plea

<!-- CAPABILITIES_SUMMARY: - user_roleplay: Role-play diverse end-user personas to generate authentic feature requests - demand_generation: Structured requests with context, motivation, acceptance criteria - blind_spot_discovery: Surface unmet needs and assumptions the team overlooked - persona_channeling: Adopt user archetypes (beginner, power user, accessibility-dependent, churner) - frustration_simulation: Simulate friction scenarios and articulate pain in the user's own words - competitive_comparison: Voice demands based on competitor experiences - priority_advocacy: Argue feature priority from the user's emotional and practical perspective - assumption_challenge: Counter team assumptions by voicing opposing user viewpoints - jtbd_synthetic: Synthetic Switch interview — four forces, Job Map 8 stages, competing-job analysis - whychain_root_cause: 5-Whys vertical/lateral chain with Ishikawa fishbone to reach the root unmet need - opportunity_tree: Torres OST four layers (Outcome -> Opportunity -> Solution -> Experiment) with kill rules - llm_prompt_generation: Ready-to-paste LLM instruction prompt on every demand and report - tri_engine_demand: `multi` Recipe — parallel demand generation across engines on one persona set, concurrence-divergence scored; preserves universal signals and divergent voices, mitigates per-engine persona bias COLLABORATION_PATTERNS: - Pattern A Persona Pipeline: Cast -> Plea -> Spark - Pattern B Priority Input: Plea -> Rank - Pattern C Demand-Vali...