Best skills for QA / test engineer

Testing

Provides a structured debugging workflow (reproduce, isolate, identify root cause, fix minimally, verify) and testing guidance (TDD, test priority, verification commands). Helps developers systematically fix bugs and ensure code quality before marking tasks as done.

Testing

Create or modify evaluation configurations for MCP Servers. This skill guides the creation of eval YAML files, task definitions, MCP config, and agent files, and provides commands to run the evaluations using mcpchecker. Particularly useful when testing MCP server functionality through automated task assertions.

Testing

Check whether an artifact (code, config, state) conforms to tests, specs, or invariants. Produces a PASS/FAIL verdict with observable evidence. Helps validate changes or test hypotheses.

Testing

Provides step-by-step guidance for writing Go tests with the gt library, including type-specific assertions (e.g., `gt.Array`, `gt.String`), fail-fast patterns with `Required()`, and return value handling via `R1`/`R2`/`R3`. Helps when creating new test files or adding tests to existing Go code by referencing the locally installed gt documentation.

Testing

Covers testing strategies for Tauri v2 applications: unit and integration testing using a mock runtime, end-to-end testing with WebDriver (Selenium, WebdriverIO), and CI integration with GitHub Actions.

Testing

Generates synthetic data for the Forward Impact suite from a universe DSL file. Produces framework definitions, organizational documents, activity records, and personal knowledge base content. Use for testing, generating example datasets, or creating synthetic pathways for new installations.

Testing

Verifies test quality, coverage, and correctness by ensuring BDD scenarios map 1:1 to tests and that testing rules (≥80% coverage, error handling) are followed. Used during the review phase to confirm the implementation meets acceptance criteria through automated test validation.

Testing

Write tests for REST and GraphQL APIs using Playwright's built-in API testing features. Helps validate responses, mock endpoints, and integrate API tests into end-to-end flows.

Testing

Launch a sub-agent that performs end-to-end verification of the application. It checks builds, linting, type errors, runs unit tests, performs manual UI testing via Playwright, and verifies integration points. Ideal for QA verification before release or after changes to ensure app stability and correctness.

Testing

This skill echoes a message back with a timestamp. Helpful for testing skill functionality and learning how skills work. Use it when you need to verify that skills are operating correctly.

Testing

Runs pytest with optional arguments, lists test files, executes specific test files, and generates coverage reports. Useful for continuous integration and ensuring code quality during development.

Testing

Enforces the TDD cycle: write a failing test (red), implement minimal code to pass (green), then refactor while keeping tests green. Best for any testable code change, especially in projects using Vitest.

Testing

Reviews code for quality, security, and maintainability issues. Use after implementing features or completing significant work, or when the user asks for code review. Provides structured feedback organized by priority (critical, warning, suggestion).

Testing

Validates code compliance with 7 key principles (TDD, fail fast, modular, reuse, open source, no debt, excellence). Detects violations and suggests improvements during code review or refactoring.