evaluate
MANDATORY PREPARATION
Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first. Consult the feedback-loops reference in the agent-workflow skill for evaluation patterns, golden test sets, and regression detection.
Evaluate the workflow's actual interaction quality by testing it against scenarios that represent real usage.
Evaluation Dimensions
1. Task Completion
- Does the workflow actually accomplish what it's supposed to?
- Does it handle the complete task or only the happy path?
- Are edge cases addressed or silently dropped?
2. Output Quality
More from sharpdeveye/maestro
agent-workflow
Use when any Maestro command is invoked — provides foundational workflow design principles across prompt engineering, context management, tool orchestration, agent architecture, feedback loops, knowledge systems, and guardrails.
149diagnose
Use when the user wants to find problems, audit workflow quality, or get a comprehensive health check on their AI workflow.
147calibrate
Use when workflow components are inconsistent, naming conventions vary, or a new team member's work needs alignment to project standards.
142teach-maestro
Use when starting a new project with Maestro or when no .maestro.md context file exists yet. Run once per project.
140iterate
Use when the workflow needs to self-correct, improve over time, or establish feedback loops and evaluation cycles.
140fortify
Use when the workflow lacks error handling, has been failing in production, or needs retry logic, fallback strategies, and circuit breakers.
140