cuda-debugging
Expert skill for GPU debugging using CUDA-GDB and NVIDIA Compute Sanitizer. Detect memory errors, race conditions, uninitialized memory access, validate atomic operations, analyze kernel synchronization issues, and generate debugging reports with recommendations.
methodical-debugging
Systematic debugging approach using parallel investigation and test-driven validation. Use when debugging issues, when stuck in a loop of trying different fixes, or when facing complex bugs that resist standard debugging approaches.
debug-specialist
디버깅, 디버그, 버그, 에러, 오류, 버그 수정 - Specialized in identifying root causes of bugs, analyzing error logs, and providing robust fixes. Use this when the user reports an error, unexpected behavior, or needs performance troubleshooting.
debugging
Use when debugging bugs, test failures, or unexpected behavior. Supports --scientific and --systematic flags for direct methodology selection.
debug
Hypothesis-driven debugging through observe, hypothesize, test, narrow. Use when something is wrong and you need to find why.
sf-debug
>
root-cause-tracing
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
root-cause-tracing
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
