Simulate a structured peer-review process using multiple specialized agents to validate designs, surface hidden assumptions, and identify failure modes before implementation.
Transform a single-agent design into a robust, review-validated design by simulating a formal peer-review process using multiple constrained agents.
This skill exists to:
This is not parallel brainstorming. It is sequential design review with enforced roles.
The process is gated and terminates by design.
Each agent operates under a hard scope limit.
Role:
brainstorming skillMay:
May NOT:
Role:
May:
May NOT:
Prompting guidance:
“Assume this design fails in production. Why?”
Role:
Focus areas:
May:
May NOT:
Role:
Focus areas:
May:
May NOT:
Role:
May:
May NOT:
brainstorming skillNo other agents participate yet.
Agents are invoked one at a time, in the following order:
For each reviewer:
Primary Designer must:
The Integrator / Arbiter reviews:
The Arbiter must explicitly decide:
The Decision Log must record:
No design is considered valid without a completed log.
You may exit multi-agent brainstorming only when all are true:
If any criterion is unmet:
This skill exists to answer one question with confidence:
“If this design fails, did we do everything reasonable to catch it early?”
If the answer is unclear, do not exit this skill.
This skill is applicable to execute the workflow or actions described in the overview.