Query saved measurement evidence and submit an Episode Report without Direction or Experiment recording.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Use python3 tools/sandbox.py inside a controller-registered Episode. Direction and research
Experiment recording are disabled; do not use update-direction or record-experiment.
This does not disable automatic measurement persistence, duplicate detection, correctness checks,
or independent ABBA promotion. Framework Baseline has its own smoke-and-exit procedure.
Inspect saved measurement evidence and optional canonical memory/v*.json summaries when present.
Implement and measure a candidate, then leave its exact source in place (kernel.py or the
contracted source tree from WORKSPACE.md) and cite real Gateway Record IDs in episode-report.
No synthetic Direction, Experiment, separate plan/profile document, or Git operation is required.
skills/gpu-measurement/SKILL.md for new measurements.Read-only Direction/Experiment history queries remain available for earlier recorded Episodes; they do not create records or change the current policy. Never invent IDs or measured results. Reuse saved results rather than repeating identical tasks. Accepted reports can be replayed to repair publication, but different terminal reports are rejected. Report acceptance is not promotion.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Prepare requests for the selected AKA Execution entry point, consult Gateway or SSH guidance, and preserve complete execution output and artifacts. Use for handing prepared GPU commands, evaluation, or profiling work to AKA Execution; experiment planning and result interpretation belong to their callers.
中文简介正在准备中。当前显示原文说明。
Use the selected reliable GPU executor from the legacy Workflow.
中文简介正在准备中。当前显示原文说明。
Let AKA autonomously add, run, inspect, and revise intra-kernel timeline probes for standalone CUDA/inline PTX or CuTe DSL when ordinary benchmark, NSYS, or NCU evidence cannot answer a specific kernel-internal timing question.
中文简介正在准备中。当前显示原文说明。
Generate a structured implementation plan from an evidence draft. Validate paths, obtain configured independent Codex and Qoder reviews, synthesize available advice against repository evidence, preserve the draft, and produce testable acceptance criteria and validation steps.
中文简介正在准备中。当前显示原文说明。
Learn the target framework from enabled knowledge tools and implement a baseline GPU kernel. Use this skill to understand compute semantics, determine the target platform and framework, search reference implementations, and produce a correct V0 baseline with performance records for later profile-driven optimization.
中文简介正在准备中。当前显示原文说明。
Run the evidence loop of one long-horizon GPU kernel optimization episode. Use this skill to reconstruct the incumbent, profile and localize a bottleneck, research progressively, plan one coherent direction, implement and repair, validate development correctness and performance, and record every decisive experiment in the episode journal.
中文简介正在准备中。当前显示原文说明。