Improve Codebase Architecture

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Overview

The Improve Codebase Architecture skill, found within the mxyhi/ok-skills repository, enables AI agents to evaluate software structures for technical debt and design inconsistencies. By synthesizing information from domain-specific documentation in CONTEXT.md and historical architectural decision records in the docs/adr/ folder, the skill identifies specific areas for refactoring. It is particularly effective for consolidating tightly-coupled modules and improving the overall testability of a project. This tool helps ensure that codebases remain navigable for both developers and AI models. Part of a repository with 423 stars, this skill supports various agents including Claude, Cursor, and Codex, focusing on aligning implementation with established project standards.

Use Cases

Consolidating tightly-coupled modules to improve modularity and separation of concerns.
Identifying refactoring opportunities based on historical architectural decision records.
Enhancing codebase navigability and testability for automated AI development agents.

Install Notes

# Review source first
open https://github.com/mxyhi/ok-skills/blob/main/improve-codebase-architecture/SKILL.md

Copy or clone the skill folder into your agent skills directory after reviewing its instructions and scripts.

Security Notes

This skill requires read access to project documentation and architectural records to provide informed recommendations. Users should verify that CONTEXT.md and ADR files do not contain sensitive information or hardcoded credentials. The skill's functionality is limited to codebase analysis and does not specify additional external execution permissions.

Related Skills

Skill Creator

anthropics/skills

Coding

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Claude CodeClaude
pythondesign
150,001 starsSource linked

MCP Server Development Guide

anthropics/skills

Coding

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

CodexClaude
typescriptpython
150,001 starsSource linked

Building LLM-Powered Applications with Claude

anthropics/skills

Coding

This skill helps you build LLMpowered applications with Claude. Choose the right surface based on your needs, detect the project language, then read the relevant languagespecific documentation.

Claude CodeClaude
typescriptpython
150,001 starsSource linked

Karpathy Guidelines

mxyhi/ok-skills

Coding

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

CodexClaude Code
review
423 starsApache-2.0

Vercel AI SDK — Build AI-Powered Apps in TypeScript

TerminalSkills/skills

Coding

You are an expert in the Vercel AI SDK, the TypeScript toolkit for building AIpowered applications. You help developers integrate LLMs (OpenAI, Anthropic, Google, Mistral, Ollama) with React Server Components, streaming UI, tool calling, structured output with Zod schemas, RAG pipelines, multistep agents, and edgecompa

CodexClaude Code
typescriptreact
71 starsApache-2.0