A **GitHub PR / code change** → changelog / feature-reveal / fix / refactor explainer |

| `/embedded-captions` | Adding **captions / subtitles** to an existing talking-head video (footage untouched) |

| `/talking-head-recut` | Packaging an existing talking-head video with **designed graphic overlays** — lower-thirds, data callouts, kinetic titles, pull-quotes |

| `/motion-graphics` | A short, **unnarrated, design-led motion graphic** — kinetic type, a stat / chart hit, a logo sting, a lower-third overlay |

| `/music-to-video` | A **music track** → a **beat-synced** video — lyric video, slideshow, or kinetic promo; the music drives pacing (optional user images / videos cut onto the beat grid) |

| `/slideshow` | A **presentation / pitch deck / interactive deck** — discrete slides, fragments, branching, hotspots; output is a navigable **deck**, not a rendered video |

| `/general-video` | **Anything else** — longer or multi-scene pieces, a static loop / poster, a custom composition |

| `/remotion-to-hyperframes` | **Porting an existing Remotion (React) composition** to HyperFrames (migration, not creation) |

**Disambiguation (only where confusable):**

- **Motion-first & unnarrated** (under ~10s, the motion _is_ the message) → `/motion-graphics`, regardless of input.

- **A URL or script** — ask one thing: _is the site selling a product?_ **Yes** (SaaS / app / product / company site) → `/product-launch-video` — a promo, and the default for any commercial URL even if the site is only named. **No**, or the user just wants the site shown as-is (portfolio / blog / docs / personal / event) → `/website-to-video` — a tour. A GitHub PR link → `/pr-to-video`; a concept with no product or site → `/faceless-explainer`.

- **Existing footage** — plain spoken-word subtitles → `/embedded-captions`; designed overlay cards → `/talking-head-recut`. Neither edits the footage itself (re-timing / recolor / reframe / reorder / audio is NLE editing — out of scope).

- **A music track is the input** (an audio file, or a video to pull audio from) with **no narration** → `/music-to-video` — the music's beats/energy drive the pacing. (Narrated pieces stay with the input-matched workflow above; `/motion-graphics` is for short unnarrated motion that isn't music-driven.)

- **A presentation / pitch deck / interactive deck** (discrete slides, navigation, presenter mode) → `/slideshow` — output is a navigable deck, not a rendered video. An explicit "slideshow" request proceeds directly; an adjacent trigger ("deck / slides / presentation / convert this page") makes `/slideshow` confirm it's a slideshow before authoring, and switch to the appropriate non-slideshow workflow if not.

- **Length is a guide, not a gate** — intent picks the workflow; go to `/general-video` only when the piece is clearly longer than ~3 min, or is a static / loop / custom format.

## If the matched workflow isn't installed

Once you've picked a workflow, check it's actually available to you. If the matched workflow skill isn't installed, don't fall back to guessing — tell the user to install it first:

- **Just this workflow:** `npx skills add heygen-com/hyperframes --skill <workflow-name>` (e.g. `--skill pr-to-video` — bare name, no leading `/`).

- **All workflows at once:** `npx skills add heygen-com/hyperframes --all` (core + every workflow, skips the picker).

After they run it, re-read the workflow's skill and continue.

## Keeping skills current

HyperFrames skills are versioned. `npx hyperframes init` checks the installed skills against the latest on GitHub and installs/refreshes the **full** set whenever anything is out of date or missing — so a freshly init'd project always has the complete, latest set (and re-running init on an up-to-date project is a no-op). The check is a quick GitHub round-trip; offline (or rate-limited) it falls back to installing after a short timeout, so init never hard-fails on a network hiccup. The creation workflows scaffold with `init`, so starting a new project always runs this check and pulls our latest skills from GitHub when they're stale. The `--skip-skills` flag is currently neutered (a temporary measure while the skills.sh registry catches up): passing it no longer skips the check, so every `init` checks GitHub. CI/tests opt out via the `HYPERFRAMES_SKIP_SKILLS=1` env var.

If a task is behaving unexpectedly, or before a long build, confirm the installed skills are current:

- **Check:** `npx hyperframes skills check` (add `--json` for a machine-readable verdict; exits non-zero when anything is outdated **or missing**).

- **Update:** `npx hyperframes skills update` — pulls the full set to the latest, **installing any not yet present** (same as init's install step).

The CLI also surfaces a one-line reminder when a `render` / `lint` / `validate` run detects stale skills.

## Workflow details

### `/product-launch-video`

- **Input:** A product being marketed — **(a)** a product URL (crawled with headless Chrome for assets + brand tokens), **(b)** a script / brief that names the product's site even without a link (PLV resolves + crawls it, unless the user opts out), or **(c)** a script with no derivable site / "don't scrape" (no-capture mode — pick a style preset that supplies palette + design system). A supplied script can be the **verbatim** voice-over or **restructured** per scene — PLV asks.

- **Output:** a product launch / SaaS **promo** as a HyperFrames composition → MP4 (sweet spot 30–90s) — the product's value is the subject, not a walkthrough of the site. For a plain tour of the site, use `/website-to-video`.

- **Triggers:** "launch video for X", "promo for our site", "explain my SaaS in a minute", "turn my script into a 60s promo", "text-only launch video, don't scrape".

### `/website-to-video`

- **Input:** A website / URL whose goal is to show **the site itself**, not to sell a product. Best for non-commercial sites (portfolio, blog, docs, personal, event), or when the user explicitly wants a tour of a site as-is. Captured with headless Chrome for real screenshots + brand assets. If the site is selling something and the user wants a promo, use `/product-launch-video`.

- **Output:** a site tour / showcase / social clip built from the site's own visuals → MP4.

- **Triggers:** "turn this website into a video", "site tour from ", "social clip from our homepage", "I just have a URL — make something".

### `/faceless-explainer`

- **Input:** Arbitrary text — a topic, article, or notes — being **explained**, with no product being marketed and no site to capture. (Forked from `/product-launch-video`; no headless Chrome.)

- **Output:** faceless explainer → MP4, every visual LLM-invented per scene (typography / abstract / diagram / data-viz); ships the `pin-and-paper` preset. (sweet spot 30–90s).

- **Triggers:** "faceless explainer about X", "explain how DNS works as a video", "turn this article into an explainer", "explainer from my notes".

### `/pr-to-video`

- **Input:** A **GitHub pull request** — a PR URL, an `owner/repo#N` ref, or "this PR" — read via the `gh` CLI (not a site to scrape).

- **Output:** code-change explainer (changelog / feature-reveal / fix / refactor) → MP4 — diff highlights, before/after, file-tree + impact scenes. ≤ (sweet spot 30–90s).

- **Triggers:** "make a video about this PR", "turn PR #1187 into a changelog video", "release-notes video from github.com/org/repo/pull/123".

### `/embedded-captions`

- **Input:** An existing **talking-head video** (MP4) to caption — actual footage, not a URL or brief. Transcribed locally (Whisper, no API key) and matted (RVM) so the subject can occlude captions.

- **Output:** the same footage **untouched**, with a caption layer — **Standard** (verbatim lower-third rail + an embedded climax behind the subject) or **Cinematic** (every caption composited behind the subject). Any length.

- **Triggers:** "add captions / subtitles to this video", "captions behind the subject", "cinematic captions for my clip".

### `/talking-head-recut`

- **Input:** An existing **talking-head / interview / podcast video** (MP4) to package with on-screen graphics — actual footage. Transcribed locally (Whisper). The clip plays in full underneath, untouched.

- **Output:** the same footage with timed **graphic-overlay cards** — kinetic titles, lower-thirds, data callouts, pull-quotes, side panels, picture-in-picture — synced to the transcript. Any length.

- **Triggers:** "package this video", "add graphic overlays / lower-thirds / data callouts to my talk", "turn this interview into a graphics-packaged edit".

### `/motion-graphics`

- **Input:** A short, design-led motion graphic where the **motion is the message** — typically under ~10s, no narration. Genres: kinetic typography, a stat / number count-up, a chart hit, a logo sting, a lower-third / overlay, or a search-driven page / tweet / headline shot.

- **Output:** a short motion graphic → MP4 or a **transparent overlay** (alpha WebM / MOV) for a lower-third / callout.

- **Triggers:** "an 8s logo sting", "animate this stat", "a kinetic-type intro", "turn this tweet into a motion graphic", "a transparent lower-third overlay".

### `/music-to-video`

- **Input:** A **music track** — an audio file, or a video to pull the audio from — with **no narration and no website capture**. Optionally, user-supplied images / videos to weave in. The track is analyzed once into a deterministic beat / energy map (`audiomap.json`) the whole video is built on.

- **Output:** a **beat-synced** HyperFrames composition → MP4 where the music drives pacing. Typography and templates are the floor (a complete video needs zero assets); any supplied media is cut onto the same beat grid (beat-cut / ken-burns). The genre — lyric video, slideshow, kinetic promo — emerges from the per-frame choices; the pipeline never branches on it.

- **Triggers:** "make a video for this song", "beat-synced video from this track", "lyric video", "turn this music into a video", "music visualizer / kinetic promo to this beat".

### `/slideshow`

- **Input:** A **presentation / pitch deck / interactive deck** to author — a brief, an outline, or an existing page to convert to slides. Not a request for a rendered video; if the intent is ambiguous, the skill confirms "do you want this as a HyperFrames slideshow?" before authoring.

- **Output:** a runnable HyperFrames composition + a **JSON island** the player's `SlideshowController` reads to turn the GSAP timeline into a navigable **deck** — discrete slides, fragment reveals, branching sequences, hotspot navigation, presenter mode, and speaker notes. The deliverable is a deck, not an MP4.

- **Triggers:** "make a pitch deck / presentation / slide deck", "an interactive deck", "convert this page into slides", "a slideshow with presenter mode".

### `/general-video`

- **Input:** Anything not above — a creative brief, a single element to animate, an edit to a composition you're building. Input- and length-agnostic.

- **Output:** a HyperFrames composition (any length / format) via the original flow: design system → prompt expansion → plan → layout-before-animation → build (delegating to the `hyperframes-`\* skills) → validate.

- **Triggers:** "make a title card", "animate this", "a longer brand / sizzle reel", "a multi-scene composition", "a static loop / poster", any "make a video" that fits no row above.

### `/remotion-to-hyperframes`

- **Input:** An existing **Remotion** (React) composition's source — the user **explicitly** asks to port / convert / migrate it. One-way (Remotion → HyperFrames); not creation-from-input. A passing mention of Remotion is not a trigger.

- **Output:** a HyperFrames HTML composition translated from the Remotion source, graded against the Remotion render (SSIM eval harness + tiered test corpus).

- **Triggers:** "port my Remotion project to HyperFrames", "convert this Remotion comp", "migrate from Remotion".