The Ultimate Collection of 900+ Agentic Skills for Claude Code/Antigravity/Cursor. Battle-tested, high-performance skills for AI agents including official skills from Anthropic and Vercel.

Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.

AI that ships your tickets - autonomous dev pipeline with Claude Code

Bootstrap projects from Figma, Linear, Notion & GitHub specs. The only AI ralph with source integrations.

🤖 World's first AST-powered AI development agent | Autonomous Django/Flask builder | Zero-token intelligence | Military-grade sandbox | Made in India 🇮🇳

Governance runtime enforcing immutable constitutional rules on AI coding agents

EverythingAgent - Windows 桌面 AI 助手与自主编码代理 强大的 Windows 桌面 AI 助手，集文件管理、网络搜索、代码生成、文档处理于一体。支持 Everything 快速文件搜索、自主编码工作流、多格式文档生成、系统命令执行，以及完整的文件和应用管理功能。

Autonomous multi-agent coding system on local LLMs. No frameworks, no API costs. Plan → Build → Test → Fix with Qwen 80B + 7B on your own GPUs.

Structured wrapper for autonomous AI coding with Claude Code. PRD-driven task planning, atomic verification, and bash loop execution.

🌌 Explore 255+ essential skills for AI coding assistants like Claude Code and GitHub Copilot to enhance your development workflow.

The Intelligence Layer for your Software Development Lifecycle. Installable, scalable, and self-learning.

Autonomous coding agent that ships tested PRs from GitHub issues. Trust-scored multi-agent pipeline - every decision transparent. Trust is earned, not assumed. 💎

Persistent semantic memory for AI agents. Makes repositories self-aware by structuring intent, constraints, and architecture into a graph that survives context windows.

🚀 Workflow for generating .cursorrules and AGENTS.md files with dynamic AI skills integration

Security-first autonomous coding for GitHub Copilot. Issue-to-merge automation with 4-layer security architecture. Full autonomy with configurable guardrails.

AI-driven development system for graphical web applications using autonomous vision-guided iteration loops and open source models.

Production-ready autonomous coding agent with React UI. Two-agent pattern, JWT auth, loop detection, checkpoints & rollback. Built on Claude Agent SDK.

AI agent that plugs into any codebase — scans your stack, generates specs through AI interviews, and runs autonomous coding loops. Works with Claude Code, Codex, or any CLI-based coding agent.

An architecture for autonomous full-stack AI development — division of labor across agents, vision-driven validation

Mobile dev cockpit for Claude Code & Codex CLI — monitor, review, and steer autonomous coding sessions from your phone