菜单
Run dogfooding iterations to test the Sharpy compiler
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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
Run compiler or cross-language benchmarks and compare results
Regenerate C# snapshot tests and spy stdlib after intentional codegen changes
| name | dogfood-run |
| description | Run dogfooding iterations to test the Sharpy compiler |
| argument-hint | [number_of_iterations] |
Run the Sharpy dogfooding pipeline to generate, compile, and verify AI-generated test cases.
Parse iteration count from $ARGUMENTS. If empty or non-numeric, default to 5.
Run the dogfooding tool in the background using Bash with run_in_background: true:
cd build_tools && python3 -m sharpy_dogfood run -n <N> --verbose 2>&1
Replace <N> with the parsed iteration count.
Inform the user that dogfooding is running in the background. Each iteration involves AI code generation + compilation + execution, so estimate roughly 1-2 minutes per iteration.
Wait for completion by reading the background task output.
Present results. After the task completes:
dogfood_output/SUMMARY.md (relative to the project root /Users/anton/Documents/github/sharpy/) and present its contents to the user./dogfood-analyze to classify them by root cause.