Skills for running and evaluating computer-use agents on OSWorld and WeaveBench. They cover task validation, trajectory analysis, environment setup, agent migration, and reproducing CUA-Harness experiments from a GitHub checkout.
@amap-mlCheck OSWorld tasks. Validate the evaluation function, verify that the instruction is feasible given the task setup and…
@amap-mlAnalyze OSWorld-V2 agent trajectory logs and task results to produce actionable insights. Use this skill whenever the user wants…
@amap-mlMigrate an agent from upstream OSWorld into this OSWorld-V2 repository, add matching evaluation entrypoints, and verify the…
@amap-mlProvision and verify an OSWorld-V2 checkout after clone. Use when the user asks for OSWorld-V2 setup, installation, onboarding,…
@amap-mlReproduce CUA-Harness experiments on WeaveBench from a GitHub checkout. Use when the user wants an AI coding agent to set up…
@amap-mlIs this you? Claim your profilePut a plugin at the top of Plugins, from $9
