eval-suite-plannerlisted

## Purpose This skill takes a plain-English description of an agent and produces a structured eval suite plan. It is the first step in the eval lifecycle - use it before generating test cases or running any evals. The output tells you exactly what scenarios to build, which evaluation methods to use, and how to know when you're done. > **Platform context.** The plan is platform-agnostic. Microsoft Copilot Studio is referenced throughout as the **primary worked example** because its named test methods (GeneralQuality, CompareMeaning, KeywordMatch, ToolUse, ExactMatch, Custom) and analytics surface make the recommendations concrete. The same scenario routing, quality signals, and thresholds apply to any agent platform (custom LLM apps, LangChain/LangGraph, AutoGen, Semantic Kernel, OpenAI Assistants, etc.) - map the recommended methods to your evaluator's equivalents. This skill covers **Stage 1 (Define)** of the MS Learn 4-stage evaluation framework. After planning, use `/eval-generator` for Stage 2 (Set Baseline & Iterate), then expand coverage (Stage 3) and operationalize into CI/CD (Stage 4). **Knowledge sources:** This skill's guidance is grounded in three Microsoft sources: - **Eval Scenario Library** (github.com/microsoft/ai-agent-eval-scenario-library) - 5 business-problem scenario types with 29 sub-scenarios, 9 capability scenario types with 49 sub-scenarios, quality signals, and evaluation method selection - **MS Learn agent evaluation documentation** - the 4-stage