Skill UI

Guides setup of Langfuse tracing for LLM pipelines, covering automatic OpenAI wrapping, manual spans, streaming responses, and parent-child trace linking for end-to-end observability.

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.

Step-by-step instructions for integrating the Langfuse observability SDK into apps, configuring cloud and self-hosted deployments, and ensuring traces flush across Vercel, AWS/GCP, Docker, and LangChain workflows.

This skill provides comprehensive guidance for senior-level Laravel engineering. It focuses on building production-grade, maintainable, and highly secure applications using modern architectural patterns (clean architecture, services, etc.). Use this when developing new features, refactoring complex code, designing robust APIs, or optimizing database interactions within a Laravel environment. Adheres to best practices like Eloquent optimization and proper authentication flows.

Step-by-step instructions for automating Lastpass workflows through Composio’s Rube MCP, covering service discovery, connection validation, schema compliance, and execution patterns with the MCP tooling.

Automates LaunchDarkly feature flag, environment, segment, and rollout workflows through Composio's Rube MCP toolkit; discover schemas with `RUBE_SEARCH_TOOLS`, manage connections, and orchestrate multi-step operations safely.

Automates LaunchDarkly feature flag workflows by listing projects and environments, crafting webhook-driven trigger workflows, deleting flows, and tracking code references through Composio MCP.

Automates frontend lazy-loading workflows by guiding best practices, generating React/Vue-ready code, and validating production configurations for accessible, high-performance web apps.

Leadfeeder Automation Guide explains how to connect Rube MCP and Composio to discover schemas, manage connections, and run Leadfeeder tools reliably, prioritizing search-before-execute and session reuse for automated workflows.

Automates Leadoku tasks through Composio’s Rube MCP by insisting on upfront schema discovery, connection validation, and schema-compliant RUBE_MULTI_EXECUTE_TOOL calls, making workflows reliable and repeatable.

Provides automated guidance for configuring learning rate schedulers during ML training, covering best practices, setup patterns, and framework-ready code snippets for PyTorch, TensorFlow, and Scikit-learn while validating against common standards.

Provides a senior migration architect workflow that researches legacy codebases, maps bounded contexts, and writes Strangler Fig-based modernization roadmaps so other teams can incrementally reshape systems.