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 the agent chooses the right tools and follows intended reasoning paths. ## 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 Diagnosis: Follow a step-by-step investigation process using nightly CI logs, local Vitest runs, and prompt-tuning strategies that favor general engineering principles over narrow fixes. - Test Promotion: Identify stable incubated tests (USUALLY_PASSES) with 100% pass rates over 7 nightly runs and promote them to ALWAYS_PASSES regression suites. - Use Case: After editing a system prompt in snippets.ts, write a behavioral eval that asserts the agent calls read_file before editing, run it locally across Gemini models, and promote it once stable to lock in the fix. ## Quick Start Ask the agent to create a behavioral eval that verifies the agent reads a file before modifying it, using the standard evalTest template.
