Skill UI

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.

A comprehensive diagnostic toolkit designed for advanced troubleshooting of Lindy AI agents. This bundle systematically collects environment information (OS, Python, Node.js), tests API connectivity for webhooks and major integrations (Slack, Notion, Gmail), reviews task history, and guides the user in generating a full, structured support ticket for technical support.

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.

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.

This skill guides the design and implementation of a complete, production-grade Machine Learning pipeline. It employs a multi-agent orchestration workflow, systematically covering all stages of the ML lifecycle: data ingestion and quality assurance, feature engineering, model training, optimization, and robust deployment (MLOps). It ensures built-in reproducibility, monitoring, and scalability.

A comprehensive workflow for advanced AI applications using Mistral AI. This guide covers generating text and code embeddings (1024 dimensions), implementing semantic search via cosine similarity, and building robust RAG pipelines. It also demonstrates advanced tool augmentation using function calling, allowing LLMs to interact with external APIs and databases.

Automatically collects comprehensive diagnostic evidence for Mistral AI support tickets. This bundle includes environment details (OS, Node/Python versions), installed SDK versions, API connectivity test results, available models, and recent error logs. It is essential for reproducing and diagnosing persistent issues when contacting technical support.

Automate More Trees operations via the Rube MCP and Composio toolkit by discovering current tool schemas, managing the More Trees connection, and executing compliant workflows through the recommended execute/multi-execute calls.

nanoGPT is a simplified, minimalist implementation designed specifically for educational purposes. It reproduces the core architecture of GPT-2 (124M) using clean, hackable code, allowing users to understand the entire transformer pipeline from scratch. The framework supports full workflows, including data preparation on various datasets (e.g., Shakespeare, OpenWebText), model training, and text generation, making it ideal for students and researchers learning NLP and deep learning principles.

Guides researchers through nnsight’s tracing and activation APIs so you can inspect or modify PyTorch internals locally or via NDIF-powered remote runs on 70B+ foundation models without local GPUs.

Implements standardized function/tool calling across various large language models (LLMs) via OpenRouter. This unified approach allows developers to build sophisticated, multi-step agents and complex workflows, regardless of the underlying provider (e.g., GPT-4o, Claude 3.5). It simplifies the process of achieving structured output and tool-augmented reasoning in production systems.

Use this tool to query, filter, and compare over 400 available AI models from OpenRouter. It allows users to check pricing, context lengths, model capabilities (e.g., tool calling), and select the best model based on specific needs, ensuring optimal performance and cost efficiency in AI development.