Multi-Persona Critique: Parallel Philosophical Review of Proposals

Overview

This skill takes a set of proposals — feature ideas, architectural decisions, design choices, strategy options — and sends ALL of them to 5 distinct intellectual personas for parallel, independent critique. Each persona brings a different philosophical lens. The skill then synthesizes all critiques into a consensus report showing where personas agree, where they disagree, and what the disagreements reveal.

This is NOT the roast skill. Key differences:

• roast critiques CODE with HackerNews personas and validates file:line claims
• This skill critiques IDEAS/PROPOSALS with philosophical/methodological personas and evaluates logical coherence, practical viability, and human impact
• roast is evidence-based (checking actual code); this is argument-based (evaluating reasoning)

Key constraints baked into the workflow:

• Every persona sees ALL proposals — no cherry-picking
• Personas run in parallel with no awareness of each other — independence is the source of value
• Ratings are mandatory: STRONG / PROMISING / WEAK / REJECT for every proposal from every persona
• Rankings are mandatory: each persona orders proposals from strongest to weakest
• Fairness mandate: genuine strengths must be acknowledged, genuine weaknesses explained with precision
• Disagreements are preserved, not averaged away — the disagreements ARE the insight
• The synthesis phase adds cross-cutting analysis, it does not edit persona outputs