codegraph

Name: codegraph
Availability: InStock
Author: local

Analyze codebases using graph database and vector index technologies.

Updated May 15, 2026

Search Tags:#architecture #code analysis #codebase #graph database #vector index

Ready to run

npx skills add https://github.com/qazz92/glm-code --skill codegraph-qazz92

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: codegraph
Source: https://github.com/qazz92/glm-code/tree/main/.glm/skills/codegraph
Command: npx skills add https://github.com/qazz92/glm-code --skill codegraph-qazz92

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires codegraph-ai, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill allows you to analyze and understand codebases at a deeper level by leveraging graph database and vector index technologies.

Core Features & Use Cases

Codebase Analysis: Analyze indexed codebases using graph database (neug) and vector index (zvec).
Code Knowledge Graph: Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, and bug root cause from GitHub issues.
Class Diagrams: Generate UML class diagrams for visualizing class relationships and ownership.
PR Review: Score PR risk, detect conflicts, identify auto-merge candidates, and label PRs based on analysis results.
Use Case: If you want to understand the architecture of a large codebase or identify the root cause of a bug in a complex system, this Skill can help you visualize and analyze the codebase in a more efficient way.

Quick Start

Use the codegraph skill to analyze your local codebase and generate a report.

Frequently Asked Questions about codegraph

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I analyze a large codebase architecture and visualize dependencies?▼

Codebase architecture analysis uses a graph database and vector index to map code structure, call graphs, dependencies, and module coupling, generating architecture reports and UML class diagrams for visualization.

How can I perform impact analysis and find dead code in my codebase?▼

Impact analysis and dead code detection are performed by querying a code knowledge graph built from your codebase, identifying hotspots, unreachable code, and dependency chains to evaluate change impacts.

Do I need Python and specific libraries to run codebase graph analysis?▼

Yes, codebase graph analysis requires a Python environment and specific libraries to build the graph database and vector index for indexing code structure and performing semantic search queries.

What is the best way to find the root cause of a bug from a GitHub issue in a complex system?▼

Finding the root cause of a bug from a GitHub issue is best achieved by analyzing the codebase with a graph database and vector index, tracing call graphs and dependencies to pinpoint the exact failure location.

Can I use code analysis to score PR risk and identify auto-merge candidates?▼

Yes, you can use code knowledge graph analysis to review pull requests, score PR risk, detect conflicts, identify auto-merge candidates, and label PRs based on impact analysis results.