graphify
Transform code, documentation, and more into queryable knowledge graphs.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 71.2k
- Source
- skill-github
- Repository
- github.com/safishamsi/graphify
Overview
Graphify is an AI coding assistant skill that supports multiple coding assistants (such as Claude Code, Codex, OpenCode, etc.). It can convert code, SQL schemas, R scripts, shell scripts, documents, papers, images, or videos into queryable knowledge graphs. With simple commands, users can generate reports containing key concepts, connections, and suggested questions, and view the graphical results in a browser. Ideal for developers and teams to quickly understand and manage project structures.
Capabilities
- ▪Convert code files into knowledge graphs
- ▪Generate Mermaid call flow diagrams
- ▪Generate reports on key concepts and connections
- ▪Support multiple coding assistants
Use cases
Setup
uv tool install graphifyy or pipx install graphifyy, then run graphify install to register the skill.
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I install Graphify?
Install the graphifyy package using uv or pipx, then register the skill.
Which coding assistants does it support?
Supports multiple coding assistants including Claude Code, Codex, OpenCode, Cursor, and others.
Related skills
mantis
Provides security review capabilities for AI coding agents, automatically discovering, reproducing, and fixing vulnerabilities.
sast-skills
Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.
Lightswind-UI-Library
AI-native CLI-first React component library with MCP Server support.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.