ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows, an autonomous runtime watchdog, and a pixel-art web dashboard.
You.com skills and plugins for web search, content extraction, research, finance, and integration discovery, helping AI agents build with up-to-date web context.
UK legal API for AI agents and researchers.
Agent skills for daily use
Replace chaotic AI code generation with a disciplined, spec-driven workflow. SDD Pilot enforces structured development phases and quality gates, leveraging AI agents to conduct online research for best practices and plan your architecture before a single line of code is written.
Connect Cursor, Copilot & Claude AI directly to Cheat Engine via MCP. Automate reverse engineering, pointer scanning, and memory analysis using natural language.
make agents think, thoroughly
MCP Server for SigNoz
Moondream MCP Server in Python
Model Context Protocol For R
Raindrop MCP Server
pentestMCP: AI-Powered Penetration Testing via MCP, an MCP designed for penetration testers.
A curated list of Model Context Protocol (MCP) servers
Memory and context manager just works.
The implementation of Model Context Protocol (MCP) server for VictoriaMetrics
Algorand Local Model Context Protocol (Server & Client)
MCP server for reverse engineering tasks in Ghidra 👩💻
A fully functional and production-grade reverse engineering MCP Server
MCP Server with ArcGIS Pro Add-In
Wassette: A security-oriented runtime that runs WebAssembly Components via MCP
Fast, flexible, and open tooling for building intelligent workflows with Cypress.
MCP Server with RouterOS docs + commands + products + changelogs, using SQLite-as-RAG, sourced from MikroTik
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read