• surface hidden assumptions
• identify failure modes early
• validate non-functional constraints
• stress-test designs before implementation
• prevent idea swarm chaos

• One agent designs.
• Other agents review.
• No agent may exceed its mandate.
• Creativity is centralized; critique is distributed.
• Decisions are explicit and logged.

• Owns the design
• Runs the standard

  brainstorming

  skill
• Maintains the Decision Log

• Ask clarification questions
• Propose designs and alternatives
• Revise designs based on feedback

• Self-approve the final design
• Ignore reviewer objections
• Invent requirements post-lock

• Assume the design will fail
• Identify weaknesses and risks

• Question assumptions
• Identify edge cases
• Highlight ambiguity or overconfidence
• Flag YAGNI violations

• Propose new features
• Redesign the system
• Offer alternative architectures

“Assume this design fails in production. Why?”

• Enforce non-functional and real-world constraints

• performance
• scalability
• reliability
• security & privacy
• maintainability
• operational cost

• Reject designs that violate constraints
• Request clarification of limits

• Debate product goals
• Suggest feature changes
• Optimize beyond stated requirements

• Represent the end user

• cognitive load
• usability
• clarity of flows
• error handling from user perspective
• mismatch between intent and experience

• Identify confusing or misleading aspects
• Flag poor defaults or unclear behavior

• Redesign architecture
• Add features
• Override stated user goals

• Resolve conflicts
• Finalize decisions
• Enforce exit criteria

• Accept or reject objections
• Require design revisions
• Declare the design complete

• Invent new ideas
• Add requirements
• Reopen locked decisions without cause

1. Primary Designer runs the standard

   brainstorming

   skill
2. Understanding Lock is completed and confirmed
3. Initial design is produced
4. Decision Log is started

1. Skeptic / Challenger
2. Constraint Guardian
3. User Advocate

• Feedback must be explicit and scoped
• Objections must reference assumptions or decisions
• No new features may be introduced

• Respond to each objection
• Revise the design if required
• Update the Decision Log

• the final design
• the Decision Log
• unresolved objections

• which objections are accepted
• which are rejected (with rationale)

• Decision made
• Alternatives considered
• Objections raised
• Resolution and rationale

• Understanding Lock was completed
• All reviewer agents have been invoked
• All objections are resolved or explicitly rejected
• Decision Log is complete
• Arbiter has declared the design acceptable

• Continue review
• Do NOT proceed to implementation If this skill was invoked by a routing or orchestration layer, you MUST report the final disposition explicitly as one of: APPROVED, REVISE, or REJECT, with a brief rationale.

• Idea swarm chaos
• Hallucinated consensus
• Overconfident single-agent designs
• Hidden assumptions
• Premature implementation
• Endless debate

• One designer, many reviewers
• Creativity is centralized
• Critique is constrained
• Decisions are explicit
• Process must terminate

“If this design fails, did we do everything reasonable to catch it early?”