Skill UI

Defines how to build AI wrapper products that solve specific customer problems, covering prompt engineering, API cost control, usage metering, and defensible UX so AI becomes a paid, reliable feature.

Defines how to build AI wrapper products that solve specific customer problems, covering prompt engineering, API cost control, usage metering, and defensible UX so AI becomes a paid, reliable feature.

This skill details advanced techniques for enhancing the effective context capacity of LLMs. It outlines four core strategies—Compaction, Observation Masking, KV-Cache Optimization, and Context Partitioning—to prevent context limits from constraining task complexity. By strategically managing token usage, users can reduce operational costs, minimize latency, and implement robust, long-running agent systems for handling large documents or conversations.

Automates Gemini operations by walking through Rube MCP/Composio tool discovery, connection management, and execution steps, ensuring schema-aware usage, memory handling, and session reuse for reliable flows.

A comprehensive guide to setting up production-grade observability for LangChain applications. It integrates LangSmith tracing for zero-code debugging, custom callbacks for detailed metric collection (latency, token usage, error rate), and Prometheus exporters for robust alerting. This allows developers to monitor LLM pipelines, track performance metrics, and manage operational health in real-time.

Implement comprehensive end-to-end tracing for Large Language Model (LLM) calls, chains, and complex agents using Langfuse. This workflow demonstrates techniques like OpenAI drop-in wrappers, manual span creation for RAG pipelines, tracking streamed responses, and integrating with various LLM providers (OpenAI, Anthropic). Use this to monitor latency, track token usage, and debug complex AI features in production.

This guide details how to establish comprehensive observability for LLM operations using Langfuse. It covers setting up Prometheus metrics (tracking traces, generation duration, and token usage) and visualizing them in Grafana dashboards. Ideal for monitoring application health, optimizing costs, and tracking performance over time.

Fetch execution traces from LangSmith Studio to inspect LangChain/LangGraph agent runs, analyze errors, tool calls, memory usage, and performance, and export sessions for deeper diagnostics using the langsmith-fetch CLI.

This skill provides comprehensive best practices for managing data within AI agent workflows. It covers data classification (PII, PHI), prompt-level controls, secure memory usage, and isolation techniques. It ensures that agents adhere to global regulations like GDPR, CCPA, and HIPAA when handling sensitive or regulated data.

This skill simulates an expert prompt engineer, specializing in optimizing prompts for Large Language Models (LLMs). It applies advanced techniques such as Constitutional AI, Chain-of-Thought reasoning, and model-specific tuning. Use this tool to transform basic instructions into production-ready, high-performance prompts, significantly boosting accuracy, reducing hallucinations, and optimizing token usage.

Practical guide to integrating Claude models: covers API client usage, streaming responses, tool calls, RAG pipelines, document chunking, cost-aware model selection, and anti-pattern warnings for efficient LLM workflows.

Guidelines for automating Mailsoftly tasks through Composio’s Mailsoftly toolkit via Rube MCP, covering discovery, connection checks, execution steps, and schema-aware tool usage for reliable workflows.