What problem does it solve? Prompt and tool changes can silently alter an AI agent's decision-making, and standard unit tests cannot catch these regressions. This Skill provides a structured workflow for writing, fixing, and promoting behavioral evaluations that verify how the agent chooses tools and responds to prompts. ## Core Features & Use Cases - Eval Creation Guidance: Choose between evalTest (subprocess TestRig) and appEvalTest (in-process AppRig), seed realistic workspaces, and write assertions using breakpoints, tool-log audits, and mock MCP servers. - Failure Debugging: Follow a step-by-step investigation process using nightly CI logs, local Vitest runs, and prompt-tuning strategies grounded in snippets.ts. - Test Promotion: Identify stable USUALLY_PASSES tests with 100% pass rates over 7 nightly runs and promote them to ALWAYS_PASSES regression suites. - Use Case: After editing a system prompt, write a behavioral eval that asserts the agent calls read_file within the first five turns, run it locally three times across Gemini models, then promote it once stable. ## Quick Start Ask the agent to create a new behavioral eval that verifies the agent reads a file before editing it in a seeded NodeJS workspace.
