#claude-code

UI UX Pro Max Skill, developed by NextLevelBuilder, is an AI Agent product dedicated to providing intelligent design assistance for UI/UX across multiple platforms and frameworks. Its flagship feature, introduced in v2.0, is the "Intelligent Design System Generator." This powerful AI-powered reasoning engine swiftly analyzes project requirements to generate a complete, tailored design system in seconds. It performs multi-domain parallel searches across 161 product types, 67 UI styles, 161 color palettes, 24 landing page patterns, and 57 typography combinations. The output includes professional recommendations for page patterns, styles, color schemes, typography, key effects, and a crucial pre-delivery checklist, empowering designers and developers to efficiently build professional, user-friendly, and accessible cross-platform interfaces.

CLIProxyAPI is a powerful proxy server designed to unify access to various command-line interface (CLI) based large language models. It transforms services like Gemini CLI, Antigravity, ChatGPT Codex, Claude Code, Qwen Code, and iFlow into an OpenAI/Gemini/Claude/Codex compatible API. This enables developers to seamlessly integrate and utilize their existing subscriptions or CLI access to leading LLMs, including Gemini, GPT, Claude, and Qwen, through a standardized API. Key features include multi-account load balancing, OAuth-based authentication for Codex and Claude Code, multimodal input, function calling, and streaming support. The product offers deep integration with Amp CLI and IDE extensions, providing intelligent provider routing, model fallback, and mapping capabilities, alongside a reusable Go SDK for embedded proxy solutions, enhancing productivity for AI coding and application development.

The ai-website-cloner-template is an innovative AI-driven tool engineered to reverse-engineer and reconstruct any existing website into a clean, modern Next.js codebase. Leveraging advanced AI coding agents, it employs a multi-phase intelligent pipeline that automates reconnaissance, design token and asset extraction, component specification generation, parallel code building, and final assembly with quality assurance. This product accurately captures a website's visual styles, interactive behaviors, and responsive layouts, transforming them into high-quality code built on Next.js 16, shadcn/ui, and Tailwind CSS v4. Key applications include migrating websites from platforms like WordPress or Webflow to a modern stack, recovering lost website source code, and serving as a powerful tool for learning and deconstructing professional-grade website architectures. It supports various leading AI coding agents, including Claude Code, significantly boosting development efficiency and code quality.

get-shit-done (GSD) is a lightweight yet powerful meta-prompting, context engineering, and spec-driven AI-assisted software development system. It fundamentally addresses 'context rot' in large language models, ensuring consistent code quality across diverse AI coding assistants like Claude Code, Copilot, and Gemini. GSD orchestrates complex subagent workflows, state management, and XML prompt formatting, offering developers a streamlined, high-efficiency experience. Featuring robust built-in quality gates, including schema drift detection, threat model-anchored security enforcement, and scope reduction detection, GSD reliably transforms ideas into high-quality, verified code, eliminating the overhead of traditional enterprise development complexities.

Rowboat is an open-source, local-first AI coworker designed to build and leverage a long-lived knowledge graph from your digital workspace. By connecting to services like Gmail and Google Calendar, it transforms your emails and meeting notes into an inspectable, Obsidian-compatible Markdown vault stored locally. This unique approach allows Rowboat to remember important context and help you act on it—from drafting documents and preparing meeting briefs to tracking topics and automating follow-ups. Emphasizing privacy and local data storage, Rowboat offers a compounding memory system that understands and anticipates your needs, supporting both local and hosted AI models, and extensible through external tools for enhanced productivity.

The `claude-code-best-practice` project is a comprehensive guide for mastering agentic engineering with Claude Code. It compiles best practices, conceptual frameworks, and practical implementations for developing sophisticated AI agents. The resource covers core components like Subagents, Commands, Skills, and Hooks, emphasizing robust workflow orchestration and efficient context management. It guides developers in leveraging advanced features such as Routines, Devcontainers, and MCP Servers to build high-performing, adaptable, and integrated Claude-based solutions, transitioning from 'vibe coding' to systematic 'agentic engineering'.

graphify is a multimodal knowledge graph construction tool designed for AI Agents, deeply integrated into the Claude Code environment. It transforms diverse information sources—including code, documents, papers, images, and even video links from any folder—into a queryable, structured knowledge graph. Leveraging Claude Vision, graphify extracts core concepts and relationships from various formats, including multilingual images, to build an interconnected knowledge network. This product significantly enhances information retrieval efficiency, reducing token consumption by up to 71.5 times per query, and supports cross-session graph persistence. It intelligently identifies "god nodes," "surprising connections," and "suggested questions." Additionally, it offers automatic synchronization with codebases via `--watch` mode or maintains graph currency through a Git Commit Hook. Outputs include interactive HTML, Obsidian Vaults, and agent-navigable Wikis, providing efficient intelligent assistance and knowledge management for developers and researchers.

Development kit for working with the Claude Agent SDK. Interactive setup for new Agent SDK projects with validation agents.

Automated migration of model strings, beta headers, and prompt adjustments from Sonnet 4.x and Opus 4.1 to Opus 4.5.

Automated PR code review using 5 parallel Sonnet agents for CLAUDE.md compliance, bug detection, historical context, PR history, and code comments.

Git workflow automation for committing, pushing, and creating pull requests. Commands: /commit, /commit-push-pr, /clean_gone.

Adds educational insights about implementation choices and codebase patterns. Hook injects educational context at the start of each session.

Comprehensive feature development workflow with a structured 7-phase approach. Agents: code-explorer, code-architect, code-reviewer.

Create distinctive, production-grade frontend interfaces that avoid generic AI aesthetics. Auto-invoked for frontend work with guidance on bold design choices.

Easily create custom hooks to prevent unwanted behaviors by analyzing conversation patterns or explicit instructions.

Interactive learning mode that encourages users to write meaningful code (5-10 lines) at decision points while receiving educational insights.

Comprehensive toolkit for developing Claude Code plugins with 7 expert skills and an 8-phase guided workflow for building plugins.

Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification.

Interactive self-referential AI loops for iterative development. Claude works on the same task repeatedly until completion.

Security reminder hook that monitors 9 security patterns including command injection, XSS, eval usage, dangerous HTML, pickle deserialization, and os.system calls.