Testing & Quality skills
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
debug-flydsl-kernel
Debug FlyDSL GPU kernels that produce NaN, inf, wrong results, or crash. Covers cache invalidation, tracing pitfalls (runtime conditionals, range vs range_constexpr), loop-carried state packing, buffer_load addressing, MFMA operand layout verification, LDS bank conflict diagnosis, and systematic error isolation (all-1s test, single-partition test, host-side tensor inspection). Use when a FlyDSL kernel produces incorrect output or compilation errors. Usage: /debug-flydsl-kernel
debug-run-transcript-maintainer
Use when analyzing one Rudder agent run or recent run batches: run IDs, partial IDs, transcripts, run logs, execution traces, runtime failures, finalizer failures, stdout/stderr, run quality, or recent org run behavior.
hickey
Evaluate code (especially LLM-generated) for structural simplicity using Rich Hickey's "Simple Made Easy" framework. Use this skill whenever reviewing a PR, diff, or code snippet for accidental complexity — particularly when the code was generated by an AI coding assistant and line-by-line review isn't feasible. Also use when the user asks about complecting, simplicity vs. easiness, structural coupling, or concept deduplication. Trigger on phrases like "is this simple", "does this complect", "review for complexity", "structural analysis", or any reference to Hickey, Simple Made Easy, or grey-box review.
kernel-trace-analysis
Profile GPU kernels using rocprofv3 to collect ATT instruction-level traces, then analyze the trace data using hotspot_analyzer.py to identify top-K stall hotspots (VMEM-load, VMEM-wait, LDS/SMEM-wait, barrier, MFMA stalls) mapped back to source lines, and produce an actionable optimization plan. Usage: /kernel-trace-analysis <cmd> Can also analyze an existing dispatch dir directly: /kernel-trace-analysis --dir <path>
lds-optimization
Optimize LDS (Local Data Share / shared memory) access patterns in FlyDSL GPU kernels. Diagnose bank conflicts and high lgkmcnt stalls from ATT trace data, then apply swizzle or padding layouts to eliminate conflicts. Also increase the distance between LDS write and subsequent LDS read to hide LDS latency. LDS read preceded by write always requires a sync (s_waitcnt lgkmcnt or s_barrier). Use when trace analysis shows ds_read/ds_write/lgkmcnt as a bottleneck. Usage: /lds-optimization
oob-detection
Detect out-of-bounds memory accesses in CPU or GPU code using static interval analysis and runtime assertions/printfs. Use when investigating OOB, buffer overrun, invalid memory access, HIP/ROCm illegal address, CUDA illegal memory access, silent tensor corruption, or suspicious buffer_load/store address arithmetic.
pr-local-preview-maintainer
Use when checking out, running, previewing, reviewing, or validating a GitHub pull request locally in a safe worktree, including PR preview URLs, local screenshots, readiness checks, logs, and cleanup instructions.
product-acceptance-verifier-maintainer
Use when implemented Rudder feature, UI, workflow, Desktop, CLI, runtime, release, or regression work needs black-box acceptance verification against user requirements and the running product surface.
project-health-auditor
Comprehensive codebase health analysis. Use when reviewing code quality, identifying technical debt, checking dependencies, or assessing project structure.