Skill UI

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.

This skill provides comprehensive patterns for building highly reliable applications that interact with external Large Language Model (LLM) APIs, such as Perplexity Sonar. It implements critical reliability techniques including Circuit Breakers, Model Fallback, Streaming Timeout handling, and Caching layers. Use this to ensure your application maintains high availability and graceful degradation even when external services experience intermittent failures or variable performance.

This skill provides production-ready patterns for integrating with the Perplexity Sonar API in both TypeScript and Python. It covers best practices for creating robust wrappers around the standard OpenAI client, including dedicated handling for citations, search results, and related questions. It also includes essential utilities like implementing exponential backoff for reliable retries. Use this when setting up complex search-augmented generation workflows or standardizing team coding practices around Perplexity usage.

Provides comprehensive security best practices for integrating the Perplexity API. This guide covers secure API key management using environment variables, critical query sanitization (stripping PII like emails, phone numbers, and credit cards), and implementing domain filters for compliance. Essential for developers building production applications that handle sensitive user data.

This skill enables the development of robust, event-driven pipelines interacting with the Perplexity Sonar API. Since Perplexity lacks native webhooks, this system simulates event patterns using advanced techniques: Streaming Server-Sent Events (SSE) for real-time data, job queues (like BullMQ/SQS) for asynchronous batch research, and cron-triggered monitoring for scheduled news and trend alerts. It provides patterns for building complex, reliable, and scalable AI applications.

Guides how to connect to Persistiq via Rube MCP and run Composio automations, highlighting prerequisite connections, tool discovery steps, schema compliance, session reuse, and execution calls for reliable workflows.

Guides building productivity-first tools by scratching your own itch—rapid prototyping, CLI/local-first apps, scripting to product evolution, and dogfooding for reliable personal workflows.

Guide for automating Piggy workflows via Composio’s Rube MCP, covering prerequisite connections, tool discovery, schema-aware execution, and dependable patterns for running RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS, and RUBE_MULTI_EXECUTE_TOOL safely.

Automates Piloterr workflows via Composio Rube MCP, guiding connection validation, tool discovery, schema compliance, and structured execution for dependable API-driven operations.

Automates Pingdom maintenance by ensuring you first discover the current tool schemas via Rube MCP, confirm the Pingdom connection, and then execute workflows with schema-compliant arguments so operations stay reliable and predictable.

Automates Pipedrive CRM workflows via Rube MCP, covering deal/contact/org operations, activity scheduling, notes, and pipeline stage management through the Composio toolkit for reliable sales automation.

Automate Pipeline CRM operations through Composio’s Pipeline CRM toolkit by orchestrating Rube MCP searches, connections, and multi-step executions so workflows stay schema-compliant and reusable.