Discover and explore top open-source AI tools and projects—updated daily.
axtonliuText-to-diagram generation for Obsidian
New!
Top 36.9% on SourcePulse
This project provides a set of "skills" for Claude Code, enabling users to automatically generate visual diagrams—specifically Excalidraw, Mermaid, and Obsidian Canvas files—directly from text descriptions within Obsidian. It targets Obsidian users, researchers, and developers seeking an efficient way to translate textual information into structured visual representations, thereby enhancing knowledge management and documentation workflows.
How It Works
The core mechanism leverages Claude Code's "skills" feature, which allows prompt-based extensions for specialized capabilities. These skills are implemented as simple markdown files that Claude Code loads on demand. When a user requests a visualization using specific trigger words, the relevant skill processes the input text to generate the corresponding diagram format (Excalidraw JSON, Mermaid syntax, or Obsidian Canvas JSON). This approach offers a more accessible alternative to complex server-based integrations, focusing on demonstrating how AI models can be augmented with practical, output-specific functionalities.
Quick Start & Requirements
git clone https://github.com/axtonliu/axton-obsidian-visual-skills.git) and copy the skill folders (excalidraw-diagram, mermaid-visualizer, obsidian-canvas-creator) into your Claude Code skills directory (e.g., ~/.claude/skills/).Highlighted Details
.md files with embedded Excalidraw JSON, supporting a hand-drawn aesthetic, full Chinese text, and various diagram types (Flowchart, Mind Map, Hierarchy, etc.)..canvas files using MindMap or Freeform layouts. Features smart node sizing, automatic edge creation, color-coded nodes, and overlap prevention algorithms.Maintenance & Community
This project is described as an "Experimental" public prototype. The author's primary focus is demonstrating how tools and systems integrate, rather than active codebase maintenance. Contributions, including bug reports with reproducible cases and feature suggestions, are welcome. The author, Axton Liu, can be found at axtonliu.ai, YouTube (@AxtonLiu), and Twitter/X (@axtonliu).
Licensing & Compatibility
The project is released under the MIT License. This permissive license generally allows for commercial use and integration into closed-source projects without significant restrictions.
Limitations & Caveats
The project is explicitly labeled as "Experimental" and a "public prototype." It does not yet cover all input scales or edge cases, and output quality can vary depending on the AI model version and input structure. Users encountering issues are encouraged to submit reproducible cases, as the primary focus is on demonstrating system integration rather than ongoing maintenance.
1 week ago
Inactive