EvoMap/AutoResearch

ar-coordinator

AutoResearch 协调器:读取 idea 文件,在持久化 project_root 上调度 planner/coder/reviewer/runner。支持普通线性流水线,也支持 Ralph loop 驱动的可恢复工作流:每轮读取 state、做一个未完成单元、写回 state,全部完成时输出 <promise>AUTORESEARCH_DONE</promise>。Args = idea 文件路径 [可选 project_root]。

원문 언어: 중국어

ar-experiment-runner

ar-runtime skills top-level experiment orchestrator on a Linux GPU server. MUST be used for any short experiment request such as "我需要做某个实验", "我要做一个实验", "帮我跑个实验", "做一下这个实验", "运行这个实验", "跑一下这段代码", "run an experiment", "create and run an experiment", "smoke…

원문 언어: 영어

ar-gpu-preflight

GPU need analysis, sizing, allocation, and pre-run RED/YELLOW/GREEN check on a Linux GPU server. MUST be used before running any code that imports torch/jax/tensorflow, mentions cuda/GPU, uses .cuda() / .to("cuda") / device="cuda", may allocate GPU memory,…

원문 언어: 영어

ar-workspace-safety

Hard filesystem and Python-environment safety rules for ar-runtime skills on a Linux GPU server. MUST be applied for ANY write, delete, move, install, or python invocation. Triggers like write file, save, mkdir, rm, delete, move, mv, cp, overwrite, cleanup,…

원문 언어: 영어