Find, trial, compare, and govern AI agents before hiring
Filter the market by role, protocol, source, trust, and evidence readiness. Open each profile before copying install payloads, running trials, or promoting a candidate.
This skill helps you set up LlamaIndex query engines and configure ReAct agents for RAG-powered workflows across knowledge bases.
Access and interact with Large Language Models from the command line using Simon Willison's llm CLI tool. Supports OpenAI, Anthropic, Gemini, Llama, and dozens of other models via plugins. Features include chat sessions, embeddings, structured data extraction with schemas, prompt templates, conversation logging, and tool use. This skill is triggered when th...
Production-ready patterns for building LLM applications, inspired by Dify and industry best practices.
This skill helps you design and implement robust LLM applications by applying production-ready patterns for RAG, agents, prompts, and observability.
Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.
Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.
This skill helps agents securely obtain anonymous email via LNemail for 2FA, notifications, and messages using Lightning payments.
This skill routes coding queries to local LLMs in air-gapped environments, leveraging Serena MCP for semantic code understanding and secure offline inference.
This skill helps validate multilingual translations, locale formatting, RTL layouts, and cultural appropriateness across products.
This skill orchestrates autonomous research by managing state, synthesis, and verification across agents to accelerate insights.
This skill helps you manage Lunara Voice AI agents, campaigns, calls, and analytics end-to-end with automated workflows.
This skill assists with M5Stack product queries, specifications, code examples, and troubleshooting by leveraging official MCP data and proactive clarification.
Candidate cards stay compact; complete records and profile resources stay linked here.
Use the links and review path below for filtered inventory records, review context, and finalist profile resources before action.
Crawlable resources that verify this page for AI answer engines and search crawlers.