classify-repo-artifacts

Categorize codebase artifacts into core, support, generated, test, and infrastructure categories.

1|1|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/quangphu1912/codebase-analyzer --skill classify-repo-artifacts
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: classify-repo-artifacts
Source: https://github.com/quangphu1912/codebase-analyzer/tree/main/skills/classify-repo-artifacts
Command: npx skills add https://github.com/quangphu1912/codebase-analyzer --skill classify-repo-artifacts

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps developers and analysts distinguish between core modules and supporting code, ensuring that analysis efforts are focused on the most relevant parts of the codebase.

Core Features & Use Cases

  • Artifact Categorization: Sorts modules/files into categories like core, support, generated, test, and infrastructure.
  • Provenance Analysis: Utilizes provenance maps to validate classification against the codebase's history.
  • Entropy Analysis: Measures information density and naming patterns to identify core logic and generated code.
  • Use Case: Before diving into a codebase, use this Skill to quickly identify and isolate the business logic, which can then be analyzed in detail.

Quick Start

Run the classify-repo-artifacts skill to categorize the artifacts in your current codebase.

Frequently Asked Questions about classify-repo-artifacts

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

FAQPage Schema
How do I categorize codebase artifacts to isolate core business logic?

Categorize codebase artifacts by analyzing file content, naming patterns, and provenance information to sort modules into core, support, generated, test, and infrastructure groups. This isolates business logic for targeted analysis and refactoring workflows.

What is provenance tracking and how does it validate artifact classification?

Provenance tracking utilizes historical codebase maps to validate artifact classification accuracy. By cross-referencing file history with content and naming patterns, it ensures generated code and core modules are categorized correctly.

How do I identify generated code versus core modules in a large codebase?

Identify generated code by measuring information density and analyzing naming patterns through entropy analysis. This technique distinguishes repetitive, auto-generated files from high-density core logic modules.

Do I need external tools to perform entropy analysis and categorize codebase artifacts?

Categorizing codebase artifacts requires external tools for file analysis and code provenance tracking. The Skill provides the categorization logic and reasoning, while depending on these tools to supply content metrics and historical data.

When should I categorize codebase artifacts before starting a refactoring workflow?

Categorize codebase artifacts before diving into refactoring to distinguish core modules from supporting code. This ensures analysis efforts target relevant business logic rather than test files, infrastructure, or generated code.

What's the best way to separate test and infrastructure files from core modules during code analysis?

The best way to separate test and infrastructure files is to run an artifact classification process that evaluates provenance and entropy. This categorizes files by functional role, cleanly isolating core modules from support code.