mcpbeat Sign in

Hyperframes Explainer Builder Agent Skill

Turn a website URL, product docs, or a founder's rambling description into a tight 60-90 second explainer video built in HyperFrames -- problem/solution narrative, animated product walkthrough scenes, captions, and voiceover, ready for the homepage hero, sales emails, and onboarding.

996 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
235
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/OneWave-AI/claude-skills --skill hyperframes-explainer-builder

The instruction itself

7 sections, as written by the author

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:

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

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

Step 3 -- Build the composition

  • Scene per beat: animated type and simple diagram motion for problem/turn; for "how it works," product-UI scenes -- rebuilt clean in HTML (crisp, brand-consistent, always legible) or screenshots panned with intent, whichever the source supports better.
  • Motion serves comprehension: one idea moving at a time, cursor/flow animations that trace what the VO describes, counters for the proof beat. Deterministic and seek-safe per HyperFrames rules.
  • Brand tokens honored (reuse design-style-installer / existing token sets; no purple, no emoji); captions synced for muted viewing; VO via the media pipeline -- offer two voice options before rendering the full track.
  • Lint and preview before declaring done; never claim it renders without running the pipeline.

Step 4 -- Deliver

The hero cut (16:9), a square social cut, and a 30s trim (open + best capability + CTA) for ads and email embeds. Include the poster frame and a one-line embed recommendation (muted autoplay with captions for the homepage).

Rules

  • Outcomes over features, three beats maximum -- the explainer that explains everything explains nothing.
  • Claims trace to the source material; the script never invents numbers, customers, or capabilities the product does not have.
  • The viewer's vocabulary, not the industry's: if the site says "workflow orchestration" and customers say "it does the follow-ups for me," the script says the second.
  • 90 seconds is the ceiling, not the target -- cut until it hurts, then preview.
  • UI shown must match the product's current reality closely enough that a trial user recognizes it.

Quick Commands

  • "Explainer from [URL]" -- full workflow from a website
  • "Explainer from this description" -- interview-driven when there is no site yet
  • "Just the script" -- steps 1-2 for approval before building
  • "Cut a 30-second version" -- the trim from an existing build

Other skills for the same job

different authors, same section of the catalogue
Canvas Design
by anthropics
vendor ×13

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

1388k tokens
Algorithmic Art
by anthropics
vendor ×10

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

15k tokens scripts
Image Enhancer
by frostant
×6

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

635 tokens
Video Downloader
by CommandCodeAI
×4

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

671 tokens
Histolab
by christophacham
×3

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

18k tokens
Omero Integration
by christophacham
×3

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

32k tokens
Pydicom
by christophacham
×3

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

13k tokens scripts
Transformers
by christophacham
×3

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

13k tokens

How to use it

Copy the folder

Take onewave-ai/hyperframes-explainer-builder from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.