Skill UI

This tool generates production-grade, spec-compliant agent definition files (.md) adhering to the Anthropic 2026 schema. It supports both the creation of new custom subagents and the validation of existing agent files against marketplace compliance rules. Use it when building complex agent architectures, reviewing agent quality, or ensuring agents meet high industry standards.

A comprehensive, multi-chain reference architecture for building robust decentralized applications (dApps) powered by Alchemy. This guide outlines the full stack, from the React/Next.js frontend and API layer to core blockchain interactions, incorporating best practices like rate limiting, caching, and secure API proxying. Ideal for planning complex, production-grade Web3 systems across multiple chains (ETH, Polygon, etc.).

This comprehensive guide provides a production-ready reference architecture for implementing scalable search using Algolia. It details best practices for index design (including multi-index strategies), establishing robust data pipelines from source databases, structuring the service layer (search, indexing, settings), and integrating the frontend for optimal performance.

This resource provides production-ready architectural patterns for integrating Anthropic's Claude models using TypeScript and Python. It covers robust client wrappers, managing multi-turn conversations, enforcing structured JSON output via prefilling, and implementing multi-tenant architectures. Essential for building reliable, enterprise-grade AI applications.

A robust reference architecture designed for integrating multi-property portfolios with the AppFolio Stack API. It manages complex tasks such as real-time vacancy tracking, tenant lifecycle management, work order routing, and financial accounting reconciliation (e.g., QuickBooks/Xero). Key components include a service layer, multi-level caching strategies for optimal data freshness, and an event-driven pipeline (using webhooks and message queues) to ensure data consistency and idempotency across all transactions, addressing potential rate limits and failure modes.

A comprehensive guide detailing the architecture and strategy for migrating a design system from legacy platforms (like Figma or Adobe) to the Canva Connect API. It employs the Strangler Fig Pattern to ensure a safe, gradual transition, covering asset mapping, adapter layer implementation, and feature flag traffic splitting across multiple phases.

A persistent memory kit designed for Claude AI agents. It maintains deep context across multiple sessions and projects using a two-layer architecture (hot cache and knowledge wiki). Features include safety hooks, multi-project context isolation, and a /close-day command for daily synthesis, ensuring agents remember complex information and continuously learn.

Provides a comprehensive, production-ready reference architecture for building advanced analytics platforms powered by ClickHouse. It details everything from project layout (TypeScript/Node.js structure) and data ingestion pipelines (Kafka, Webhooks) to the optimal 3-layer schema design (Raw, Hourly, Daily) and multi-tenancy patterns, ensuring scalable and efficient OLAP query performance.

Provides a production-ready, layered architectural guide for integrating with the ClickUp API v2. This comprehensive reference covers implementing core features such as custom fields, detailed time tracking, goal setting (OKRs), and robust two-way synchronization with external systems. It is essential reading for developers building sophisticated, enterprise-grade ClickUp solutions.

This detailed guide outlines a production-ready, layered architecture for building complex AI applications using the Cohere API v2. It covers implementing Retrieval-Augmented Generation (RAG) pipelines, advanced tool-use agents, and multi-model orchestration. Use this structure when designing new Cohere integrations or establishing robust architectural standards for enterprise AI solutions.

This reference architecture provides a comprehensive blueprint for deploying Machine Learning models on CoreWeave's GPU cloud infrastructure. It details the structure for multi-model serving (e.g., vLLM, TGI), scalable Kubernetes deployments, shared persistent storage (PVC), and autoscaling mechanisms using KServe/Knative. Use this when designing robust MLOps pipelines, planning high-performance multi-model inference services, or establishing standardized best practices for GPU cloud deployment.

This skill acts as a rigorous, Socratic interviewer designed to stress-test a proposed plan against an established domain model and existing project documentation. It forces the user to sharpen terminology, resolve cross-cutting dependencies, and identify inconsistencies between stated requirements, code implementations, and documented decisions. It ensures the resulting architecture is precise, consistent, and well-documented by automatically updating the context and generating Architecture Decision Records (ADRs).