Skill UI

Provides expert guidance for GRPO training with TRL, covering dataset prep, reward engineering, structured outputs, and multi-objective alignment when preference pairs are scarce.

This document provides the enterprise reference architecture for deploying Guidewire InsuranceSuite Cloud. It details the integration flow from the Jutro Frontend through the Cloud API Gateway to core modules like PolicyCenter, ClaimCenter, and BillingCenter. It guides users on the overall system structure, data warehousing via DataHub, and analytics using Explore.

Provides production-ready patterns for integrating with the Guidewire insurance platform. This SDK abstracts the complexity of hybrid APIs (REST/SOAP), offering a structured client, robust error handling (retry logic, conflict detection), and a fluent query builder for consistent data access across policies and claims.

Execute complex and compute-intensive workloads directly on fully managed Hugging Face cloud infrastructure. This skill eliminates the need for local setup, allowing users to run jobs using cloud CPUs, GPUs, or TPUs. Ideal for large-scale data processing, batch inference, reproducible model training, and scheduled automation tasks, while persisting results to the Hugging Face Hub.

This guide details best practices for securing Ideogram API integrations. It covers essential steps like using environment variables for key storage, implementing key rotation procedures, establishing server-side proxies to prevent key exposure, and sanitizing prompts to mitigate data leaks. Use this when setting up, maintaining, or auditing API security infrastructure.

This guide outlines the process of migrating codebase dependencies and logic when upgrading the Ideogram API from legacy versions (V1/V2) to the robust V3 endpoints. It addresses critical breaking changes, including the shift from JSON body to multipart/form-data, changes in model naming, aspect ratio syntax, and the integration of new V3 features like rendering speed and style presets. Provides structured code adapters for smooth transition.

A comprehensive guide and implementation structure for configuring Instantly.ai across Development, Staging, and Production environments. This skill ensures strict workspace isolation by utilizing environment variables and dedicated workspaces, preventing accidental data leakage or incorrect live deployments during testing and iteration cycles. It covers secure key management and safe promotion workflows.

This skill provides a comprehensive guide and implementation for deploying a production-ready, containerized integration service using Docker. It connects to the Juicebox API to manage datasets, execute advanced AI-powered analyses, and retrieve structured business insights. The service includes health check mechanisms and supports zero-downtime rolling updates, ensuring reliable real-time data processing and analysis.

This module provides production-grade patterns for integrating the Juicebox AI-powered people search API. It includes a singleton client for centralized rate-limit handling, a robust request builder for complex criteria (location, company, experience years), and structured error wrappers for reliable API calls (retries, error context). Ideal for building scalable recruitment, market research, or data enrichment tools.

A comprehensive guide to mastering asynchronous programming using Kotlin Coroutines and Flow. Covers advanced topics such as structured concurrency, robust exception handling, and creating reactive data streams with StateFlow and SharedFlow. Essential for developing high-performance, modern Kotlin applications.

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.

A comprehensive workflow for implementing robust LLM evaluation using Langfuse. This skill guides users through key processes including scoring traces (numeric, categorical, boolean), collecting user feedback, managing versioned prompts, creating structured datasets, running automated experiments, and implementing LLM-as-a-Judge patterns for advanced quality assurance and system benchmarking.