[GitHub Trending] cathrynlavery/diagram-design

7.6 relevance

Editorial diagram types for AI coding agents is highly actionable and novel for developer experience.

AI/ML github.com

Answer the board on AI readiness

Arrive with evidence, not opinion. See how your foundation benchmarks against your peers, get a clear read, and leave with a ranked place to start.

Why It Matters

For a platform engineer building AI-augmented SDLC tooling, this skill eliminates the friction of generating consistent, editorial-quality architecture diagrams from LLM outputs—no more fighting Figma or accepting generic rounded boxes—and integrates directly into agent workflows via Claude Code, Codex, or Agent Skills-compatible hosts.

Key Takeaways

Install the skill via `/plugin marketplace add cathrynlavery/diagram-design` and enable auto-update to generate brand-consistent architecture diagrams in 60 seconds from any LLM chat.

38 editorial diagram types for Claude Code, Codex, and Pi. Self-contained HTML + SVG. No shadows. No Mermaid slop. - cathrynlavery/diagram-design

Summary

Diagram Design v2.5.10 is a Claude Code skill offering 39 editorial-quality diagram types (Sankey, fishbone, Wardley map, UML class, database schema, etc.) as self-contained HTML+SVG with no build step or external dependencies. Semantic patterns decouple behavior from layout, allowing reuse of existing types for queues, policy traces, or trust boundaries without expanding the type count. Static HTML remains the default output, with optional accessible motion for ordered explanations, and the skill can redraw draw.io or Mermaid sources at a chosen format, size, and detail level.

Author

cathrynlavery