Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
A Multi-Agent System (MAS) evaluation framework using PydanticAI that generates and evaluates scientific paper reviews through a three-tiered assessment approach: traditional metrics, LLM-as-a-Judge, and graph-based complexity analysis.
Multi-LLM comparison and evaluation framework for coaching scenarios
Research and evaluation framework for AI-powered telemetry instrumentation agents
Distributed adversarial behavioral security evaluation framework for LLMs - Swarm-based parallel probing with cryptographic consensus