agent-integration-testinglisted

# Agent Integration Testing ## Overview This skill guides the creation and autonomous execution of verifiable integration test specifications. It ensures that tests are actionable by agents, properly documented, and systematically executed by subagents to validate features or fix failures. ## Core Process 1. **Investigate Codebase Area** - By default, investigate the entire codebase to understand the context. - If the user specifies a feature area, use `glob` and `grep` to narrow the investigation. 2. **Write Test Specification** - Create a test spec file at `./tests/<name>.md`. - Use `<name> = "integration"` unless the user specifies a particular feature area. - The document MUST include a **Prerequisites** section at the top detailing any setup needed before tests become runnable (e.g., environment variables, database seeding, background services). 3. **Define Verifiable Tests** - Each test must be written in plain English. - Include clear **steps to reproduce**. - Include a set of **expectations**. - **CRITICAL:** Every expectation must be strictly verifiable by an agent using available tools (e.g., shell commands, HTTP requests, reading file outputs). If a test cannot be verified by an agent, it is invalid and must be rewritten or removed. 4. **Execute Tests via Subagents** - Spawn subagents (using the `Task` tool or `@mention` subagent system) to run each individual test. - The subagent must follow the prerequisites, execute the ste