AGENTS.md rules / skills for AI coding agents: Codex, Cursor & Claude Code. Inspired by Clean Code, Refactoring, DDD, Clean Architecture and DDIA programming books.

Build, debug, profile, test, refactor, and release Swift apps across iOS, macOS, Xcode, SwiftUI, SwiftPM, Tuist, and App Store Connect.

Graph-based long-term memory skill for AI (LLM) coding agents — faster context, fewer tokens, safer refactors

SOLID principles and design patterns for backend code — applied with restraint. Skill for Claude Code, OpenCode, GitHub Copilot, and OpenAI Codex.

Code-quality skills by Max Kanat-Alexander.

Production-Stage Visual Design & In-Codebase UI Engineering Suite

humanizer, but for code — an agent skill that removes AI-generated code slop: duplicated helpers, try-import fallbacks, broad excepts, speculative abstractions. Test-gated, behavior-preserving.