“Testing”

Use this skill when you need evidence-bounded failure classification, retry/fallback/escalation, state consistency, user notice, and recovery evidence…

Investigate Astroclaw pnpm test memory growth, Vitest OOMs, RSS spikes, and heap snapshot deltas.

Add a simple Unity Edit Mode unit test to an existing project, run it through the repository's `./unity-test` daemon workflow, inspect `status`, `results`…

Test a half-formed idea in a questioning conversation, with different personas probing its weak points, until the user can act on it or drop it with confidence.

Autonomously verify what a Windows desktop GUI app you are developing (WPF, WinForms, Win32) actually RENDERS — without Computer Use.

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

QA workflow for building test strategies and validating releases: risk-based testing, test pyramid decisions, E2E/integration/unit coverage, exploratory…

Runs the bundled Python echo script with user-provided text.

Plan and write Playwright end-to-end coverage for user-facing generated application features, flows, and failure states.

End-to-end UI testing for the Ducko macOS app using pre-built helper scripts, run in the Lume VM so the user's Mac is not disturbed.

Use after implementation of a SOX-tracked change to run or summarize required tests, capture audit-ready context, and produce deterministic evidence such as…

Run deployed PyGPUBench smoke/profile test mode for a kernel with a standardized artifact that includes repo git hash, kernel diff, command output, and JSON…

自动执行统计检验，根据数据特征（组数、正态性、配对设计）智能选择 t 检验、卡方检验、ANOVA、Mann-Whitney U 等合适方法，并输出包含 p 值、效应量和通俗中文解读的完整报告。当用户需要进行假设检验、组间比较、显著性分析，或提及 t 检验、卡方、方差分析、p 值、配对检验、非参数检验等关键词时触发。

Genome-wide association studies (GWAS) with PLINK.

Plan and write Maestro mobile end-to-end coverage for user-facing generated Expo or React Native flows, including applicable failure paths and dedicated…

Use when a SPEC, INNOVATE, or VALIDATE (Layer 2) approach hinges on an unverified runtime/library/external mechanism: run a probe from the 8-family taxonomy…

Use this skill when you need high-quality test cases from requirements and analysis artifacts; triggers include testcase writer plus and advanced test case…

Vendor-neutral skill to estimate experiment power, sample size, and runtime for product experiments.

Comprehensive QA and testing skill for quality assurance, test automation, and testing strategies for ReactJS, NextJS, NodeJS applications.

Generates production-grade Cypress E2E and component tests in JavaScript or TypeScript.

Testing strategy, test pyramid, unit/integration/E2E testing, load testing, cross-browser testing, and code quality tooling.

Guided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted…

Test animations for motion sensitivity compliance and reduced motion preferences

针对 Kimi Code CLI 的新增或变更功能，规划并执行可重复的端到端冒烟测试。从 git diff 推断功能边界，读取相关文档和代码，设计测试 prompt，以 --print 非交互模式运行本地 CLI，检查进程退出码和 session…