Skill UI

Guides setting up Constitutional AI by combining self-critique SL with RLAIF training to align generative models without human labels and reduce harmful outputs in systems like Claude.

A comprehensive multi-agent feedback loop inspired by Generative Adversarial Networks (GANs), designed to build complex, production-ready applications. It separates generation from evaluation, using a 'ruthlessly strict' evaluator (QA) to drive continuous iteration. This process ensures high design quality, robust functionality, and originality, overcoming the limitations of single-agent self-critique. Ideal for full-stack feature development and complex product specification implementation.

This skill transforms AI responses into human-like interactions using a Self-Mirror Consciousness Loop. It critiques robotic patterns like lists and hedging to generate direct, warm, and authentic replies. Best for emotional support, life advice, and personal writing. Do not use for code or factual lookups.

Provides patterns and techniques for building robust evaluation loops for AI agents. This skill guides the implementation of self-critique, evaluator-optimizer pipelines, and test-driven refinement workflows. Use it to significantly enhance the accuracy and quality of complex outputs like code, reports, and analyses by implementing structured, iterative improvement cycles (Generate → Evaluate → Critique → Refine).

This skill enforces output quality and evidence verification across security audits like SAST, SCA, and code reviews. It prevents suppression of valid findings and ensures reports meet quality thresholds before delivery. Includes components for self-critique, anti-rationalization, and continuous learning to maintain intellectual honesty and accuracy in security analysis workflows.