Skill UI

This skill guides the installation and configuration of the Juicebox PeopleGPT API. It enables developers to access AI-powered people search capabilities across millions of professional profiles. Use this when setting up the initial connection or performing deep people search functionality within your application.

This comprehensive guide assists developers in planning and executing upgrades for systems utilizing the Juicebox API. It covers critical steps such as API version detection, migrating complex data schemas (e.g., search results), updating query syntax, and implementing robust rollback strategies. Essential for maintaining continuous operation in recruiting and market research applications when the underlying API changes.

Guides frontend developers through keyboard navigation testing, offering best-practice advice, code snippets, and automated validation for accessibility, frameworks, and performance.

A comprehensive guide for developers on utilizing the Kling AI Text-to-Video REST API. This skill provides minimal working examples in Python and Node.js, demonstrating the complete workflow: submitting a text prompt, polling the task status, and retrieving the final generated video URL. Ideal for integrating advanced AI video generation capabilities into development projects.

This comprehensive guide helps developers safely migrate between different versions of the Kling AI video generation model (e.g., v1.x to v2.x). It details breaking changes, parameter differences, feature availability matrices (including native audio and camera control), and provides code examples for parallel A/B testing and robust rollback strategies, ensuring seamless API adoption.

This guide provides minimal working examples demonstrating the LangChain Expression Language (LCEL). It shows how to chain together diverse components—such as prompts, LLMs, and output parsers—using simple pipe syntax (e.g., .pipe() or |). Ideal for developers starting a new LangChain project, understanding core AI workflow patterns, or mastering structured data output.

This comprehensive guide walks developers through migrating complex LLM codebases from raw SDK calls (OpenAI, Anthropic) or legacy frameworks (LlamaIndex) to the structured LangChain framework. It covers code assessment, pattern-by-pattern migration, advanced agent construction, robust tool calling, and transforming custom RAG pipelines into scalable, standardized chains.

A comprehensive guide to setting up production-grade observability for LangChain applications. It integrates LangSmith tracing for zero-code debugging, custom callbacks for detailed metric collection (latency, token usage, error rate), and Prometheus exporters for robust alerting. This allows developers to monitor LLM pipelines, track performance metrics, and manage operational health in real-time.

Learn how to monitor, analyze, and optimize the expenditure of Large Language Models (LLMs) using Langfuse's advanced analytics suite. This guide covers techniques like automatic token tracking, programmatic cost reporting via the Metrics API, and implementing smart model routing to automatically select the most cost-effective model based on task complexity and input length. Essential for any developer managing AI budgets and ensuring operational efficiency.

This guide provides a comprehensive local development setup for LLM applications using Langfuse. It enables fast iteration cycles, real-time trace debugging, and hot reloading, making it ideal for developers building and testing complex AI workflows locally. Instructions cover environment setup, advanced SDK usage, and optional self-hosted Docker deployment.

Guides deliberate skill development during AI-assisted coding by offering optional 10–15 minute exercises after architecture work, schema changes, or “why” questions so developers stay engaged and understand decisions.

A comprehensive guide for setting up a local development loop to test AI agent integrations. This skill teaches developers how to build and debug webhook receivers, callback handlers, and associated application code that interacts with a cloud-hosted AI agent (like Lindy). It requires using tunneling services (e.g., ngrok) to expose local endpoints for receiving webhooks and simulating the entire agent-to-application data flow.