Skill UI

Core principles for designing user interfaces on Apple platforms. Covers accessibility, system colors, typography, motion, and privacy. Ensures consistency with Apple's design language across iOS, macOS, and visionOS.

This comprehensive guide outlines Apple's Human Interface Guidelines (HIG) for various technologies and user flows (e.g., Siri, Apple Pay, HealthKit, ARKit, Generative AI). It teaches developers how to ensure their applications feel natively integrated, respect user privacy, and adhere to established platform patterns across iOS, macOS, and other Apple devices. Essential reading for building high-quality, compliant, and seamless user experiences.

Plan and synthesize multi-perspective research using bounded parallel agents when delegation is authorized. Define questions, sources and deliverables, record evidence and uncertainties per perspective, then deduplicate and resolve conflicts against primary sources. Includes scope, privacy and verification limits.

Drafts privacy policies, terms of service, cookie policies, DPAs, and disclaimers with jurisdiction-aware compliance notes for GDPR, CCPA, LGPD and other regulations, plus review checklists.

Architecture and integration sketches for LLM applications, covering RAG retrieval, tool dispatch, agent loops, caching, privacy boundaries and verification requirements before production use.

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.

Deploy a local LLM stack with Ollama, Open WebUI, and LiteLLM for offline, privacy-first AI workloads. Covers installation, model selection, Docker Compose setup, API usage, and custom Modelfiles for development environments.

A comprehensive guide to integrating privacy protections into software architecture from the ground up. This skill ensures compliance with major global regulations like GDPR, CCPA, and LGPD by implementing core principles such as data minimization, purpose limitation, and default privacy settings. Essential for developers building any application that handles personal user data.

Privacy Mask is a CLI utility for detecting and redacting sensitive PII in screenshots and images locally. It supports various detection engines including regex and NER to identify IDs, financial data, and API keys. All processing is offline to ensure data security. Users can run dry-runs before masking. Ideal for debugging and sharing images without exposing private credentials or secrets.

This skill manages and stores approved team context securely using RuVector isolation. It ensures tenant-local data privacy by excluding sensitive credentials and personal information. During retrieval, it preserves provenance and treats data as untrusted. It prevents memory transfer between teams, maintaining strict security boundaries for AI team operations.

Tree Ring Memory is a local-first framework for managing AI agent memory lifecycles. It enables recall, evidence recording, auditing, and forgetting without dumping transcripts. Built with Rust and SQLite, it supports scoped memory, privacy, and durable project knowledge consolidation. Ideal for developers managing AI agent projects securely.

This skill helps plan and review read-only data warehouse analysis with explicit scope, privacy, and validation checks. It turns business questions into reproducible analysis plans without assuming specific schemas. It identifies needed data, reviews proposed queries for risks like grain or privacy, and ensures results are communicated accurately. Suitable for authorized data warehouse usage, query review, and analysis documentation while avoiding administrative tasks.