Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Run full ADK-Rust workspace verification and produce a findings-first review. Use when validating build/test/lint health, triaging regressions, or preparing merge/release quality reports.
Analyze failed llm_bench execution results for a model. Use when: checking llm_bench log, troubleshooting llm_bench fails.
Validate a newly supported optimum-intel model with OpenVINO GenAI. Use when: checking new model support, verifying model export to OpenVINO IR, running GenAI inference test with llm_bench, benchmarking model accuracy with who-what-benchmark.
Analyze results of WWB execution with a specific model with all possible backends. Use when: checking wwb logs, troubleshooting wwb fails.
Full review of the claude-desktop-bin project - patches vs the official Linux .deb (still needed? new ones needed? did the surrounding code change?), docs accuracy, Linux compatibility across the distro/session matrix, and runtime logs. Orchestrates a team of sub-agents and produces a consolidated report with solution approaches.
Review code for patterns known to cause flaky tests. Use when the user asks to review tests or a change for flakiness, or when reviewing a diff that adds or modifies tests.
后端测试编写指南，包括单元测试、集成测试和E2E测试的编写方法和最佳实践
前端测试编写指南，包括单元测试、集成测试和E2E测试的编写方法和最佳实践
Playwright E2E 测试完整方法论，涵盖项目初始化、Page Object Model、认证复用、API Mock、视觉回归、多浏览器测试、CI 集成和调试技巧