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

O que é 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.

Funciona com~Claude Code~Codex CLI~Cursor
npx skills add trajectoryRL/trajrl-bench

Installed? Explore more Programação e Desenvolvimento skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

Documentação

O que trajrl-bench faz?

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

Habilidades Relacionadas