trajectoryRL/trajrl-bench
TrajRL-Bench: AI agent skills benchmark. SSH sandbox with mock services, LLM judge scoring, split-half delta evaluation. Leaderboard at trajrl.com/bench
TrajRL-Bench: AI agent skills benchmark. SSH sandbox with mock services, LLM judge scoring, split-half delta evaluation. Leaderboard at trajrl.com/bench
npx skills add trajectoryRL/trajrl-benchTrajRL-Bench: AI agent skills benchmark. SSH sandbox with mock services, LLM judge scoring, split-half delta evaluation. Leaderboard at trajrl.com/bench
Personal Claude Code skills collection
Claude Code 投資研究與組合管理框架：skills + MCP + 第一性原理紀律 + thesis ledger
Synthadoc: An open-source LLM knowledge compilation engine that turns raw documents into structured, local-first wikis. A transparent, human-readable alternative to traditional RAG, which can be self-managed and self-improved without the use of any tools.
MNC-style pharmaceutical pipeline asset assessment Agent Skill
Agent skill repository: wandanan/dazi-todo-releases
Teams-first Multi-agent orchestration for Claude Code