#8282nd of 85 in Skills, plugins and rules
anatomy
Agent skill that builds interactive isometric figures to explain technical ideas
- Stars
- 9.1k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- JavaScript
Missed the latest GitHub check; these facts may be older.
Overview
Anatomy is an Agent Skill for Claude Code, OpenCode, Codex and Antigravity. Given a concept, it invents a physical object whose behaviour models the idea and builds it as an interactive isometric figure in SVG, SVG plus WebGL, or beta 3D. Output is standalone HTML, a lone SVG, or React/Next.js components, with a zero-dependency Node kit and geometry audit scripts.
Who it is for: Developers who want interactive figures for docs, blogs or landing pages
Strengths
- Installs with one `npx skills add` command across four agents; no API keys needed
- Kit uses only Node built-ins; React is needed only for the React components
- Includes geometry audit and headless Chrome capture scripts to verify figures
- Ships nine built examples, including React components copyable into a site
Weaknesses
- Verification needs headless Chrome, which the Codex sandbox may block without config changes
- 3D mode is marked beta and only re-renders the moving parts
- Raptor engine example build takes a few minutes; 3D audit is slow
- Repository is about 10 MB because the CLI copies examples too
What it needs
- no GPU
- Needs Node.js >= 20.10, headless Chrome (for verification)
- Models: Claude Code, OpenCode, Codex, Antigravity
Also in Skills, plugins and rules
See all 85| Rank | Project | Score |
|---|---|---|
| 1 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| 2 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 94 out of 100 |
| 3 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 94 out of 100 |
| #4 | ponytailSkill prompt that makes coding agents write less code and add tests | 92 out of 100 |
| #5 | impeccableDesign skill with 24 commands and a detector for AI-generated frontends | 92 out of 100 |