HyperFrames Explainer Builder

Every product needs the 75-second answer to "what is this and why do I care," and most teams either skip it or pay an agency five figures for it. This skill directs a real, renderable explainer from whatever source material exists. It owns the narrative and assembly; composition mechanics, captions, transitions, and TTS live in the hyperframes skill (hyperframes-cli for init/lint/preview/render, hyperframes-media for voiceover, website-to-hyperframes when the source is a site to visually mine).

Step 1 -- Extract the story

From the URL (fetch and read it), docs, or interview: who it is for, the painful before-state, what the product does (in outcomes, not features), the 2-3 capabilities that prove it, and the action to take. If the source material buries the value proposition in jargon, the script fixes that -- write what the customer would say, not what the About page says.

Step 2 -- Write the script

The explainer arc, ~150-190 words for 60-90 seconds of comfortable VO:

1. Cold open (0-5s) -- the problem, stated the way the viewer complains about it. No logo intro; nobody waits through a logo.
2. The turn (5-15s) -- product named once, positioned as the answer in one sentence.
3. How it works (15-55s) -- three beats maximum, each one capability shown as an outcome ("invoices chase themselves") with its walkthrough scene.
4. Proof (55-70s) -- one number or one quote, not a wall.
5. CTA (70-85s) -- the single action, spoken and on-screen.

Every sentence read aloud before it ships; explainer VO exposes written-word clunk instantly.