agentleFS
Sign inStart free
podopodo/design-agent-skills/skills/anatomy/SKILL.md

anatomy

Skill32 starsChanged 6 months agoMITView on GitHub

Build carefully crafted, interactive isometric SVG figures that explain a technical idea as a real physical object — a machine whose moving parts are the concept — framed in a card with a title, hint and live readout. Use for isometric illustrations, explanatory figures for docs or blog posts, and interactive explainers of how a system, algorithm or component works. Optionally adds WebGL shaders, true 3D, or a printable A4 PDF.

18 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use autoresearch.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • GitHubSkill

    autoresearch

    Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy''s autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.

    Also in 3 projects that use this

The file

Create a free account to mount
Files
SKILL.md

anatomy

Catalogue stub — full skill: wheresryan22/anatomy

<!-- das:install:start — generated from stub.yaml by `npm run generate`; edit stub.yaml, not this block -->

Decision tree

  1. Is the full skill already installed?
    • Global: f=~/.agents/skills/anatomy/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"
    • Project: f=.agents/skills/anatomy/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"
    • installed → the skill is installed as anatomy, invoke it and proceed
    • pointer → go to step 2

  2. Detect scope, then install:

    [ -e ~/.agents/skills/anatomy ] && echo "global" || echo "project"

    Global:

    npx skills add wheresryan22/anatomy --skill anatomy -g -y

    Project:

    npx skills add wheresryan22/anatomy --skill anatomy -y

    Claude Code: send a command as a chat message starting with ! to run it without leaving the conversation.

Heads-up

  • License: MIT
<!-- das:install:end -->

Invoke after install

  • Skill name: anatomy
  • Trigger phrases: "isometric illustration", "anatomy figure", "interactive explainer"

What it does

Invents and draws a real object whose mechanism is the idea being explained, instead of boxes and arrows. One line of prompt ("explain how an LRU cache evicts entries, interactive") yields a self-contained interactive figure: dozens to hundreds of solid parts, one isometric camera looking down at 30°, four-tone shading, painter's order solved per frame, one lit accent part, and a live readout whose numbers come from the same small model that drives the motion.

Work happens in a fixed order — size the figure (Figure / Hero / Epic), collect the real numbers into a model, invent the object, list 40+ parts, plan the world, build geometry once, paint back to front, frame it, make it live, then audit it with screenshots at 4×. Output is framework-free TypeScript that writes SVG and HTML, React/Next.js components, or a printable A4 PDF (poster, drawing, handout). Opt-in keywords in the prompt add WebGL shaders (WebGL) or true 3D (3D), and it respects prefers-reduced-motion with keyboard and pointer interaction.

Six worked examples ship with it, from a ~300-line dial gauge up to a full turbofan engine, and the agent opens the closest one before starting. Expect 30–90 minutes for a normal figure; a Hero is 2–4 hours.

When NOT to use

  • Structural or flow diagrams where the boxes-and-arrows abstraction is the point (use excalidraw-diagram, or hand-drawn-diagrams for a rough sketch look)
  • Anything that has to come back in seconds: this skill optimises for detail over speed and will not trade parts for turnaround
  • Abstract data charts and infographics (use antvis-chart-skills), or 3D scenes that are art rather than explanation (use threejs-claude-skill-package or shader-dev)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free