Skill UI

This skill provides a comprehensive guide to designing and developing autonomous AI agents for code plugins. It covers the required file structure (YAML frontmatter), best practices for defining agent roles, designing robust system prompts, and setting up clear triggering conditions. Use this when you need to conceptualize, structure, or refine an agent's capabilities to handle complex, multi-step tasks autonomously.

A comprehensive guide to understanding the complete state (context) available to Large Language Models during inference. Covers core components like System Prompts, Tool Definitions, Message History, and Retrieval Augmented Generation (RAG). Learning to engineer context is crucial for building robust, efficient, and reliable AI agent systems by managing the attention budget and ensuring high-signal information delivery.

DSPy lets you declaratively program complex language model systems, assemble modular RAG/agent pipelines, and optimize prompts and modules automatically for reliable LM-driven apps.

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.

LangSmith centralizes tracing, evaluation, and monitoring for LLM applications, letting teams debug prompts, run regression tests, collect latency/cost metrics, and integrate with OpenAI, Anthropic, LangChain, or LlamaIndex to keep production systems observable.

Master comprehensive strategies for evaluating Large Language Model (LLM) applications. This skill covers automated metrics (BLEU, ROUGE, BERTScore), structured human evaluation dimensions, and advanced LLM-as-Judge techniques. Use it to systematically measure model performance, compare prompts, detect regressions, and build confidence in production systems.

This skill specializes in designing, optimizing, and evaluating prompts for Large Language Models (LLMs). It allows users to generate optimized prompt templates, structured output schemas (e.g., JSON mode, function calling), and comprehensive test suites. Use this skill when building new LLM applications, implementing complex reasoning patterns like Chain-of-Thought, defining system guardrails, or building robust evaluation frameworks to measure and improve model performance.

Document describes structured prompts, chain-of-thought guidance, few-shot examples, system prompt design, and tooling advice for building reliable prompt engineering workflows in LLM-augmented products.

A comprehensive collection of battle-tested, structured prompts designed to elevate interactions with Large Language Models (LLMs). Covers advanced use cases including expert coding reviews, system architecture design, performance analysis, technical writing, and creative brainstorming, ensuring high-quality, actionable AI output.

This skill enables the creation and configuration of specialized Cascade agents tailored for specific domains or tasks. Users can define system prompts, integrate domain knowledge, and set precise activation triggers. It facilitates building highly customized, domain-specific AI agents and automated workflows within the Windsurf ecosystem.

A comprehensive guide to building production-grade evaluation systems for Large Language Models (LLMs). This skill covers advanced methodologies, including Direct Scoring and Pairwise Comparison, alongside critical techniques for mitigating systematic biases (e.g., Position Bias, Length Bias). Learn how to select appropriate metrics and structure prompts to ensure reliable, consistent, and objective quality assessment across various AI applications.

This methodology converts verbose, natural language system instructions into an atomic, structured-label format (e.g., trigger:, action:). By structuring rules, it bypasses the limitations of natural language processing, ensuring LLMs allocate full attention to every constraint, thereby maximizing compliance, improving reliability, and reducing token usage.