Skill UI

This guide details integrating FoundationModels for running Large Language Models (LLMs) directly on the device (iOS 26). It covers advanced patterns including text generation, extracting structured data using @Generable, implementing custom tool calling for domain logic, and streaming responses for real-time UI updates. Key features emphasize strong privacy and offline capability, ensuring no data leaves the device.

This comprehensive skill guides the user through the entire process of creating a deep, multi-layered AI persona (Soul.md). It helps define the identity, core rules, name, and visual prompts for agents designed for the OpenClaw platform. Users can initiate character creation via guided prompts or a random 'gacha' draw, ensuring a cohesive and compelling character profile.

This guide helps researchers determine the most appropriate top-tier academic conference (e.g., CoNEXT, SIGCOMM, NSDI, IMC) and submission cycle for their networking research. It provides detailed criteria, routing tables, and tests (e.g., platform-realism test, model-swap test) to ensure the contribution is evaluated on a real target and fits the target community's scope and rigor.

This comprehensive checklist guides authors through the final pre-submission review for the Journal of Policy Analysis and Management (JPAM). It ensures the manuscript is properly anonymized (double-blind), confirms adherence to membership/fee requirements, and verifies all necessary metadata, data availability statements, and formatting standards before upload to the Wiley Research Exchange platform.

This comprehensive skill guides authors on whether their enabling technology, platform, or method is suitable for Nature Biotechnology. It analyses the journal's specific focus on translational potential, broad applied impact, and industrial relevance. It covers best practices for advanced topics including genome editing, synthetic biology, biomanufacturing, and AI applications, emphasizing the requirement for robust in vivo proof and comprehensive benchmarking.