Bailiang Li

Agent Skill that silently refines prompts for the currently running model

An AI coding assistant add-on that silently rewrites your questions into the format each specific AI model (Claude, GPT, Gemini, Llama) responds to best, then shows you only the final answer.

Claude Code skill for MCP-Safeguard security scanning

Security scanner and runtime protection for Model Context Protocol servers

No description.

A framework for few-shot evaluation of language models.

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.