DEDUPED We read 1,000+ AI sources. You read one email. Subscribe free

AI USE CASES

How to show a client how a process works with a 3D figure with anatomy

Replace a long written explanation with a rotatable, clickable figure of the process.

Seen in the wild

Evidence: X, Oct 2026

Similar to what people reported. The steps and prompt below are AI written, not copied from those posts.

Who it is forConsultant or architect who struggles to explain a process to a client in words

The problemClients lose the thread in text-only explanations of multi-step systems.

The outcomeAn interactive figure the client can rotate and click through, shared as an HTML page.

What you need first

  • An agent that supports Agent Skills: Claude Code, Antigravity, OpenCode, Codex or MiniMax Code
  • Node.js 20.10 or later (the skills CLI itself may need a newer Node, 22.20 or later for version 1.7.1)
  • Model usage costs from your agent account; the kit has no extra API keys or npm dependencies
  • A browser to open the finished HTML pages (WebGL for the effects layer)

Steps

  1. Install the skill: npx skills add wheresryan22/anatomy -g -a claude-code
  2. Describe the process in one sentence with /anatomy and name the key stages.
  3. Open the generated page and walk the client through the parts.
  4. Export or share the HTML page after checking the labels.

Prompt for your agent

Use wheresryan22/anatomy to build an interactive figure that explains <client process> as a machine with clickable parts. Confirm every stage is labeled and the readout makes sense to a non-technical viewer.

Caveat. Invented metaphors can mislead a client if a detail is wrong, so review each label against your real process before showing it.

About anatomy

An agent skill that builds interactive illustrations of machines and complex systems to explain an idea. Part of this week's top 10 repos: ranked #4 on Repo Radar. View wheresryan22/anatomy on GitHub.

More with anatomy

See all use cases for wheresryan22/anatomy

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page