Prod By Claude

Organization

heygen-com

prod-by-claude

Use when an agent needs to make a HyperFrames video of a Strudel live-coding track, where the code itself is the picture and every token lights up on the note it plays. Trigger on: "strudel video", "live coding video", "show my code playing", "make a video of this track with the code", "prod by claude". Covers composing the track, recording it offline from pinned Strudel, and building the 1080x1080 video (typed opener, parts powering on, real Strudel theme switches, graffiti ASCII drops, typed sign-off).

Overview

Publisher	heygen-com
Repository	`hyperframes-community-skills`
Skill name	`prod-by-claude`
Stars	226
Forks	22
Bundled files	12
License	Apache-2.0
Links	Skill source Repository

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.
12 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by heygen-com on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/heygen-com/hyperframes-community-skills/tree/master/skills/prod-by-claude
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/heygen-com/hyperframes-community-skills/tree/master/skills/prod-by-claude

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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/heygen-com/hyperframes-community-skills.git /tmp/hyperframes-community-skills
mkdir -p .claude/skills
cp -r /tmp/hyperframes-community-skills/skills/prod-by-claude .claude/skills/prod-by-claude

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prod By Claude 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 Prod By Claude 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 Prod By Claude 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.

prod-by-claude

Turn a Strudel track into a live-coding video. The music is rendered offline from the code, and the video is driven by Strudel's own note events, so every highlight lands on its note.

When to use

The user wants a video of Strudel code playing: "make a video of this Strudel track", "show the code lighting up", "live-coding video", or a track the agent composed for them.
Not for other audio or DAW projects, talking-head videos, or visualizers of an existing audio file with no Strudel code (use the HyperFrames music workflow for those).

Inputs

A Strudel track (.strudel.js), or a brief to compose one. Compose with references/composing.md. With no track, start from assets/example/track.strudel.js (synth-only, no samples).
The arrangement: length in bars, and which bars are builds and drops.

Tools and dependencies

Node 22 or newer, npm, and the HyperFrames CLI pinned to hyperframes@0.8.70 (run through npx --yes).
tools/package.json pins everything else: @strudel/web 1.3.0 (AGPL-3.0, installed from npm, not bundled here), puppeteer-core 25.12.0, @puppeteer/browsers 3.2.3, and the OFL fonts @fontsource/jetbrains-mono 5.3.0 and @fontsource/rubik-mono-one 5.3.0.
Chrome for Testing 149.0.7827.22 for recording, or any Chrome given as CHROME=<path>.
No credentials.

Workflow

Create the project (plain file copies): node <skill>/scripts/new-project.mjs <project-dir> [track.strudel.js]
Edit <project-dir>/video.json: bars, builds, drops, themes, storm parts, signoff (references/video.md, references/themes.md). The template already matches the example track, so skip this step when using it.
From <project-dir>/tools, install the pinned tools: npm install
From <project-dir>/tools, if CHROME is not set, fetch Chrome for Testing: npx --yes @puppeteer/browsers@3.2.3 install chrome@149.0.7827.22 --path .chrome
From <project-dir>/tools, record: node record.mjs .. It takes about 5-7 minutes for 32 bars (give it a 10 minute timeout), prints levels per 4 bars and warns on clipping. Fix the track and record again until the drops peak at or below -2 dBFS with no clipped samples.
From <project-dir>/tools, build the video data: node build-data.mjs .. It prints the snapshot command for step 7.
From <project-dir>, run npx --yes hyperframes@0.8.70 check ., then the printed snapshot command, and look at every frame (what to look for: references/video.md).
From <project-dir>, render locally when the user asks for the video: npx --yes hyperframes@0.8.70 render . -o renders/video.mp4 HyperFrames cloud render (npx --yes hyperframes@0.8.70 cloud render .) spends credits on the user's account: use it only after the user explicitly agrees.

If the track changes, repeat steps 5-7. If video.json changes, repeat steps 6-7.

Outputs

assets/bgm.wav (the mix), assets/stem-<part>.wav (the scope part), data/events.json (every note with its code locations), data/events.js (what the composition reads).
renders/video.mp4, 1080×1080, 30 fps, about pre + bars × 240 / bpm + 4.6 seconds with a sign-off.

Side effects

Files: writes only inside <project-dir>. build-data.mjs rewrites the data-duration and audio data-start attributes in index.html.
Network: npm install (npm registry), the Chrome for Testing download (about 150 MB from Google's storage), and GSAP from cdn.jsdelivr.net when the composition loads. snapshot uploads frames to a hosted captioning model unless given --describe false, so always pass it. Recording runs on 127.0.0.1 only and fetches nothing unless the track itself loads samples (then from the sample URLs the track names).
Audio: recording is headless and muted; nothing plays out loud.
Cost: none, unless the user approves a cloud render.

Verify

record.mjs exits 0, lists every part, and reports no clipping.
check passes with 0 errors. canvas_overflow info notes for code lines below the frame are expected.
In the snapshots: line 1 typing at 0.6 s, the first part blooming and highlighted after pre, graffiti in each drop, the decode after each drop, the sign-off at the end.
In the render: the first sound lands at pre seconds, and the video ends in black.

Rights

The music written in Strudel belongs to its author; Strudel's AGPL covers the software, not the tracks. Built-in synths need no clearance. Samples loaded by a track are other people's recordings: use only sounds the user owns or has cleared.

Bundled files

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

Frequently asked questions

What does the Prod By Claude AI skill do?

Why use Prod By Claude on TypingMind?

Because you install it once and use it with any model. Prod By Claude 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 Prod By Claude in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/heygen-com/hyperframes-community-skills/tree/master/skills/prod-by-claude. 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 Prod By Claude?

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 Prod By Claude?

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

Is the Prod By Claude AI skill free?

Yes. It is published on GitHub by heygen-com 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

Hyperframes

NousResearch

OrganizationPopular

Render MP4/WebM videos from HTML compositions.

Kanban Video Orchestrator

NousResearch

OrganizationPopular

Plan and run multi-agent video production pipelines.

Pixel Art

Pixel art w/ era palettes (NES, Game Boy, PICO-8).

Inference Sh Cli

Run 150+ AI apps (image, video, LLM) via inference.sh CLI.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

prod-by-claude

When to use

Inputs

Tools and dependencies

Workflow

Outputs

Side effects

Verify

Rights

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now