“LangChain”

Use this skill when the user asks to research a topic and produce a structured report.

Use this skill whenever the user provides a block of text and asks for statistics on it — character count, word count, sentence count, unique words, or most…

Use this skill whenever the user asks for an analysis, summary, or sentiment report of a customer's support tickets.

Use when the user wants to write a sales pitch or outreach message for a prospect.

Use this skill when the user asks to save a report, note, summary, or generated content into a file.

Expert in Langfuse - the open-source LLM observability platform.

High-performance knowledge graph MCP server for AI coding agents with semantic search.

Platform for developers of AI chatbots and LLM apps, covering monitoring, prompts and analytics

Toolkit for evaluating LLM applications with objective metrics, test data generation and feedback loops

Searches and retrieves MLflow documentation from the official docs site.

Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google…

OWASP LLM Top 10 (2025) audit checklist for AI applications, agent tools, RAG pipelines, and prompt construction.

Expert in designing and building autonomous AI agents.

Mem0 Platform SDK for adding persistent memory to AI applications.

Write in plain language per the US Plain Writing Act of 2010 and the Plain Language Action Network.

Python interface for running and evaluating agents from several frameworks, with OpenTelemetry traces; now in soft deprecation.

Marketplace of ready-to-run web scraping and automation tools called Actors, runnable through an API.

Open source vector database for AI apps, built on Postgres with pgvector and available self-hosted or managed.

Open-source NVIDIA library that connects existing agents to tools and data, with profiling and LangSmith tracing; deprecated, EOL end of 2026.

OpenAI-compatible inference API for open models, with dedicated GPUs, post-training and batch inference.

AI observability in Sentry for tracing and debugging agent runs, tool calls, token usage and errors

Inject the 3 most recent session IDs for the current workspace into the prompt before Claude responds.

AI gateway and agent observability for 250+ LLMs, with tracing, analytics, guardrails and cost controls.

Use when the user says "scaffold an agent", "build me a LangGraph agent that does X", "create a Deep Agent", "start a new agent", or hands off from /lg-design…