Skill UI

Guides LangChain teams through a production deployment checklist covering security, resilience, observability, performance, testing, and cost controls so you can validate readiness before launch or audit live systems.

Guided workflow for creating, configuring, testing, and deploying Lindy AI agents, covering specification, tool setup, and validation steps that you trigger when building new agent personas.

Provides a minimal Lindy AI agent example for starting a new integration, testing your setup, or learning core API patterns, guiding you through file creation, client initialization, and first agent execution.

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.

Structured production checklist guiding OpenEvidence clinical AI deployments through legal, security, infrastructure, monitoring, resilience, and testing milestones to ensure compliant launches and pre-deployment reviews.

Provides a structured process for reviewing security and compliance of OpenRouter integrations, covering prerequisites, implementation review, testing, and monitoring to prepare for audits or security assessments.

Use this skill to implement OpenRouter function and tool calling when building agents or structured outputs with supported models such as GPT-4 or Claude, covering prerequisites, implementation guidance, testing, and production monitoring for API integrations.

Guides integrating OpenRouter streaming responses to deliver realtime chat output and lower time-to-first-token, covering prerequisites, configuration tips, testing steps, and production monitoring for SSE-capable frontends.

This guide outlines the structure and content guidelines for an AGENTS.md file. This file serves as a comprehensive 'README for agents,' providing detailed, technical context and operational instructions (such as setup, development workflow, testing procedures, and code style) that enable advanced AI coding agents to interact with and understand a codebase effectively. It greatly complements traditional READMEs by focusing purely on machine-readable technical requirements.