Hyperframes logo

Hyperframes

Community
waker240
hyperframes

Plan, author, review, and render HTML videos with HyperFrames. Use for narrated films, explainers, animation, or a video workflow needing versioned review, audio, captions, and final audit.

Overview

Publisherwaker240
RepositoryFullVideoProductionSkill
Skill namehyperframes
Stars
211
Forks
47
Bundled files
70
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.

  • 70 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 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
  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 .claude/skills/hyperframes
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hyperframes 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 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 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.

HyperFrames video workflow

HyperFrames renders video from HTML. Use this entry point for a narrated film, explainer, animation or review package. The user's chosen framework, provider, visual style and delivery stage take precedence. Install the sibling skills together and read runtime setup. This pack does not install an AI model, hosted service, music catalog or desktop tool.

Production principles

  1. Complete the authorized stage. A requested storyboard, A/B review or audio audition is a real deliverable. Existing authorization to finish does not require invented approval stops. Current instructions and versioned choices supersede stale notes.
  2. Direct before scaling. Study the script, define each beat's visual change, and prove moving benchmarks. The capability palette is a menu, not a quota. Admit 3D, dense editing or a persistent world only when it serves the argument.
  3. Preserve review evidence. Record candidate/version, choice, comment and repair. Agent QA never creates user approval. Keep approved shots and protected windows intact. See review-driven production.
  4. Direct sound with picture. Plan voice, captions, BGM or intentional silence, and action-linked SFX. Audition alternatives alone and under narration. Discovery, validation, shortlisting and actual final use are different states.
  5. Keep media portable. Save prompts and non-secret provenance; freeze selected media into the project. Keep source audio and required lossless masters. No render depends on a private output folder, live catalog, credentials or runtime network access.
  6. Keep time deterministic. Use seeded randomness, seekable timelines and framework-owned media. Test cold seeks and the encoded result. Follow the core contract.
  7. Audit meaning and mechanics. Inspect the full film, every adjacent seam, type/captions, sound and protected windows. Repair findings and recheck neighbors. Numerical audio checks cannot establish listening quality.
  8. Capture learning locally. Save a short project RETROSPECTIVE.md; generalize proven fixes in a separate maintenance task.

Script or topic to film

Resolve material unknowns using the brief and session context: script handling, delivery format, voice/provider, length and review stage. Preserve supplied wording unless editing is authorized. For a bare topic, produce the script first; honor requested review before dependent production. Do not assume a platform, house style, personal voice or account.

Read the user's completion checklist if supplied; otherwise adapt the bundled checklist. A short title card does not inherit a publishing package's requirements.

Follow pipeline.md. For A/B review or repeated visual corrections, also read review-driven-production.md. The runnable review workbench provides versioned choices, notes and audio/visual candidates. Review publishing covers optional sharing when requested.

PhaseWork and evidence
1Scaffold; record runtime/configuration and audio route. Bundled synthesis helpers implement Fish. Supplied narration or a selected provider can enter through the imported-audio contract.
2Study script; make DESIGN.md, narration/visual plan, scene contract and sound palette. Record reasoned PASS/USE for Spatial Canvas and fast passages; neither is a quota.
3Generate/import voice, concatenate/master, obtain word timing and align authoritative text. Lock the clock before exact shot timings.
4Generate/source assets with prompts/provenance. Audition music/SFX and freeze selected files.
5Build scenes with locked timing/ownership; protect approved concepts and windows.
6Assemble picture, chosen BGM/SFX, directed mix and intentional scene handoffs.
7Validate, snapshot and watch the complete assembly at final frame rate; check captions, sound, camera returns and fast-passage release.
7.5Run readiness gates appropriate to the requested deliverable. A review package is not a finished film.
8For a full film, log audit → repair → recheck evidence in DIRECTION.md; run scripts/gate.cjs. The supplied gate expects at least two logged loops.
9Render, decode and inspect the encoded master; reconcile retained files/checklist, deliver rebuild instructions and a project retrospective.

Small edits enter at their relevant phase. Timing changes require the pipeline's Cascade.

Routes

TaskSkill or reference
Composition, tracks, media ownership and sub-compositionshyperframes-core
Motion, transitions, cameras and runtime adaptershyperframes-animation
Direction, storyboards, typography and asset promptshyperframes-creative
Narration, timing, mixing and sound reviewhyperframes-media
Reviewed local media discovery/resolution/freezingmedia-use
Registry blocks/componentshyperframes-registry
Short synthetic-graphics explainerfaceless-explainer
Short motion graphic or overlaymotion-graphics
Music drives the timelinemusic-to-video
General custom compositiongeneral-video
Port existing Remotion sourceremotion-to-hyperframes
Approved studies to narration-locked final assemblyreview-to-final-assembly
Still generation / generated footage / paper theatreasset generation, generated media, paper theatre
Persistent world / bounded fast passageSpatial Canvas, fast editing
Cover candidatesthumbnail generation

Browser tools, generators, sharing and delegation are host capabilities or separate installations. Use current schemas and permissions. If absent, use supplied media or execute work serially; name a missing capability precisely without claiming it is included.

Maintenance

Keep the bundle version fixed during production. Set HYPERFRAMES_SKIP_SKILLS=1 before CLI initialization that may install upstream skills. Use the project's tested CLI version. Review upgrades separately and preserve local changes/notices. Project output and skill maintenance are separate.

Bundled files

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

and 10 more files.

Frequently asked questions

What does the Hyperframes AI skill do?

Plan, author, review, and render HTML videos with HyperFrames. Use for narrated films, explainers, animation, or a video workflow needing versioned review, audio, captions, and final audit.

Why use Hyperframes on TypingMind?

Because you install it once and use it with any model. Hyperframes 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 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/waker240/FullVideoProductionSkill/tree/main/skills/hyperframes. 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?

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?

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

Is the Hyperframes 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 👇