anatomy vs archify
Agent skill that explains an idea by inventing a physical machine whose working is the concept, then builds it as an interactive isometric SVG, optionally with WebGL effects. — versus — Agent skill for architecture, workflow, sequence, data-flow and lifecycle diagrams: the agent emits typed JSON IR, Archify compiles it deterministically to interactive HTML/SVG with PNG/WebM export.
Both are agent skills that produce technical figures. Archify draws literal architecture and flow diagrams; Anatomy builds metaphorical interactive machines.
| anatomy | archify | |
|---|---|---|
| Stars | 25k | 94k |
| Forks | 2.1k | 6.4k |
| Language | JavaScript | JavaScript |
| License | MIT | Apache-2.0 |
| Last activity | 19 days ago | yesterday |
| Topics | skills | skills, code-intel |
| Curated connections | 1 | 5 |
anatomy — the curator's take
Use it when a concept needs to land with readers, for docs, posts or talks, and a box-and-arrow chart won't do. No API keys or npm installs; works in Claude Code, Codex, OpenCode, Antigravity and MiniMax Code. Skip it for accurate system diagrams: it uses metaphor, not your real architecture. Each figure takes many tokens and some iteration.
archify — the curator's take
The right tool when an agent needs to *present* a system, not just describe it: `npx skills add tt-a1i/archify`, describe the system (or point at a repo) and you get a self-contained HTML map with search, upstream/downstream tracing, guided stories and a Before/Delta/After compare between two validated snapshots. The model never draws — it emits IR that a validator checks, so the topology can't be hallucinated at render time. NOT a code-derived architecture tool: what it shows is what the agent authored, verified against the schema, not against the code. For a map that is provably the codebase, use a code-intelligence tool and hand its output to Archify.