Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This skill enables the creation and iterative refinement of research figures, system architectures, and method diagrams. It transforms prompts, academic papers, or screenshots into structured .drawio files that remain fully editable in diagrams.net.
ML researchers and system architects can use it to reproduce reference figures or resolve layout issues such as text overlap, component alignment, and arrow routing.
WHO IT'S FOR
ML / AI researchers
generating scientific figures and paper method diagrams
System architects
designing ML and system architecture diagrams
Technical writers
reproducing reference figures from existing documentation
Software engineers
iteratively refining technical diagrams via screenshot feedback
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Installs: The repository's complete drawio-diagram-builder skill bundle. · Codex, Claude Code, other local coding agent
Before you start
Python 3 (3.7+)
Browser automation such as Playwright MCP, Puppeteer, or equivalent for screenshot-based visual verification
Internet access so the preview can load https://embed.diagrams.net/
File write access for creating .drawio files
For reference images used as style guides: a vision/image-reading or color-picking capability, or a user-provided palette
In a Codex, Claude Code, or other local coding-agent session—not a terminal—paste the following text exactly:
Install and test the drawio-diagram-builder skill from:
https://github.com/Will-hxw/drawio-diagram-builder-skill
After installing, run its smoke test and tell me the exact skill path.