Testing

当用户明确要求“测试项目”、 “运行 auto-test-project”或“进行项目级测试”时使用。对完整项目执行多轮 A 轮批判性测试与 B 轮质量检查，发现、记录、修复并验证问题。⚠️ 不适用：用户只是想优化功能、询问项目问题，或没有明确测试意图。

Maintain the .qa/ knowledge base of cross-session QA knowledge (quirks, flaky verdicts, defect patterns, contract changes); read before test tasks.

Operates HyperExecute end-to-end for TestMu AI/LambdaTest cloud test execution: analyze projects, create YAML, validate locally, run CLI jobs, debug failures…

Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers and stand the test of time.

当用户明确要求测试代码、代码审查或代码自检时使用。系统化发现并验证代码问题。⚠️ 不适用：用户只是想实现或优化功能、询问代码问题，或没有明确测试意图。

当用户明确要求测试 Skill、运行 auto-test 或对 Skill 进行批判性测试时使用。系统化发现、记录并验证 Skill 问题。⚠️ 不适用：用户只是想开发或优化 Skill，或没有明确测试意图。

Run stepped HTTP load tests with ab/wrk, ramping concurrency levels to collect p50/p90/p99 latency, detect performance inflection points, and recommend…

Run regression analysis (OLS or logistic) on uploaded CSV/Excel data, generating coefficients, R², p-values, VIF, and plain-language interpretation.

Disciplined diagnosis loop for hard bugs and performance regressions.

Scaffold, structure, and manage AI/ML projects that run on AzureML.

Build type-safe LLM applications with DSPy.rb — Ruby's programmatic prompt framework with signatures, modules, agents, and optimization.

Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can…

Generate realistic synthetic data using Spark + Faker (strongly recommended).

Guided development workflow — task decomposition, planning, peer plan review, approval, implementation, tidy, prose polish, check/test, rules compliance…

Periodic evidence-based self-audit of the whole agent system — the orchestrator, its docs/SSOTs, rules, memory, subagents, tools, infra and the work it claims…

Investigates software failures, exceptions, and errors by tracing execution, reproducing the problem, and testing the suspected cause.

Diagnoses hard bugs and performance regressions by building a reproducible feedback loop and testing competing causal hypotheses.

Harden a skill or any agent instruction file (CLAUDE.md, AGENTS.md, GEMINI.md, .cursor/rules, .github/copilot-instructions.md) through judge-panel refinement…

Build RAG / unstructured-document evaluation datasets and demo documents (e.g.

Automated end-to-end UI testing and verification on an Android Emulator using ADB.

Repo-local focused Sage capability, adapter, and notification validation workflow.

Take finished work to a merge-ready PR in one pass - intent, review, live test, docs, lint, PR, and CI.

Cypress end-to-end and component testing operations - selector/retry-ability strategy, cy.intercept network stubbing, cy.session auth, component vs e2e, flake…

Landing discipline for parallel work: sequential test-gated landing queue, pre-land scrub, auto-rebase of in-flight lanes, fleet status, one-shot revert…