test▌

Comprehensive test case generation from PRD documents and user requirements with full coverage mapping. \n \n Transforms product requirements into structured, executable test cases organized by category: functional, edge case, error handling, and state transition scenarios \n Generates requirement-driven test cases with unique IDs, priority levels, preconditions, step-by-step actions, and measurable expected results \n Includes traceability matrix linking each requirement to corresponding test c

Multi-agent pipeline that generates compilable, passing unit tests across eight programming languages. \n \n Orchestrates a Research → Plan → Implement workflow: researcher analyzes the codebase, planner creates phased test strategy, implementer writes and validates tests across phases \n Supports C#, TypeScript, JavaScript, Python, Go, Rust, Java, and more; auto-detects language, testing framework, build commands, and project structure \n Includes builder, tester, fixer, and linter subagents th

Generate Playwright tests from scenarios using interactive browser exploration and validation. \n \n Guides you through step-by-step test creation: scenario review, browser exploration, element inspection, interaction validation, and final test generation \n Integrates with Playwright MCP tools to inspect page elements, capture selectors, and validate interactions before writing test code \n Generates TypeScript tests using @playwright/test framework and automatically saves them to the tests dir

Generates and writes new unit tests for any programming language using a Research-Plan-Implement pipeline. Use when asked to generate tests, write unit tests, add tests, improve test coverage, create test project, achieve high coverage, comprehensive tests, or asked to scaffold a new test project for an app, service, or library. Supports C#, TypeScript, JavaScript, Python, Go, Rust, Java, and more. Orchestrates the code-testing-generator sub-agent through research, planning, and implementation phases so tests compile, pass, and follow project conventions. DO NOT USE FOR: running existing tests or test filters (use run-tests); diagnosing coverage plateaus or project-wide coverage/CRAP analysis without writing tests (use coverage-analysis); targeted method/class CRAP scores (use crap-score); MSTest assertion guidance, MSTest test pattern modernization, or fixing existing MSTest test code (use writing-mstest-tests).

Comprehensive testing specialist for functional, performance, and security test design and execution. \n \n Covers unit, integration, E2E, performance (k6, Artillery), and security testing (OWASP) with structured workflows from scope definition through reporting \n Enforces test quality standards: meaningful assertions, isolated dependencies, edge-case coverage, and flaky-test remediation \n Provides reference guides for TDD methodology, testing anti-patterns, automation frameworks, and QA pract

Systematically identify and fix all failing tests using smart error grouping. \n \n Groups failures by error type, affected module, and root cause, then prioritizes fixes by impact and dependency order \n Fixes infrastructure issues first (imports, dependencies, configuration), followed by API changes, then logic bugs \n Runs focused test subsets after each fix using pytest markers and file patterns to verify progress before moving to the next group \n Follows a structured workflow: initial test

Runs .NET tests with dotnet test. Use when user says "run tests", "run my tests", "run these tests", "execute tests", "dotnet test", "test filter", "filter by category", "filter by class", "combine filters", "run only specific tests", "integration tests", "unit tests", "tests not running", "hang timeout", "blame-hang", "blame-crash", "crash dump", "TRX report", "TRX", "test report", "generate TRX", "TUnit", "treenode-filter", "target framework", "multi-TFM", or needs to detect the test platform (VSTest or Microsoft.Testing.Platform), identify the test framework, apply test filters, or troubleshoot test execution failures. Covers MSTest, xUnit, NUnit, and TUnit across both VSTest and MTP platforms. Also use for --filter-class, --filter-trait, --report-trx, --logger trx, --blame-hang-timeout, and other platform-specific filter and reporting syntax. DO NOT USE FOR: writing or generating test code, CI/CD pipeline configuration, or debugging failing test logic.

Write failing tests first, then minimal code to pass, then refactor while keeping tests green. \n \n Follows the red-green-refactor cycle: write one failing test, verify it fails correctly, implement minimal code to pass, verify all tests pass, then refactor safely \n Requires watching each test fail before writing implementation code; tests that pass immediately prove nothing about correctness \n Applies to all new features, bug fixes, refactoring, and behavior changes; code written before test

GPUI provides a comprehensive testing framework that allows you to test UI components, async operations, and distributed systems. Tests run on a single-threaded executor that provides deterministic execution and the ability to test complex async scenarios. GPUI tests use the #[gpui::test] attribute and work with TestAppContext for basic testing and VisualTestContext for window-dependent tests.

You can start and use Codex TUI to verify changes. \n Important notes: \n Start interactively.\nAlways set RUST_LOG=\"trace\" when starting the process.\nPass -c log_dir=<some_temp_dir> argument to have logs written to a specific directory to help with debugging.\nWhen sending a test message programmatically, send text first, then send Enter in a separate write (do not send text + Enter in one burst).\nUse just codex target to run - just codex -c ...