Awesome GitHub RepositoriesDevelopment and Code Tools

Superpowers 是一个基于浏览器的游戏开发引擎和协作集成开发环境。它提供了一个用于构建二维交互体验的统一工作区，允许用户直接在 Web 浏览器中管理代码、资产和场景逻辑，而无需本地编译器或沉重的桌面软件。 该平台通过模块化的、基于组件的脚本架构脱颖而出，其中游戏对象由附加的逻辑和视觉属性定义。它支持实时同步，使多个开发者能够同时在同一个项目上工作。该环境旨在作为一种教育工具，通过图形、音频和逻辑的集成创建来教授编程概念。 该系统包括一个全面的构建流水线，处理静态站点 Markdown 编译和基于文件系统的路由。它通过在构建时解析依赖、注入可复用的 UI 组件并管理资产流水线来自动化开发工作流，以确保高效的资源交付。

This project provides a standardized framework for extending the functional range of artificial intelligence agents through a registry of modular, declarative instructions. It enables agentic workflow automation by allowing developers to define task-specific behaviors and operational constraints that guide how agents interact with external tools and execute multi-step processes. The system distinguishes itself through a directory-based discovery model and a plugin-registry architecture that facilitates the distribution of specialized workflows. By utilizing a schema-driven specification that

gstack is an AI agent framework and development workflow system designed to automate the software development lifecycle. It coordinates specialized AI personas to manage tasks across product design, engineering management, and quality assurance, transforming product intent into technical specifications and final releases. The project is distinguished by its deep integration of headless browser automation and semantic code memory. It utilizes a persistent Chromium daemon for web scraping and visual auditing, and implements a searchable knowledge base that logs architectural decisions and repos

This project is a collection of guides, toolkits, and scripts designed to optimize agentic coding workflows using large language models. It provides strategies for orchestrating AI agents, automating git patterns, and enhancing terminal-based development environments. The toolkit focuses on AI agent orchestration and git management, offering patterns for parallel codebase analysis and autonomous testing frameworks. It includes specialized workflows for conducting interactive pull request reviews and performing root cause analysis on continuous integration failures. The project covers a broad

Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the receipt. 76 MCP tools, 30+ agents, local-first.

Hand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.

An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and interact with your apps. I mainly use it as an xcodebuild wrapper to save context.

Collection of agent skills for AI coding assistants

Claude Code plugins and agent skills for AWS development — IaC(CDK/SST), serverless, cost ops, and Bedrock AgentCore

A Claude skill for d3.js.

Automatically updates terminal window titles based on Claude Code tasks—stop guessing which terminal is which.

A claude skill that generate test cases using N-wise test cases using the pypict library

Claude Code skill for analyzing Move packages against the official Move Book Code Quality Checklist

Agent-native way to access any website. Bridging agent CLI and web GUI through API.

A thoughtful "Root of all evil" for engineers and explorers of the software arts. Take any problem a step past the pragmatic answer. A Claude Code skill that surfaces advanced data structures, distributed-systems algorithms, niche frameworks, and frontier tooling — each scored on a calibrated complexity scale.

Claude Code skill: zero-dependency full-page screenshot via Chrome DevTools Protocol

Opinionated Claude Code skill for adding an SEO-first, translate-ready blog to a Next.js Sanity site. 40-question intake, one-page plan, batteries-included spec, AI hero images via Nano Banana Pro.