Agent skills for OpenAI Agents SDK

Walk one test-driven development cycle (RED then GREEN, optionally Refactor while GREEN).

Use this skill when writing new features, fixing bugs, or refactoring code.

Automated E2E testing with Playwright including the auto-fix loop — generate test cases from the UI, run them, fix failures and re-run…

Investigates failing tests and routes the issue to the right developer using dependency and history context.

Add a small deterministic test fixture and a focused test to an existing repository, following its current test conventions and reporting…

Initialize test framework with Playwright or Cypress.

Agent skill for test-long-runner - invoke with $agent-test-long-runner

Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect…

Render, collect, compare, and visually verify representative OpenGraph or social-card image variants as a labeled contact sheet.

Test Planning and Quality Assurance prompt that generates comprehensive test strategies, task breakdowns, and quality validation plans for…

Identify a .NET project's test platform, framework, command mode, and SDK-style vs classic project system.

Invoke this skill when you need rules for writing tests.

Audits existing tests in any language using formal, research-backed test smell names and the testsmells.org 19-smell academic taxonomy.

Run tests against the running Godot instance.

Create test versions to verify app auto-update functionality and version migration.

Provides guidelines for writing test code for Unity projects.

Use when designing unit, integration, or characterization tests.

Use when writing or changing tests, adding mocks, or tempted to add test-only methods to production code - prevents testing mock behavior…

Automatically generates comprehensive test suites (unit, integration, E2E) based on code and past testing patterns.

Testing code that calls an APIMatic-generated .NET SDK in C# — which seam to fake, covering error and edge paths, asserting real behaviour…

How to write integration tests for error processors in packages/core/src/processors/.