Agent Design Review Skill

Most agents don't fail because the model is weak — they fail because the design lets them loop, call the wrong tool, lose the thread across steps, or burn tokens with no stopping rule. This skill reviews an agent's architecture against the decisions that actually determine reliability, and ranks the fixes — so "it works in the demo but not in prod" becomes a specific list of changes. (Writing a new agent spec? Use agent-spec.)

Working from a brief

Given a sketch ("a research agent that searches, reads, and writes a report"), deliver the full review anyway — infer the likely control flow and tools, label the inference, and flag what to confirm. Never withhold the review for missing detail.

Required Inputs

Ask for these only if they aren't already provided (else infer and label):