gkg

Build a knowledge graph from Git repository code for navigation and impact analysis.

Updated Feb 27, 2026
One-click install
npx skills add https://github.com/haidonglethqb/CloudSchool --skill gkg-haidonglethqb
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gkg
Source: https://github.com/haidonglethqb/CloudSchool/tree/main/.claude/skills/gkg
Command: npx skills add https://github.com/haidonglethqb/CloudSchool --skill gkg-haidonglethqb

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

GitLab Knowledge Graph (GKG) provides IDE-like code navigation, semantic analysis, and architecture visualization by building a knowledge graph from repository code, enabling faster understanding and safer refactoring.

Core Features & Use Cases

  • Go-to-definition across files to quickly locate symbol definitions.
  • Find all usages and impact analysis to assess refactoring effects.
  • Architecture visualization and RAG-enhanced code understanding for complex codebases.
  • Supports multiple languages (Ruby, Java, Kotlin, Python, TypeScript/JavaScript) and works with Git repositories.

Quick Start

Index your repository with gkg index and start the HTTP API server with gkg server start to enable go-to-definition and find-usages.

Frequently Asked Questions about gkg

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

FAQPage Schema
How do I find usages and do go-to-definition across multiple programming languages in a Git repository?

Go-to-definition and find-usages across Ruby, Java, Kotlin, Python, and TypeScript/JavaScript are achieved by building a knowledge graph from your Git repository code. Index the repository first to enable these IDE-like navigation queries.

What is the best way to assess the impact of refactoring code in a large codebase?

Impact analysis for refactoring is performed by querying a knowledge graph built from the repository code. This graph maps all symbol usages and definitions to help visualize architecture and assess the downstream effects of code changes.

How do I index a repository and start querying code architecture via HTTP API?

Indexing a repository requires running the indexing workflow command, followed by starting the HTTP API server. Once the server is active, you can execute interactive go-to-definition and find-usages queries through HTTP endpoints and MCP tools.

Does this code analysis approach work with Ruby, Java, Kotlin, Python, and TypeScript?

Yes, semantic code analysis and architecture visualization support Ruby, Java, Kotlin, Python, and TypeScript/JavaScript. The knowledge graph extracts structural relationships across these languages within Git repositories to enable cross-file navigation.

Can I visualize software architecture and enhance code understanding for complex projects?

Architecture visualization is generated from the repository's knowledge graph to clarify complex codebases. This graph-based representation enhances code understanding and enables safer refactoring by mapping structural dependencies.

Why do I need to build a knowledge graph for code navigation instead of using standard text search?

A knowledge graph provides semantic code navigation by mapping structural relationships, whereas standard text search lacks contextual awareness. Building this graph enables precise go-to-definition, find-usages, and impact analysis across multiple programming languages.