Egonex-AI/Understand-Anything

Agent skills in the GitHub repository Egonex-AI/Understand-Anything, each with its code score out of 100.

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

Repository score

67 / 100 C

Skills

9

Verified

0

Average skill score

66

GitHub stars

92,258

License

MIT

Open Egonex-AI/Understand-Anything on GitHub

9 skills in this repository

1. understand-figma

   Analyze a Figma file via the Figma REST API and generate an interactive design knowledge graph (pages, screens, components, component sets, instances, design tokens) with a kind:"…

   74B
2. understand-knowledge

   Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.

   74B
3. understand-domain

   Extract business domain knowledge from a codebase and generate an interactive domain flow graph. Works standalone (lightweight scan) or derives from an existing /understand knowle…

   69C
4. understand-diff

   Use when you need to analyze git diffs or pull requests to understand what changed, affected components, and risks

   65C
5. understand-onboard

   Use when you need to generate an onboarding guide for new team members joining a project

   63C
6. understand

   Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships

   62C
7. understand-chat

   Use when you need to ask questions about a codebase or understand code using a knowledge graph

   62C
8. understand-explain

   Use when you need a deep-dive explanation of a specific file, function, or module in the codebase

   62C
9. understand-dashboard

   Launch the interactive web dashboard to visualize a codebase's knowledge graph

   59C

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.