Generates a "learning" PR-review digest — a markdown file at PR_digests/PR_digest_<N>.md that explains what a GitHub PR does, why, and exactly where in the code, with clickable file/line links and trimmed diffs. Use this whenever the user shares a GitHub PR…
Run TPC-H benchmarks on Super Sirius or DuckDB CPU baseline — either the regular per-query timing/validation run, or the TPC-H official power run + throughput run (RF1/RF2 refresh functions reporting Power@Size / Throughput@Size / QphH@Size). Generate data,…
Use this skill to generate benchmark datasets (TPC-H, TPC-DS, etc.). Trigger when the user needs test data at a specific scale factor for benchmarking or testing. Supports parquet and duckdb output formats.
Clean the current Git changes before committing. Use when preparing to commit or when the pre-commit cleanliness hook blocks a commit.
Use this skill to analyze Sirius query execution logs — to find why a query is slow, diagnose validation errors (wrong results), spot excessive downgrading, identify pipeline gaps, or compare two runs of the same query. Trigger whenever the user mentions a…
Use this skill to find exactly which source code to optimize for better GPU performance. Maps nsys profile hotspots to specific Sirius source files and functions, classifies bottlenecks as GPU-bound, CPU-bound, or sync-bound, and recommends actionable code…
Use this skill to understand why a Sirius query is slow, identify GPU bottlenecks, or detect performance regressions. Generates reports with kernel occupancy, memory bandwidth, operator attribution, and cross-run comparisons. Trigger when the user mentions…
Use this skill when the build fails, compilation errors occur, or you see undefined references, linker errors, CUDA compilation issues, missing headers, or template instantiation failures. Analyzes errors, suggests fixes, and iteratively rebuilds until…