Testing Skills

Chrome 浏览器自动化操作。当用户需要自动化浏览器操作、网页测试、数据抓取或 UI 自动化时使用此技能。

Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.

在任何创意性工作前必须使用：创建功能、构建组件、增加能力或修改行为。通过自然对话挖掘需求，产出高质量验收标准（AC），为后续 TDD 开发提供测试依据。当用户说'我想做一个XX功能'、'帮我想想XX怎么做'、'我需要加一个XX'等模糊需求描述时触发。

When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.

Implements comprehensive backtesting capabilities for Pine Script indicators and strategies. Use when adding performance metrics, trade analysis, equity curves, win rates, drawdown tracking, or statistical validation. Triggers on "backtest", "performance", "metrics", "win rate", "drawdown", or testing requests.

Extended QMD knowledge base with multi-backend embedding (Google AI Studio / Ollama / local). Use when managing QMD embeddings, switching backends, testing embedding quality, re-indexing, or troubleshooting QMD vector search. Triggers on "qmd embed", "embedding backend", "切换embedding", "embedding测试", "re-embed", "知识库embedding", "qmd扩展". For general QMD queries and knowledge retrieval, use memory-router skill instead.

Intelligent skill router and creator. Analyzes ANY input to recommend existing skills, improve them, or create new ones. Uses deep iterative analysis with 11 thinking models, regression questioning, evolution lens, and multi-agent synthesis panel. Phase 0 triage ensures you never duplicate existing functionality.

Write the test first, watch it fail, write minimal code to pass

Never test mock behavior. Never add test-only methods to production classes. Understand dependencies before mocking.

Tool discovery and shell one-liner reference for sysadmin, DevOps, and security tasks. AUTO-CONSULT this skill when the user is: troubleshooting network issues, debugging processes, analyzing logs, working with SSL/TLS, managing DNS, testing HTTP endpoints, auditing security, working with containers, writing shell scripts, or asks 'what tool should I use for X'. Source: github.com/trimstray/the-book-of-secret-knowledge

Test-driven development workflow with test generation, coverage analysis, and multi-framework support

Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

Master AI-powered test automation with modern frameworks, self-healing tests, and comprehensive quality engineering. Build scalable testing strategies with advanced CI/CD integration. Use PROACTIVELY for testing automation or quality assurance.

Evaluate and improve interface usability using heuristic analysis. Use when the user mentions "usability audit", "UX review", "users are confused", "heuristic evaluation", "form usability", "navigation problems", "Nielsen heuristics", "cognitive walkthrough", or "usability testing". Also trigger when reviewing a design for usability issues, improving form completion rates, or evaluating information architecture and navigation. Covers Nielsens 10 heuristics, severity ratings, and information architecture. For visual design fixes, see refactoring-ui. For conversion-focused audits, see cro-methodology.

Vitest testing framework patterns for test setup, async testing, mocking with vi.*, snapshots, and test performance (formerly test-vitest). This skill should be used when writing or debugging Vitest tests. This skill does NOT cover TDD methodology (use test-tdd skill), API mocking with MSW (use test-msw skill), or Jest-specific APIs.

Answers questions about a code repository using source file analysis. Use when the user asks a question about how something works, wants to understand a component, or needs help navigating the code...

Plan, execute, investigate, and report HitKeep quality gates through hk. Use while iterating, before calling contributor work complete, when choosing change-aware versus PR-parity versus exhaustive validation, when CI parity matters, or when investigating a failed or asynchronous gate.

分析 Testany 测试失败原因 - 排查问题、查看日志、定位根因

Testany Git 导入：把 Git 仓库里的测试脚本批量注册成 Testany platform cases，并持续同步、切 commit、演化 binding、配 webhook

Testany platform case 编写助手 - 将传统测试场景拆解为 Testany platform cases，并生成可注册的 case packages

Review test strategy, 测试策略评审。Use when: 测试策略写完后，需要审查风险覆盖、独立测试分层、阶段化执行规则、环境策略与入口/出口标准是否成立。

Write test spec, 测试规格/测试用例包撰写。Use when: LLD 完成且测试策略已确认后，需要产出独立测试范围内完整的 test case package、追溯矩阵与执行说明。

Review test design and readiness, 测试评审。Use when: Test Spec/Test Case Package 完成后，需要审查独立测试范围内的覆盖、追溯、执行证据与遗留风险，作为发布准备前的测试门禁。

Write test strategy, 测试策略撰写。Use when: PRD、API Contract、HLD 基线明确后，需要定义独立测试范围、独立测试层次、阶段化执行规则、环境策略、入口/出口标准。

Expert guidance on Swift Testing best practices, patterns, and implementation. Use when developers mention: (1) Swift Testing, @Test, #expect, #require, or @Suite, (2) "use Swift Testing" or "modern testing patterns", (3) test doubles, mocks, stubs, spies, or fixtures, (4) unit tests, integration tests, or snapshot tests, (5) migrating from XCTest to Swift Testing, (6) TDD, Arrange-Act-Assert, or F.I.R.S.T. principles, (7) parameterized tests or test organization.

>- Add Dynamic Application Security Testing (DAST) steps to existing Harness pipelines using Harness STO scanners. Supports API DAST / Traceable (default), Burp Suite Enterprise, ZAP (OWASP), Nikto, and Nmap. Scans running application instances for vulnerabilities including API security issues, injection flaws, misconfigurations, and exposed services. Can insert the scan step into an existing CI or SecurityTests stage or create a dedicated SecurityTests stage. Use when asked to add DAST scanning, configure dynamic application testing, set up API security scanning, scan a running application, or add runtime security testing to a pipeline. scan running app, add Burp Suite scan, add ZAP scan, add Nikto scan, runtime security scan, API security scan.

>- Optimize Harness CI/CD pipeline performance via MCP. Configure parallel test execution with Test Intelligence, design multi-layer caching strategies, analyze pipeline bottlenecks with stage-level timing breakdowns, optimize cache hit rates, and design monorepo CI pipelines with selective builds. Use when asked to speed up pipelines, improve cache hit rates, set up parallel testing, optimize build times, or configure monorepo builds. Do NOT use for creating new pipelines (use create-pipeline instead) or debugging failures (use debug-pipeline instead). build optimization, caching strategy, monorepo pipeline, pipeline bottleneck, build speed.

Use when the user reports misbehaving software to investigate — a bug, crash, wrong output, flaky behavior, or '為什麼壞掉/不會動/查一下' — and the root cause is not yet established. Enforces building a red-capable reproduction command BEFORE any hypothesis is allowed, then 3-5 ranked falsifiable hypotheses before testing any single one. NOT for conceptual questions, code reading requests, or feature work. When a failing command already exists, Step 1 is pre-satisfied — still apply, jumping straight to the hypothesis discipline.

Test ML functions with fixed input tensors for reproducibility.

Verifies model components like loss functions using unit tests and saves the results as NumPy archives.

Testing SimPO loss function with fixed tensors and output verification

Idiomatic Scala testing patterns with ScalaTest.

Use to execute the unit test within the Python 3.10 virtual environment after implementing the loss function. This validates the implementation against fixed input tensors.

Scala's type system features, testing patterns, and integration with test specifications for ensuring correctness of translated code.

How to set up the correct Python environment for the SimPO project, specifically using Python 3.10 and resolving version conflicts. Use this when setting up the environment to run SimPO code and unit tests.

How to correctly run the SimPO unit test to generate the loss.npz output file with reproducible results. Use when executing the unit test after implementing the loss function.

Use this skill to execute the SimPO unit test with Python 3.10, save the loss results to /root/loss.npz, and log Python version and package info to /root/python_info.txt using the correct Python 3.10 executable.

Executes the provided unit test to verify the SimPO loss implementation and saves the output to a specific NPZ file for evaluation.

Creates an orchestration script to run the immutable unit test and capture the output loss values.

Run PyTorch unit tests, save results to NumPy files, and log environment information for reproducibility. Use this skill when executing test suites for neural network functions, validating loss computations, saving tensor outputs for verification, and creating reproducibility logs with Python/package versions.

Answer questions from JSON enterprise data and write results to answer.json. Use this skill when the user asks multiple questions about enterprise data and needs answers stored in a JSON file with token counts. Handles the output format requirements for answer.json.

Set up and run NLP preference optimization experiments (DPO, SimPO, CPO). Use this skill when configuring trainer environments, installing dependencies (torch, trl, transformers, peft), or running preference optimization unit tests. Triggers on: DPO, SimPO, preference optimization, trl trainer, RLHF, alignment training.

This skill should be used when the user asks to "build", "design", "scaffold", "architect", or "plan" any system, feature, service, app, agent, pipeline, connector, or tool — especially when the request is short, vague, or underspecified. It should also be used when the user asks to "review this architecture", "what am I missing", "ask me the right questions", "poke holes in this", or requests a design review before implementation. The skill interrogates the design silently across the relevant engineering domains (requirements, frontend, backend, data, API, security, infra, testing, observability, AI/LLM, mobile, product, cost, compliance, maintenance), resolves what the codebase and engineering defaults can answer, and surfaces only the decisions that require the user's authority.

Rigorous build process with worktree isolation, structured phases, quality gates, layered testing, observability, and self-improvement. Use for any substantial build task. Structurally enforced via stop hook.

Structured 4-phase debugging methodology that prevents blind probing and guesswork. Forces root cause identification before any fix attempt. Use when encountering bugs, errors, unexpected behavior, test failures, or when something "just stopped working." Trigger words: debug, bug, error, broken, not working, fix this, something's wrong, investigate, root cause, why is this failing, trace the issue.

Read Runx's native receipt history and skill catalog, then return deterministic run outcomes, catalog test coverage, and governance follow-ups without model-authored metrics.

Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions.

Use when reviewing, critiquing, or stress-testing an existing strategy document. Evaluates seven dimensions \u2014 diagnosis quality, guiding policy strength, action coherence, assumption exposure, falsifiability \u2014 with optional 7S, Five Forces, Balanced Scorecard, and Hoshin Kanri lenses. Triggers on: review my strategy, poke holes in this plan, what's weak here, strategy audit, red team this. Does NOT build strategy (use strategy-interview) or brainstorm project ideas (use brainstorm-beagle).