Use the selected reliable GPU executor from the legacy Workflow.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
For prepared host commands, use the selected aka execution --profile reliable entry point and its --help request format. The selected controller executor retains request checkpoints and known remote job IDs outside the Agent workspace. Retries apply only to confirmed admission/transport failures. An unknown submission outcome must be reconciled by the operator, not blindly resubmitted. An Eval execution timeout is a candidate failure, not an environment outage. Do not switch a failed Eval to Dev.
This selection does not replace a legacy Agent's direct tools/sandbox.py, or install the light HTTP ToolHost or Journal. The light Workflow separately provides its authenticated HTTP client and the gpu-measurement and runtime-records Skills. Do not assume that loading this Skill changes every tool's transport.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Run Kernel evaluation, ABBA comparison, profiling and GPU probes through the session's Supervisor HTTP Runtime.
The English summary is being prepared. Showing the original description.