“testing”

Test AI-powered features including LLM prompts, tool calls, nondeterministic outputs, evaluation frameworks, and hallucination risk assessment.

Execute test suites, collect evidence, and produce structured quality reports

Test autotel instrumentation with createTraceCollector() and InMemorySpanExporter.

Use this skill when you need evidence-bounded failover-testing analysis and validation preparation; triggers include 故障切换测试 and failover-testing.

Use this skill when you need evidence-bounded recovery-testing analysis and validation preparation; triggers include 恢复测试 and recovery-testing.

Use before opening or updating an OpenMetadata PR that changes Java, a JSON schema, an index mapping, a SQL migration, seed data or a pom — PR CI no longer…

Generate tests for Convex functions with convex-test (queries/mutations/auth/scheduling, in-memory).

Use this skill when you need to plan manual or exploratory testing with charters, heuristics, and session records; triggers include 手动测试 and exploratory…

Use this skill when you need to design mobile test plans for iOS or Android covering functionality, compatibility, performance, network, and security…

This skill should be used when the user asks to "test for insecure direct object references," "find IDOR vulnerabilities," "exploit broken access control,"…

Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations.

Go testing patterns.

Generate robust, zero-flakiness Playwright E2E tests following OpenMetadata patterns.

Run the bounded test-step retry loop against a slug's declared test mechanisms via bin/verify.

Go testing patterns including table-driven tests, subtests, benchmarks, fuzzing, and test coverage.

Exploratory testing sessions when requirements are vague or docs are missing — charter-driven; outputs system understanding, risks, test ideas.

Use when the user directly requests efficiency-aware multi-angle unit tests or a test report after code changes.

Choose proportionate verification and maintain useful tests when implementing changes, fixing bugs, or reviewing test coverage.

Spawn Test Butcher on the scoped test files, trim tests that are not worth keeping, then write the real tests it flags as missing.

Wendy Cloud testing skill — supplies test commands, stack setup, and failure-mode knowledge for the cloud monorepo.

AI-powered E2E web testing — eyes and hands for AI coding tools.

Tests Amazon MWAA workflow execution end-to-end: trigger a run and monitor it to completion for Provisioned (Python DAG, via Airflow REST API) and Serverless…

Write, fix, and run unit tests for Flutter and Dart code — services, repositories, models, use cases, Retrofit/Dio API clients, freezed and json_serializable…

Testing critical user/system flows through the real entry points.