Skill UI

This skill outlines security best practices for the TwinMind AI meeting assistant. It covers crucial aspects like on-device audio processing, encrypted cloud backups, and managing microphone permissions. Use it when setting up new TwinMind instances or managing AI operations to ensure data privacy, compliance, and robust security for sensitive meeting data.

An expert guide for deploying and optimizing Large Language Models (LLMs) entirely on local hardware. Mastering the entire local AI ecosystem, including inference engines like Ollama, vLLM, and llama.cpp. Provides deep knowledge on quantization formats (GGUF, EXL2, AWQ), VRAM calculation, and ensuring privacy-first, offline deployment for state-of-the-art models.

Conducts comprehensive AI prompt safety reviews that analyze bias, misinformation, injection, and privacy risks while delivering effectiveness evaluations, security guidance, and best-practice recommendations for prompt engineers.

Open Notebook is a self-hosted, open-source alternative to major AI research tools. It allows users to ingest diverse content—including PDFs, videos, and web pages—and organize them into private notebooks. Key features include context-aware AI chat, automated summarization, multi-speaker podcast generation, and full programmatic access via a comprehensive REST API. By running on your own infrastructure, it ensures complete data privacy and supports 16+ AI providers.

A comprehensive guide for building applications with Claude, ensuring responsible data handling. This skill covers critical patterns such as PII redaction (stripping sensitive data like emails, phone numbers, and card numbers), optimizing the 200K token context window through conversation trimming, and implementing best practices for data retention and privacy compliance when interacting with the Anthropic API.

This skill provides robust mechanisms to ensure data privacy when interacting with Cohere APIs (Chat, Embed, etc.). It implements advanced PII detection (emails, SSNs, IP addresses, etc.), performs pre-call redaction to mask sensitive information, and includes post-call scrubbing and detailed audit logging. Essential for achieving GDPR/CCPA compliance and safely handling sensitive user data.

This skill provides real-time monocular depth estimation using advanced models like Depth Anything v2. It transforms live camera feeds by generating colorized depth maps, enabling depth overlays and detailed scene understanding. Crucially, it supports a 'privacy mode' that anonymizes visual identities by using depth-only transformation, preserving only the spatial layout and movement patterns for secure monitoring purposes. Optimized for both CoreML on macOS and PyTorch on other platforms.

A comprehensive tool designed to scan any agent skill for potential security risks and vulnerabilities before implementation or use. Powered by local static analysis (A.I.G.), it ensures that no file contents, credentials, or personal data ever leave your device, providing maximum privacy and safety for integrating new AI capabilities across various agent platforms.

This tool reads your local GitHub Copilot CLI conversation history using the specialized `vardoger` CLI. It analyzes your behavioral patterns, coding conventions, and usage style to generate a personalized instructions block. This block is written directly to your local Copilot configuration file, allowing the assistant to adapt its guidance and suggestions specifically to your unique habits and preferences. The process runs entirely offline, ensuring maximum privacy.

A comprehensive guide detailing advanced security threats in Machine Learning and AI systems. Covers model supply chain attacks (RCE via pickle, poisoning), adversarial examples (FGSM, PGD, physical-world), data privacy breaches, and LLM-specific vulnerabilities. Essential for building robust, secure AI pipelines.

Conducts a comprehensive, structured ethical review for any AI or ML model, feature, or product. It assesses risks related to fairness, bias, transparency, privacy, and societal impact, providing a risk tier score, necessary mitigations, and governance documentation suitable for pre-deployment compliance.

This skill provides methods and frameworks to detect sophisticated AI attacks, including model stealing, membership inference, and model inversion. It focuses on monitoring query patterns, analyzing confidence exposure, and implementing defensive controls on inference APIs to protect intellectual property and data privacy.