Trackdub

Review pull requests in the Trackdub public core (Mesililm-LLC/Trackdub). Use for Copilot code review, PR review, architecture checks, dependency-direction violations, model/license safety, fake readiness, runtime planner routing, and honest test evidence. Prefer this skill whenever reviewing diffs, pull requests, or suggesting review comments in this repository.

Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or isolate work for review; whenever a user mentions a stack, branch layers, dependent PRs, or gh stack; or when a stack is checked out.

Diagnose and verify media cleanup in Trackdub projects.

Windows ML (WinML, Microsoft.Windows.AI.MachineLearning) guidance in three evidence tiers - Microsoft Learn canon, ONNX Runtime/GenAI source and NuGet facts, and dated Trackdub observations. Use whenever work touches Windows ML or WinML, ExecutionProviderCatalog, EnsureReadyAsync/TryRegister, GetEpDevices, execution provider selection or registration, onnxruntime.dll conflicts, Microsoft.ML.OnnxRuntimeGenAI.WinML, DirectML availability, EP-context compilation, or a Windows ML / ONNX Runtime upgrade, even when the user only says "DirectML is broken" or "why doesn't the NPU show up".

Windows ML (WinML, Microsoft.Windows.AI.MachineLearning) guidance in three evidence tiers. Tier 1 is canonical Microsoft Learn documentation. Tier 2 is ONNX Runtime / ONNX Runtime GenAI source and NuGet package facts. Tier 3 is Trackdub's own dated observations. Covers model setup, all Windows ML execution providers (CPU, DirectML, OpenVINO, QNN, VitisAI, MIGraphX, NvTensorRtRtx, experimental WebGPU), deployment, ExecutionProviderCatalog install and registration, OrtEpDevice selection, EP-context compilation and caching, ONNX Runtime GenAI on Windows ML, and diagnostics. Use whenever work touches Windows ML or WinML, ExecutionProviderCatalog, EnsureReadyAsync/TryRegister, GetEpDevices, onnxruntime.dll conflicts, Microsoft.ML.OnnxRuntimeGenAI.WinML, DirectML availability, or a Windows ML / ONNX Runtime upgrade, even when the user only says "DirectML is broken" or "why doesn't the NPU show up".

Definition-first code search over locally indexed repos (xerj search / xerj def)