skill
ocupação
descrição
atualizado
run-analysis
Desenvolvedores de software
Full post-run pipeline for RLE benchmark runs — leaderboard analysis vs baseline, failure taxonomy, story mining with verbatim verification, footage indexing, and X-ready video production. Use after any live run or model spread completes.
2026-06-11
benchmark
Analistas de garantia de qualidade de software e testadores
Run the full RLE benchmark suite (6 scenarios)
2026-04-09
live
Desenvolvedores de software
Run RLE against a live RimWorld colony with dashboard
2026-03-24
status
Administradores de redes e sistemas de computador
Show current RLE project status
2026-03-24
test
Analistas de garantia de qualidade de software e testadores
Run full test suite and lint
2026-03-24