メニュー
Run compiler or cross-language benchmarks and compare results
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Suggest and apply a semver version bump based on commits since the last tag
Push current branch to remote origin
Scaffold a new Sharpy.Stdlib module (spy-sourced or handwritten C#) with all required files, conventions, docs, and tests
Implement a plan with a coordinated agent team
Regenerate C# snapshot tests and spy stdlib after intentional codegen changes
Stress-test property tests across many rounds to find rare bugs. Each round uses fresh random seeds.
| name | benchmark |
| description | Run compiler or cross-language benchmarks and compare results |
| disable-model-invocation | true |
Run benchmarks for the Sharpy compiler. Two modes:
Runs equivalent programs in all three languages and produces a comparison table.
# All benchmarks
python3 benchmarks/cross-language/run_benchmarks.py
# Specific benchmarks
python3 benchmarks/cross-language/run_benchmarks.py fibonacci sorting
# JSON output for tooling
python3 benchmarks/cross-language/run_benchmarks.py --json
Available: fibonacci, sorting, string_ops, list_comprehensions, matrix_multiply
Measures how fast the compiler itself runs (lex/parse/emit).
# Run full suite
dotnet run --project src/Sharpy.Compiler.Benchmarks -c Release -- \
--filter "*CompilerBenchmarks*" --exporters json markdown \
--artifacts .claude/tmp/benchmark-results
# Specific benchmark
dotnet run --project src/Sharpy.Compiler.Benchmarks -c Release -- \
--filter "*Fibonacci*" --exporters markdown \
--artifacts .claude/tmp/benchmark-results
# Save current results as baseline
cp -r .claude/tmp/benchmark-results .claude/tmp/benchmark-baseline
# Compare next run against baseline (cross-language)
python3 benchmarks/cross-language/run_benchmarks.py --json > .claude/tmp/benchmark-current.json
src/Sharpy.Compiler.Benchmarks/Corpus/benchmarks/cross-language/*/