Coding & Development

Claude Code 测试自动化 Skills，覆盖需求分析→用例生成→E2E测试全流程，支持 Sprint 双轨迭代

Test whether your CLAUDE.md, AGENTS.md and .cursor/rules actually survive AI agent execution. Extract rules, generate sandbox scenarios, score compliance.

EverFern AI, the open-source, autonomous AI workplace agent. EverFern doesn't just chat; it uses your computer. Automate complex GUI tasks, navigate apps, and execute workflows natively on your desktop. A free, powerful alternative to Claude Co-work and Manus Desktop.

Automate the evolution and optimization of Hermes Agent’s prompts, skills, and code using genetic algorithms without GPU training.

An MCP (Model Context Protocol) server exposing authoritative, read-only Conda ecosystem metadata for AI agents.

🤖 Self-Evolving Multi-Agent AI System | 116+ Skills | TrendRadar · Reviewer | Learn, Build & Evolve

Periodically refreshed mirror of agents, skills, prompts and instruction files from public repositories.

Persistent memory MCP for AI agents — SQLite, knowledge graph, 12 tools with ToolAnnotations

Pure MCP Server for Claude Desktop, Cursor and Windsurf - Complete, Secure, and Easy-to-Use

Proof layer for AI agents. Cryptographically verify every action.

🦦 ADHDev — Agent Dashboard Hub. Monitor & control AI coding agents from a single dashboard. Self-hosted, open-source.

Open leaderboard for browser agents

Cloudflare native, ai sdk v6 agent workspace ready to use with better auth and all of the cloudflare dev bindings.

MKP is a Model Context Protocol (MCP) server for Kubernetes

Enable AI agents to generate videos, process media, and manage tasks using Pollo AI's official skills and models.

Build AI agents in Elixir and OTP with JidoClaw, a full-stack platform for tools, skills, and providers

Autonomous AI agent (Hermes + Triad) promoting Sergei Solovev's commercial brand. Browser-Use + Anthropic Computer Use + RentAHuman MCP. Production-grade Anthropic Managed Agents harness pattern.

Define an AI agent once, generate the config every tool expects (CLAUDE.md, AGENTS.md, GEMINI.md, .cursor/rules). Clean-room, built on open-gitagent (MIT).

AutoML for Claude Code — multi-agent skill that designs, runs, and reports ML experiments from a text prompt

Skill that designs paste-ready /goal prompts for Claude Code by enforcing the Three Pillars and the 4-Element Structure. Works in Cursor, Claude Code, and Codex.

Build agentic AI workflows with curated tools, MCP server reviews, and technical recipes for software developers.

R-Pay: a fictional UPI-style payment sandbox for India, demonstrating Claude Code agent workflows — state machines, idempotency, incident response, subagents, and RCA — through a simulated midnight payment outage.

Build production-ready AI agent configs for Claude Code with structured workflows, special agents, and clear rules

Orchestrate AI agents with schedules, approval gates, budget limits, and live monitoring for Claude and GPT teams