gkg_skill

This skill provides semantic code analysis with GitLab Knowledge Graph for go-to-definition, usages, impact analysis, and architecture visualization.

Python

0

GitHub Stars

1

Bundled Files

3 weeks ago

Catalog Refreshed

2 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstart where the catalogue uses aiagentskills.

npx veilstart add skill jjuidev/jss --skill gkg

SKILL.md2.4 KB

Overview

This skill provides semantic code analysis powered by the GitLab Knowledge Graph (gkg). It enables IDE-like navigation for large repositories, supporting go-to-definition, find-usages, impact analysis, and architecture visualization. It targets multi-language projects with strong cross-file support for Ruby, Java, and Kotlin, and partial support for Python, TypeScript, and JavaScript. The tool runs locally and stores indexed data under ~/.gkg/.

How this skill works

gkg parses source files into ASTs and stores code entities and relations in a KuzuDB graph database. You index a Git repository, start the local server, and then query via an HTTP API or MCP tools to retrieve symbol definitions, references, and dependency graphs. It is designed for repository-scoped semantic queries and requires stopping the server before re-indexing to avoid conflicts.

When to use it

Locate all usages of a function, class, or variable across a repo
Jump to the definition of a symbol while inspecting unfamiliar code
Perform impact analysis before renaming or removing APIs
Generate architecture or dependency visualizations for design reviews
Improve retrieval-augmented code explanations by resolving precise symbol contexts

Best practices

Ensure the project is a Git repository before indexing
Stop the gkg server before re-indexing to prevent data corruption
Index only relevant repos or subfolders to limit storage and speed up queries
Use the HTTP API or MCP tools for automation and integration with AI assistants
Validate language coverage for your codebase — Ruby/Java/Kotlin have the strongest cross-file results

Example use cases

Refactor a widely used API: find all call sites, call chains, and downstream impact
Onboard to a new codebase: quickly map modules, key types, and where symbols are defined
Pre-merge safety check: verify that a rename or signature change won’t break other components
Generate a service or module dependency graph for an architecture review
Feed precise symbol contexts into an LLM to reduce hallucinations in code explanations

FAQ

No. gkg requires a local Git repository to index and analyze. Clone the repo locally before running index.

Which languages have full cross-file support?

Ruby, Java, and Kotlin currently have full cross-file reference support. Python, TypeScript, and JavaScript are in progress and may have incomplete cross-file results.