anatomy

anatomy

Catalogue stub — full skill: wheresryan22/anatomy

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

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)