Skill UI

Automates onnx converter work for ML deployment, providing best-practice guidance on serving, pipelines, monitoring, and optimization while generating production-ready code and configs.

This comprehensive reference architecture guides the integration of OpenEvidence into clinical decision support systems (CDS). It is designed for healthcare platforms needing evidence-based query processing, deterministic citation tracking, and full audit logging. Key considerations include HIPAA compliance, optimizing for sub-second response times in point-of-care workflows, and establishing robust data models and event pipelines.

OpenRouter provides a unified API gateway to access leading AI models (OpenAI, Anthropic, Google, Meta, etc.) from a single endpoint. This skill is essential for developers who need to compare model performance (latency, tokens) across different providers, build resilient cross-provider fallback workflows, or manage complex AI pipelines without writing provider-specific code. It supports feature normalization and BYOK (Bring Your Own Key) for high-volume production use.

This skill provides comprehensive reference architectures for building production-grade AI applications using OpenRouter as a unified LLM gateway. It covers three scaling patterns: simple single-service, standard microservice (with caching and budget enforcement), and enterprise event-driven systems (with message queues and workers). Use this when planning system design, reviewing complex AI pipelines, or ensuring scalability and cost control in your LLM integration.

Orchestrates complex multi-stage deployment pipelines by generating production-ready configs and setup code based on user requirements, ideal for automating CI/CD and reliable software releases.

This skill coordinates the complex parallel execution of end-to-end, integration, and unit tests across multiple frameworks (e.g., Jest, Playwright, pytest) and CI/CD environments. It manages test splitting, worker allocation, tiered execution strategies, and aggregates results into unified reports. Ideal for optimizing the testing lifecycle and ensuring robust quality assurance in large-scale, multi-component applications. Key functions include intelligent retry logic for flaky tests and building CI pipelines (e.g., GitHub Actions matrix).

Comprehensive PDF toolkit for extracting text and tables, splitting/merging documents, filling forms, and generating new files via Python or CLI tools, enabling automated, large-scale document workflows in analytics, compliance, or reporting pipelines.

A comprehensive specialist that combines automated static analysis (SonarQube, CodeQL, Semgrep) with advanced AI capabilities. This tool performs multi-layered code reviews assessing security vulnerabilities, performance bottlenecks, architectural coherence, and maintainability across various programming languages, integrating seamlessly into CI/CD pipelines.

A comprehensive guide to implementing Perplexity's API integration at various scales. It provides three validated architectural blueprints—Direct Widget, Cached Research Layer, and Multi-Query Pipeline—allowing developers to choose the optimal structure based on required query volume, latency goals, and complexity. Learn how to scale from simple search widgets to automated, high-volume research pipelines.

This guide details how to configure robust CI/CD pipelines for Perplexity Sonar API integrations using GitHub Actions. It emphasizes best practices for automated testing, including separating costly live integration tests from lightweight mocked unit tests, ensuring code quality while managing API costs and rate limits.

This guide details the process of migrating search and LLM functionalities from legacy APIs (Google CSE, Bing, SerpAPI) to Perplexity Sonar. It demonstrates how to utilize the Strangler Fig pattern to build a robust adapter layer. The primary benefit is consolidating a complex, multi-step pipeline (Search -> Raw Results -> LLM Summarization) into a single, efficient API call, ensuring automatic citation handling and streamlined development.

This guide outlines the comprehensive reference architecture for building advanced, AI-powered search and research applications, modeled after Perplexity. It covers three core tiers: a searchable service with model routing and caching, a citation pipeline for validation and rendering, and an orchestrator for multi-query research synthesis. Use this when designing complex, production-grade, search-augmented LLM integrations or reviewing advanced system patterns.