Hyperframes Creative logo

Hyperframes Creative

Community
waker240
hyperframes-creative

Develop video direction, typography, color, visual mechanisms, storyboards, and asset prompts. Use for a HyperFrames design brief or review-led visual exploration.

Overview

Publisherwaker240
RepositoryFullVideoProductionSkill
Skill namehyperframes-creative
Stars
211
Forks
47
Bundled files
76
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 76 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by waker240 on GitHub. Read the source before you install it.

Installation

Install the Hyperframes Creative AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/waker240/FullVideoProductionSkill/tree/main/skills/hyperframes-creative
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/waker240/FullVideoProductionSkill.git /tmp/FullVideoProductionSkill
mkdir -p .claude/skills
cp -r /tmp/FullVideoProductionSkill/skills/hyperframes-creative .claude/skills/hyperframes-creative
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hyperframes Creative in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Hyperframes Creative on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Hyperframes Creative is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Install this skill with its sibling skills. See runtime setup and capability boundaries before executing commands. User instructions and the requested production stage take precedence over workflow defaults.

HyperFrames Creative

Brand, pacing, style, narration, and composition direction. Use after the technical contract from hyperframes-core is in place.

For motion patterns, scene blueprints, transitions, and CSS marker effects, use hyperframes-animation — this skill is intentionally non-animation.

Read these two FIRST for any non-trivial composition — they override web instincts:

  • references/house-style.md — "interpret the prompt, generate real content," the lazy-default list, and the background/foreground layer recipe. This is what turns a literal restyle into a concept.
  • references/video-composition.md — video-medium scale, a designed density curve, one active focal point, and produced detail only when it earns a slot.

Skipping these is the single biggest cause of generic, web-page-looking output. They are not optional rows in the routing table below — for anything beyond a one-line edit, open both before you choose colors or write HTML.

Then, for any anchor / hero / awe-inspiring piece — read the direction layer:

  • references/cinematic-direction.md — the directorial doctrine: the six-regularity Spine, the Effort Protocol (the forcing function against the lazy competent default), the Awe Test, the substrate / externalization / receiver-runway doctrines, the Canvas · Artifact · Cinema ownership lanes, the visual vocabulary, and the scene-review diagnostics. This is the difference between a composition that is correct and one a viewer screen-records. It also spells out The HyperFrames Unlock: advanced runtimes are available, while authored subject/world quality and good judgment remain the real cost.
  • references/cinema-layer.md — the Cinema-Layer vocabularies (charged transitions, atmosphere, 3D moves, lens personality, hand-drawn, diegetic UI, recursive shots, video-arc drift, post-fx cookbook) with HyperFrames HTML/CSS/SVG/GSAP/Three.js implementation hints.

Read video-composition.md + house-style.md for the floor (don't ship web-page output). Read these two for the ceiling (ship something overwhelmingly good). Cold opens, thesis reveals, hero product beats, act opens/closes, closing images — open cinematic-direction.md before you shotlist.

When a piece feels like "elegant slides" — competent, well-rendered, inert — read references/visual-storytelling.md, the film-craft companion lens (Block / Murch / Williams-Disney / McCloud / Mamet / Katz / Mascelli / McKee). It supplies the concrete levers the doctrine lacks: the visual-intensity curve, the Rule of Six + flinch test for cuts, timing-vs-spacing for alive motion, the six panel-to-panel transitions, shape-to-emotion grammar, and the value-turn audit (if a scene doesn't turn a value, it's a non-event — cut it). The "elegant PPT" feeling is almost always a deficit in the temporal/relational layers, not the surface.

Workflow

  1. If a project has a design spec, read it first and treat its current frontmatter tokens as brand truth (colors, fonts, spacing, tone, constraints). Which file to read (precedence frame.md → design.md → DESIGN.md) and how to parse it (frontmatter = normative, prose = context) are defined once in references/design-spec.md. Resolve later user instructions and revision-specific approvals before inheriting an old spec. For reference-led or iterative work, read references/reference-led-direction.md: establish the active direction, protect approved intervals, and prove representative animation before multiplying a treatment across a film.
  2. If no design spec exists and the user asks for visual direction, choose a route:
    • Ready-made frame-preset (optional) → frame-presets/ (adopt a FRAME.md as frame.md; see references/design-spec.md)
    • Named style or mood → references/visual-styles.md
    • Fast defaults → references/house-style.md
    • Interactive selection → references/design-picker.md
  3. For multi-scene work, record a reasoned Spatial Canvas PASS/USE before locking the scene map. Persistent relationships, revisitation, and consequential returns → references/spatial-canvas.md + project SPATIAL_CANVAS.json; otherwise use independent beats via references/beat-direction.md. Separately record fast-passage PASS/USE: bounded momentum, temporal compression, overwhelm, or panic → references/fast-paced-editing.md + project FAST_PASSAGES.json before transition mechanics. These are independent admissions, not format quotas.
  4. For any anchor / hero / awe-inspiring shot (cold open, thesis reveal, hero product beat, act open/close, closing image), read references/cinematic-direction.md and run its Effort Protocol before shotlisting — declare AWE vs EASY per shot, use Gaze → Dream → Create to diverge. For a cold open, map only the first three seconds of narration cue-by-cue before dreaming; for true 3D, pass hyperframes-animation/adapters/three.md's admission gate. Pick the Cinema-Layer treatment from references/cinema-layer.md.
  5. For any static asset the composition needs (illustrations, dossier cards, plates, cutout subjects, substrate/depth layers), read references/asset-generation.md before generating — use the selected provider or available host image tool, inspect true alpha for cutouts, and save every prompt and provenance. For generated footage or exact UI over a material/character plate, read references/generated-media-composition.md before generation: assign material/code roles, source clocks, camera ownership and registration. For an approved B-paper / editorial paper storyboard, first read references/paper-theatre.md for its material, shot and layer workflow.
  6. For motion-heavy work, read references/motion-principles.md (high-level guardrails), then go to hyperframes-animation for atomic rules.
  7. If a built piece feels like "elegant slides" (inert despite good assets), read references/visual-storytelling.md and run its per-scene checklist — value-turn audit, intensity curve, cut-on-the-idea, timing-vs-spacing, transition variety.
  8. Before full assembly and again on the encoded master, run references/design-adherence.md's rendered-trajectory gate: establish / midpoint / resolve for every semantic scene, every admitted Spatial visit/return, every fast passage through release, plus cue-boundary samples inside the first three seconds.

Routing

TopicRead
Reference-led direction / repeated review — active brief, animated benchmarks, mixed representations, PROTECT/POLISH/REBUILD, feedback acceptance testsreferences/reference-led-direction.md
Generated images/video with exact UI — shot contract, native media clocks, planar screen replacement, occlusion, still-versus-video selectionreferences/generated-media-composition.md
Direct an anchor / hero / awe shot — doctrine, Effort Protocol, awe test, 3-layer architecture, diagnosticsreferences/cinematic-direction.md
Fix "elegant slides" / sequence & story craft — visual-intensity curve, Rule of Six + flinch test, timing-vs-spacing, 6 panel transitions, shape-to-emotion, value-turn auditreferences/visual-storytelling.md
Cinema-Layer treatment — charged transitions, atmosphere, 3D, lens, hand-drawn, diegetic UI, recursion, post-fxreferences/cinema-layer.md
Choose 2D vs 2.5D vs true 3D — semantic abstraction, world coherence, paused-frame qualityreferences/cinematic-direction.md · hyperframes-animation/adapters/three.md
Generate static assets — configured image generation, reference roles, true alpha, sizing, prompt/provenance recordsreferences/asset-generation.md
B-paper / editorial paper theatre — storyboard fidelity, material foundry, physical mechanisms, layered shots, typography and encoded QAreferences/paper-theatre.md · concrete prompts → references/paper-theatre-prompts.md
Adopt a ready-made frame-preset as frame.md (optional)frame-presets/ · references/design-spec.md
Default palettes, motion, typography, lazy defaults to questionreferences/house-style.md
Named style presets, mood-to-style routingreferences/visual-styles.md
Palette-specific color tokenspalettes/*.md
Composition patterns — PiP, text-behind-subject, title card, slide showreferences/composition-patterns.md
Spatial Canvas admission + direction — persistent world, semantic geography, camera itinerary, cutaway/return, synthesisreferences/spatial-canvas.md + project SPATIAL_CANVAS.json
Fast-paced passage admission + direction — momentum, compression, overwhelm, rupture, sound arc, release/reorientationreferences/fast-paced-editing.md + project FAST_PASSAGES.json
Stats / infographic presentationreferences/data-in-motion.md
Structured expansion for open-ended promptsreferences/prompt-expansion.md
Video-medium density, scale, color, frame compositionreferences/video-composition.md
Per-beat direction, rhythm planning, transition timingreferences/beat-direction.md
Source adherence + rendered trajectory QA (including opening and 3-state scene review)references/design-adherence.md
High-level motion guardrails and GSAP-quality rulesreferences/motion-principles.md
Font selection, pairings, rendered-video type guardrailsreferences/typography.md
Script pacing, tone, openings, number pronunciationreferences/narration.md
Precomputed audio bands mapped to motionreferences/audio-reactive.md

Scripts

  • scripts/contrast-report.mjs — inspect contrast warnings from rendered frames.
  • scripts/extract-audio-data.py — pre-extract audio bands for audio-reactive compositions.
  • scripts/package-loader.mjs — support script for bundled creative tooling.

Run from the repo root with explicit paths, for example:

bash
python skills/hyperframes-creative/scripts/extract-audio-data.py <audio-file>

Animation analysis (animation-map.mjs) lives in hyperframes-animation/scripts/.

Boundaries

  • Do not override hyperframes-core technical rules.
  • Do not require a design system for a minimal technical composition.
  • Do not add extra scenes, narration, music, captions, or transitions unless the request calls for them or you first propose the expansion.
  • Keep recipe references task-specific; do not read every reference for simple edits.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

and 16 more files.

Frequently asked questions

What does the Hyperframes Creative AI skill do?

Develop video direction, typography, color, visual mechanisms, storyboards, and asset prompts. Use for a HyperFrames design brief or review-led visual exploration.

Why use Hyperframes Creative on TypingMind?

Because you install it once and use it with any model. Hyperframes Creative is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Hyperframes Creative in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/waker240/FullVideoProductionSkill/tree/main/skills/hyperframes-creative. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Hyperframes Creative?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Hyperframes Creative?

As many as you like. As long as a model supports skills, you can use Hyperframes Creative with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Hyperframes Creative AI skill free?

Yes. It is published on GitHub by waker240 under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇