Skill UI

Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models, reducing token usage while increasing compliance. Ideal for optimizing LLM system prompts and migrating rules between AI tools.

A comprehensive, multi-phased workflow bundle designed for building production-grade AI and Machine Learning applications. It guides users through key stages, including AI application design, RAG implementation, autonomous agent development, robust ML pipelines, AI observability setup, and security hardening.

Orchestrate AI/ML workflows including data ingestion, model training, batch inference, and RAG indexing using tools like Prefect, Airflow, or Dagster. Essential for managing complex AI systems and automating ML pipelines.

This skill guides the development of AI-powered products, focusing on LLM integration, RAG architecture, scalable prompt engineering, trustworthy AI UX, and cost optimization. It ensures products are production-ready rather than failing demos.

This skill enables structured AI red team exercises to test for jailbreak resistance, data exfiltration risks, and harmful output controls. It helps discover exploitable failure modes before attackers do, suitable for new LLM features, third-party model evaluation, and security audits. Includes Python scripts for automated testing against various attack vectors like prompt injection and tool abuse.

Secure LLM and AI systems against prompt injection, data exfiltration, model theft, and supply chain attacks in production environments. This skill covers input sanitization, output filtering, PII scrubbing, and API endpoint protection to ensure compliance with SOC2 or ISO 27001 standards.

A specialized skill for generating hyper-realistic, humanized images using Google AI Studio (Gemini). It simulates the imperfections of real photography—such as natural lighting, slight camera shake, and depth of field—to create content that looks genuinely captured by a smartphone. Ideal for creating high-quality assets for social media (influencer style) or educational materials.

Expert guidance for building successful AI wrapper products that solve specific problems and generate revenue. Covers product strategy, prompt engineering, cost optimization, model selection, AI UX, and usage metering. Ideal for developers and entrepreneurs creating AI-powered SaaS tools.

Enables agents to perform authorized security assessments, blue team exercises, and penetration testing on AI products, agents, and infrastructure. Uses first-principles reasoning to identify vulnerabilities like prompt injection and tool abuse, generating evidence-based security reports without relying solely on payload libraries.

AKF is the native metadata format specifically designed for tracking AI-generated or AI-modified content. It allows users to stamp files (including DOCX, PDF, images, and code) with detailed trust scores, source provenance, and compliance metadata. This tool is essential for professional workflows requiring strict auditing, compliance assurance, and verifiable data lineage, especially concerning regulations like the EU AI Act, HIPAA, and SOX.

This skill enables AI agents to detect and resist user pressure, manufactured urgency, and authority appeals before responding. It separates evidence from persuasion, states uncertainty, and ensures honest behavior by invoking an integrity scaffold tool. It prevents sycophantic collapse and confidently-wrong answers, enhancing decision integrity.

This skill is designed to prevent AI coding assistants from exhibiting sycophantic agreement bias. When active, it forces a structured, critical assessment of user claims. The process involves extracting the core claim, assessing it independently with evidence (for/against), and concluding solely based on that assessment, ensuring objective and evidence-based responses.