#194194th of 389 in Skills, plugins and promptsFor image, video and design, image and design
stack-diagram
Agent skill that draws stack diagrams with official logos
- Stars
- 2.4k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- TypeScript
71 on 27 Oct 20262,354 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
An agent skill that turns a plain-language description of a stack into an architecture diagram. It fetches official logos from svgl, devicon, gilbarbara/logos or vendor packages (AWS, Google Cloud, Azure), routes lines around labels, and renders light and dark themes. Output is a self-contained HTML file by default, or PNG, a React component or a Claude artifact.
Who it is for: Developers who want their coding agent to draw architecture diagrams
Strengths
- Logos come from official sources and are never recolored or redrawn
- Default output is one HTML file with fonts and logos inlined
- Installs with npx skills add; works with Claude Code, Codex, Cursor
- Covers AWS, Google Cloud and Azure icon sets plus dev tooling
Weaknesses
- Needs network access to download logos at build time
- PNG export requires Playwright with Chromium
- Requires Python 3.9+ alongside the agent
- Optional gallery posting sends the diagram and a display name to a third-party site
What it needs
- no GPU
- Needs Python 3.9+, Playwright with Chromium (PNG export), Network access for logos (svgl, devicon, gilbarbara/logos)
Quick answers
Is stack-diagram open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 389| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |