Навыки: Тестирование

Compare current benchmark results against historical baselines to spot performance regressions. Use as an explicit/manua...

Code quality, correctness, and documentation review for audio lessons — run before dev-final-pass

Set up before-push validation (b4push) in a project: scripts/run-b4push.sh, the package.json entry, a project-level b4pu...

Review a plan or implementation. Dispatches review executors, validates outputs, owns the review→repair→re-review loop....

Review all project documentation for staleness — READMEs, skills, plans, CLAUDE.md, project structure trees

Run a quality review pass on a lesson before publishing, catching recurring issues found across project PR history

Run a local code review using the CodeRabbit agent before pushing to catch issues early

Check and fix markdown formatting issues with markdownlint-cli2

Performance profiling via Aspire traces

Code quality, correctness, and documentation review for physics lessons — run before dev-final-pass

Internal skill used by dev-design at Phase 4 exit gate. Dispatches a reviewer subagent to verify PLAN.md quality before...

AI DevKit · Planning phase guidance for creating and reconciling feature task plans. Use when the user wants to create a...

Validate diagram correctness against the lesson README before pushing

Internal skill used by dev-brainstorm at Phase 1 exit gate. Dispatches a reviewer subagent to verify SPEC.md completenes...

Use when an implementation-ready story has been approved for bounded source, test, and evidence work.

Read a story file and implement it. Loads the full context (story, GDD requirement, ADR guidelines, control manifest), r...

Define technical specifications including tech stack, security, theme standards (from UX mockup), coding standards, and...

Test-driven development workflow. Auto-detects backend (.NET) and frontend (Angular/TypeScript) from project files. Loop...

Test-driven development workflow for C#/.NET using xUnit, NSubstitute, and event sourcing (EventSourcing). Covers aggreg...

Test-driven development workflow for Angular/TypeScript using Vitest, @testing-library/angular, Angular TestBed, and Pla...

This skill should be used when the user needs to 'debug web applications', 'test UI interactions', 'capture screenshots...

This skill should be used when the user asks to "test Electron app", "automate Electron desktop app", "debug Electron re...

This skill should be used when validating test coverage against requirements, after implementation tasks complete (Phase...

AI DevKit · Testing phase guidance for adding and validating feature test coverage. Use when the user wants to write tes...

Code quality, correctness, and documentation review for UI lessons — run before dev-final-pass

Post-change verification for C#/.NET backend code — build, Roslyn analyzers, dotnet format, xUnit tests with coverage, N...

Post-change verification for Angular/TypeScript frontend code — build, TypeScript type check, ESLint, unit tests with co...

Post-change verification for the project. Auto-detects backend (.NET) and frontend (Angular/TypeScript) from project fil...

Comprehensive TDD development workflow for FuzzyCat. Enforces test-driven development, post-implementation review, rippl...

devbooks-docs-consistency：检查并维护项目文档与代码的一致性，支持增量扫描、自定义规则与完备性检查。可在变更包内按需运行或全局检查。旧名称 devbooks-docs-sync 保留为别名并输出弃用提示。

devbooks-proposal-challenger：对 proposal.md 发起质疑（Challenger）+ 查漏补缺，指出风险/遗漏/不一致并给结论，发现缺失的验收标准和未覆盖场景。用户说"质疑提案/挑刺/风险评估/提案对辩...

devbooks-proposal-judge：对 proposal 阶段进行裁决（Judge），输出 Approved/Revise/Rejected 并写回 proposal.md 的 Decision Log。用户说"裁决提案/提案评...

devbooks-reviewer：以 Reviewer 角色做可读性/一致性/依赖健康/坏味道审查，只输出审查意见与可执行建议，不讨论业务正确性。用户说"帮我做代码评审/review 可维护性/坏味道/依赖风险/一致性建议"，或在 Dev...

devbooks-test-owner：以 Test Owner 角色把设计/规格转成可执行验收测试与追溯文档（verification.md），强调与实现（Coder）独立对话、先跑出 Red 基线。用户说"写测试/验收测试/追溯矩阵/v...

devbooks-test-reviewer：以 Test Reviewer 角色评审 tests/ 测试质量（覆盖、边界、可读性、可维护性），只输出评审意见，不修改代码。用户说“测试评审/评审测试质量/覆盖率/边界条件”等时使用。

--| | SSR | Server-side rendering, state hydration | [advanced-ssr](references/advanced-ssr.

Implement a story (Ready → InProgress → ready for review). Runs the OSS develop task. Use when: develop story, *develop,...

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: impleme...

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: impleme...

Independent fresh-eyes audit of a development-* step's output for FLOW-quality issues — coverage gaps, altitude leaks, u...

Review a feature's code changes before merge for bugs, security issues, quality and test coverage, ending in an approve...

Tags harness-decomposed curriculum items (KUDs, LTs, criteria) with a school's developmental band metadata while preserv...

Interact with iOS simulators and verify app behavior using xcobra

Challenge slide design with 5-7 pedagogical questions. Checks ordering, prerequisites, and cognitive load.

eval 自评测体系驱动的 AI Agent 生产体系方法论。以评测集为核心资产，建立"评测集组织 + Mock 隔离 + 标准化比对 + 自动评测脚本 + 回归门禁"闭环；L0-L4 分层评测（确定性单测/轨迹评测/输出评测/生产回归/安...

全栈集成测试专家技能。支持多服务 Docker Compose 部署场景，基于 Testcontainers + Mock Server 实现端到端集成测试。

后端 API 测试专家技能。支持 Java（JUnit）/ Python（pytest）/ Node.js（supertest + jest）后端项目的接口测试、Mock 服务、测试数据管理。

测试专家知识库。包含测试最佳实践、故障排查指南、测试策略设计、性能优化建议等专家级知识，供其他测试技能引用。