Turn a concept into an interactive machine-style explainer figure
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 agent.
Use cases
Methods
Make interactive explainer figures with the Anatomy skill
Claude Code
Anatomy skill
Steps
- Install the Anatomy skill once for all projects (or only in one project folder), after reading its SKILL.md, since it runs scripts on your computer. It needs a recent Node.js (20.10+) plus a Chromium-based browser for its checks; reload skills if Claude Code was already running.
- Describe the idea rather than the picture: in an ordinary chat, ask for three candidate physical machines that would act out the concept for your audience, each mapping its parts to the concept, with one key motion and one real number for the readout, and no boxes or arrows. Pick the one a beginner would grasp fastest.
- Choose the size before building: a Figure (roughly 40 to 80 parts, under about 90 minutes), a Hero (up to about 150 parts, a few hours) or an Epic (a whole vehicle or building, six hours or more). Start with a Figure.
- Write the build request with the machine-to-concept mapping, the key movement to show and the readout value, and add the keyword interactive (plus WebGL or 3D only if needed; 3D is beta). Ask for a single HTML file and tell it not to move up to Hero without asking.
- Before it builds, have it list every number the figure will show, with unit and source, and stop to ask rather than invent any value. Supply your real data so the numbers drive the motion.
- Treat the first build as a draft: have it run its geometry check, take screenshots at full width and at 400 pixels, and rank the three fixes that would help clarity most without applying them. Accept the fixes individually, then check the figure yourself in a browser.
- Export in the shape you need: a self-contained HTML file or a single SVG, React components, or custom elements, in one of five themes. For client work, brief it with the audience, the insight the figure has to land, their real numbers and the theme.
- Optional: The source article includes five ready prompts (metaphor finder, first figure, true numbers, inspector and client figure).
- Note: Anatomy is a third-party Claude Code skill by Ryan (@wheresryan22), MIT, version 1.0 from 2026-10-10.
Run this method with your agent
Download .mdCopied 0
--- name: "make-interactive-explainer-figures-with-anatomy-method" description: "Use when you need to Turn a concept into an interactive machine-style explainer figure. Make interactive explainer figures with the Anatomy skill" --- # Make interactive explainer figures with the Anatomy skill Job: [Turn a concept into an interactive machine-style explainer figure](https://aiagents.org/canai/make-interactive-explainer-figures-with-anatomy) ## Need - ai agent: [Claude Code](https://aiagents.org/agents/claude-code), [Anatomy skill](https://aiagents.org/agents/anatomy-skill), [Claude](https://aiagents.org/agents/claude) ## Steps 1. Install the Anatomy skill once for all projects (or only in one project folder), after reading its SKILL.md, since it runs scripts on your computer. It needs a recent Node.js (20.10+) plus a Chromium-based browser for its checks; reload skills if Claude Code was already running. 2. Describe the idea rather than the picture: in an ordinary chat, ask for three candidate physical machines that would act out the concept for your audience, each mapping its parts to the concept, with one key motion and one real number for the readout, and no boxes or arrows. Pick the one a beginner would grasp fastest. 3. Choose the size before building: a Figure (roughly 40 to 80 parts, under about 90 minutes), a Hero (up to about 150 parts, a few hours) or an Epic (a whole vehicle or building, six hours or more). Start with a Figure. 4. Write the build request with the machine-to-concept mapping, the key movement to show and the readout value, and add the keyword interactive (plus WebGL or 3D only if needed; 3D is beta). Ask for a single HTML file and tell it not to move up to Hero without asking. 5. Before it builds, have it list every number the figure will show, with unit and source, and stop to ask rather than invent any value. Supply your real data so the numbers drive the motion. 6. Treat the first build as a draft: have it run its geometry check, take screenshots at full width and at 400 pixels, and rank the three fixes that would help clarity most without applying them. Accept the fixes individually, then check the figure yourself in a browser. 7. Export in the shape you need: a self-contained HTML file or a single SVG, React components, or custom elements, in one of five themes. For client work, brief it with the audience, the insight the figure has to land, their real numbers and the theme. 8. Optional: The source article includes five ready prompts (metaphor finder, first figure, true numbers, inspector and client figure). 9. Note: Anatomy is a third-party Claude Code skill by Ryan (@wheresryan22), MIT, version 1.0 from 2026-10-10. ## Credit Method author Kanika (@KanikaBK); skill by Ryan (@wheresryan22) Source: https://x.com/KanikaBK/status/2109581014968439139
No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/make-interactive-explainer-figures-with-anatomy - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "make-interactive-explainer-figures-with-anatomy",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}