Testing

Take a screenshot of a page in a locally running app with a red ring and a short label round one element, so a developer can see exactly which button, link or…

Implement a Jira ticket end to end - Haiku scouts and TDD implementers, Sonnet investigators, Opus plans and reviews.

Use this skill when you need to design performance testing for load, stress, spike, endurance, or capacity objectives; triggers include 性能测试 and performance…

Use this skill when you need to design performance testing for load, stress, spike, endurance, or capacity objectives; triggers include performance testing…

Find and remove change-amplifying tests, docs and structure — anything that must be edited whenever something else changes (mock-echo tests, broad snapshots…

Use this skill when requirement wording has unclear actors, references, scope, quantities, conditions, timing, states, or acceptance criteria; triggers…

Use this skill when requirement wording has unclear actors, references, scope, quantities, conditions, timing, states, or acceptance criteria; triggers…

Use this skill when multiple requirement artifacts may disagree on terminology, identifiers, formats, states, rules, or behavior; triggers include requirement…

Use this skill when multiple requirement artifacts may disagree on terminology, identifiers, formats, states, rules, or behavior; triggers include 需求一致性分析…

Use this skill when requirements, acceptance criteria, design, code, tests, defects, or evidence must be mapped bidirectionally and coverage gaps made…

Use this skill when requirements, acceptance criteria, design, code, tests, defects, or evidence must be mapped bidirectionally and coverage gaps made…

Implements a single issue end-to-end: reads it, explores the code, installs dependencies when missing, builds with TDD, verifies the project's checks, commits…

仅在用户明确要求验证长任务失败或失败通知推送时使用（如 测试失败通知 / 失败测试 / 验证长任务失败）。客户周报、报告导出、报告下载等业务请求一律不用本技能。本技能必然执行失败。

Use this skill when you need to test AI agent tool-call contracts, authorization, failures, and side-effect boundaries; triggers include Agent 工具调用测试 and…

Use this skill when you need to test AI agent tool-call contracts, authorization, failures, and side-effect boundaries; triggers include agent tool testing.

Unified database intelligence for PostgreSQL, MySQL, SQLite, and MongoDB in one skill: detect the engine, connect credential-safe, extract schema, build an…

Use this skill when multiple role reports for one quality stage must be combined into a traceable synthesis; triggers include multi-role quality synthesis…

Use this skill when you need to compare performance evidence across versions and assess regression risk; triggers include performance regression analysis.

Use this skill when you need to compare performance evidence across versions and assess regression risk; triggers include 性能回归分析 and performance regression…

Use this skill when you need to design safe prompt-injection tests for AI systems and tool boundaries; triggers include prompt injection testing.

Use this skill when you need to design safe prompt-injection tests for AI systems and tool boundaries; triggers include Prompt Injection 测试 and prompt…

Use this skill when you need to select an executable regression test set from known test assets; triggers include regression test selection.

Use this skill when you need to select an executable regression test set from known test assets; triggers include 回归测试选择 and regression test selection.

Systematic debugging with reproduction, isolation, and hypothesis testing.