Loading...
Loading...
Found 1,195 Skills
Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven tasks.
Guide for building MCP (Model Context Protocol) servers that integrate external APIs/services with LLMs. Covers Python (FastMCP) and TypeScript (MCP SDK) implementations.
Build production-ready MCP clients in TypeScript or Python. Handles connection lifecycle, transport abstraction, tool orchestration, security, and error handling. Use for integrating LLM applications with MCP servers.
Implementing providers for Beluga AI v2 registries. Use when creating LLM, embedding, vectorstore, voice, or any other provider.
Best practices for LLM-assisted coding. Declarative workflows, simplicity, tenacity.
Add or refresh a fixed 20-line file-header comment that summarizes a source file and indexes key classes/functions with line-number addresses. Use when annotating large codebases for fast navigation, onboarding, refactors, or when you want LLMs/humans to locate relevant symbols quickly without reading entire files.
Build, validate, and deploy LLM-as-Judge evaluators for automated quality assessment of LLM pipeline outputs. Use this skill whenever the user wants to: create an automated evaluator for subjective or nuanced failure modes, write a judge prompt for Pass/Fail assessment, split labeled data for judge development, measure judge alignment (TPR/TNR), estimate true success rates with bias correction, or set up CI evaluation pipelines. Also trigger when the user mentions "judge prompt", "automated eval", "LLM evaluator", "grading prompt", "alignment metrics", "true positive rate", or wants to move from manual trace review to automated evaluation. This skill covers the full lifecycle: prompt design → data splitting → iterative refinement → success rate estimation.
Setup Spanora AI observability in any project (JavaScript/TypeScript or Python). Use when user asks to "add spanora", "setup spanora", "integrate spanora", "add AI observability", "monitor LLM calls with spanora", "track AI costs", or mentions spanora in the context of adding observability to their project. Detects the language and installed AI SDKs (Vercel AI, Anthropic, OpenAI, LangChain) and configures the optimal integration pattern.
AI agent development standards using golanggraph for graph-based workflows, langchaingo for LLM calls, tool integration, MCP, and LLM best practices (context compression, prompt caching, attention raising, tool response trimming).
Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.
Use this when you need to EVALUATE OR IMPROVE or OPTIMIZE an existing LLM agent's output quality - including improving tool selection accuracy, answer quality, reducing costs, or fixing issues where the agent gives wrong/incomplete responses. Evaluates agents systematically using MLflow evaluation with datasets, scorers, and tracing. Covers end-to-end evaluation workflow or individual components (tracing setup, dataset creation, scorer definition, evaluation execution).
创建高质量 MCP（模型上下文协议）服务器的指南，使 LLM 能够通过精心设计的工具与外部服务交互。在构建 MCP 服务器以集成外部 API 或服务时使用，无论是 Python (FastMCP) 还是 Node/TypeScript (MCP SDK)。