This repository showcases a production-tested infrastructure for enhancing Claude Code, an AI-assisted development tool. It provides a system for automatically suggesting and enforcing development best practices via hooks that trigger on user prompts and file operations. The core innovation is a skill auto-activation mechanism that uses contextual cues (keywords, intent, file paths, content) to recommend relevant guidelines, with a two-try blocking model for mandatory skills to ensure compliance without excessive nagging. The infrastructure is built around modular skills (each under 500 lines with progressive disclosure), specialized agents for complex tasks, and a dev docs pattern that maintains context across sessions using vector search. It also includes an AI provider abstraction layer supporting multiple LLMs (Gemini, OpenAI, Anthropic, Ollama) for flexible integration. Designed as a reference library, users are encouraged to copy and adapt the hooks, skills, and configurations into their own Claude Code setups, with setup and verification scripts to streamline installation. While not a standalone application, this collection of patterns and tools represents a sophisticated approach to scaling AI-assisted development practices in enterprise environments. Its strength lies in the reusable components: the hook-based skill system, modular skill documentation pattern, and provider abstraction layer, all demonstrating non-obvious craftsmanship in balancing automation with developer autonomy.
This is a Neovim configuration repository that sets up a modern, feature-rich development environment. It uses lazy.nvim for plugin management and configures LSP support, completion (via blink.cmp), keybindings, and various quality-of-life enhancements. The configuration is modular, with separate files for options, keymaps, LSP initialization, plugin configurations, and filetype-specific behaviors. It demonstrates solid Neovim Lua programming practices with thoughtful customizations for productivity.
Cocoa-Way is a macOS-native Wayland compositor that runs Linux GUI applications inside container runtimes (Apple Container, Docker, OrbStack, or via SSH/Waypipe) and renders them to macOS windows using Metal. The core architecture consists of a Rust binary that serves as both a desktop compositor (single window with tiled layout) and a rootless mode that maps each xdg-toplevel to a native macOS window. It features bidirectional clipboard relay (text and PNG, up to 64 MiB), CoreAudio forwarding, a control API over Unix sockets, and an optional MCP server for AI-assisted diagnostics and onboarding. The project demonstrates high craftsmanship in its Metal renderer with texture caching and damage-coalescing, as well as in its container session management, which handles multiple runtime backends and complex lifecycle orchestration. The codebase is well-structured but contains a few monolithic files (e.g., main.rs, container_mode.rs) that handle a large amount of state and UI logic.
Packmind is a developer productivity platform that centralizes engineering standards and distributes them to AI coding agents. It solves the problem of scattered standards (in Slack, Notion, PR comments) that AI agents can't access and the manual copy-pasting of standards across repositories. The platform provides organization/space-based collaboration, Git provider integrations, LLM/AI service abstraction, marketplace for sharing components, deployment/target management, and change proposal workflows. It features a hexagonal architecture with clear separation of concerns across domains (accounts, organizations, spaces, standards, skills, commands, deployments), using NestJS for the backend, React for the frontend, and a separate CLI tool for local artifact management.
This repository provides a collection of Claude Code plugins designed to enhance AI-assisted development workflows. It consists of four specialized utilities: deslop for removing AI-generated code artifacts, dig for conducting deep exploratory interviews to clarify plans, fix-ci for automatically diagnosing and resolving CI failures, and decomposition for breaking down complex tasks into detailed, actionable todos. Each plugin implements sophisticated patterns for improving developer productivity when working with AI assistants. The system follows a modular architecture where each plugin is self-contained with its own command implementation, skill definitions, and metadata. Plugins can be installed via Claude Code's plugin marketplace system and integrate directly into the AI assistant's workflow. The plugins leverage Claude Code's built-in tools (Read, Edit, Write, Bash, etc.) to interact with the development environment, analyze code, and make targeted improvements. Rather than being a monolithic application, it offers composable tools that address specific pain points in AI-assisted development.
IT-Tools is a single-page application (Vue 3 + TypeScript + Vite) that provides a curated collection of over 80 client-side developer utilities. These utilities include hashing, encoding, formatting, conversion (JSON, YAML, TOML, XML, etc.), crypto (JWT, RSA, bcrypt), network tools (IP subnet calculator, MAC address lookup), text manipulation, and many others. All processing occurs entirely in the browser; there is no backend. The app is a monolith with lazy-loaded per-tool routes, using a custom UI component library (c-*) alongside Naive UI, Pinia for state, vue-i18n for translations, and VueUse composables. It is containerized (Docker) and can be self-hosted or used via the hosted version on Vercel/Netlify. The repository demonstrates a strong convention for tool definition, testing, and internationalization, though tool quality varies. It is not a data research or analytics project.
This is a personal dotfiles repository for macOS, automating the setup of a developer environment. It is not a traditional application but a configuration management system using dotbot to symlink config files and Homebrew to install software. The repository manages shell configuration (zsh with oh-my-zsh and zplug), editor settings (VS Code, nano, hyper), browser hardening (Firefox/Zen with arkenfox user.js), macOS system preferences, and a curated set of CLI tools and applications. The core entry point is a bash install script that runs dotbot pipelines. The codebase is well-organized, follows minimalism and security principles, and is actively maintained by a single developer. It demonstrates thoughtful patterns for fzf integration, Docker-based AI agent runners, and peripheral auto-launching, though it remains a personal configuration rather than a reusable library.
This is a VS Code extension that enables users to easily insert gitmojis (emojis related to git commits) into commit messages. The extension activates via a command or SCM menu item, presents an emoji picker, and inserts the selected emoji at a configurable position (start, end, or cursor) in the commit message. It features smart handling of existing emojis (removing them when repeats aren't allowed), usage-based sorting, auto-matching based on commit message content, and support for custom emojis. The architecture follows standard VS Code extension patterns with clear separation between UI logic, data (emoji definitions), and utility functions.