CommunityCoding & Developmentgithub.com

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

What is trajrl-bench?

trajrl-bench is a Claude Code agent skill that trajRL-Bench: AI agent skills benchmark. SSH sandbox with mock services, LLM judge scoring, split-half delta evaluation. Leaderboard at trajrl.com/bench.

Works with~Claude Code~Codex CLI~Cursor
npx skills add trajectoryRL/trajrl-bench

Installed? Explore more Coding & Development skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

What does trajrl-bench do?

TrajRL-Bench: AI agent skills benchmark. SSH sandbox with mock services, LLM judge scoring, split-half delta evaluation. Leaderboard at trajrl.com/bench

Related Skills