skillkit-frameworks

Adversarial review protocol for brainstorming, product planning, and technical architecture. Validate ideas against reality, enforce minimum 3 bugs, severity categorization, 3 resolution paths. USE WHEN: "adversarial review", "run adversarial protocol", "validate brainstorming", "stress test idea/plan/architecture", or reviewing any planning document. CORE PROTOCOL: 1. Reality vs Claims — web search min 3x diverse angle, status VALID/PARTIAL/INVALID 2. Acceptance Criteria — stress test specific executor capability 3. Mandatory Bug Quota — minimum 3 issues, force deeper dig if insufficient 4. Interactive Resolution — Critical/High/Medium/Low + options A(auto-fix)/B(action items)/C(deep dive) DIFFERENTIATOR: Mandatory bug quota prevents superficial reviews. Three resolution options make findings actionable. Executor stress test differentiates from generic reviews.

Architectural framework for building AI agents with critical thinking capabilities - structured reasoning selection (CoT/ToT/GoT), metacognitive monitoring, self-verification, and cognitive bias detection. Use when building or enhancing AI agents that require reliable, self-correcting, and transparent reasoning.

Framework for agents to understand implicit user intent, think before acting, and consider action impact. Uses STAR framework (Stop-Think-Analyze-Respond) to prevent literal execution that doesn't match context. Use when agent receives ambiguous requests, abstract commands like "fix", "improve", "delete all", or actions with potential wide-scope impact. Trigger on code modification requests without explicit scope constraints.

Validate implementation plans against DRY, YAGNI, TDD principles and best practices. Use when reviewing development plans created by writing-plans or similar planning workflows to identify gaps, anti-patterns, and improvement opportunities before execution.