Skill UI

This comprehensive diagnostic bundle collects critical evidence from the Databricks environment, including environment setup, cluster state, job run history, and Delta table diagnostics. It generates a redacted, safe tar.gz file specifically designed for submitting detailed support tickets and efficiently troubleshooting complex data pipeline issues.

This bundle collects comprehensive diagnostic evidence from the Juicebox platform. It gathers API connectivity status, dataset health reports, analysis quota usage, and rate limit information into a single archive. Use it to systematically troubleshoot complex issues such as failed dataset uploads, stalled AI analysis runs, API authentication failures, or quota exhaustion.

This skill provides comprehensive, structured audit logging for OpenRouter API interactions. It automatically captures essential metadata like total cost, token usage, model details, latency, and status, while also performing PII redaction. The resulting audit trail is stored in an append-only SQLite database, making it ideal for building compliance-ready systems, detailed cost monitoring, and deep debugging of production environments.

Trackio is an essential library for logging, visualizing, and analyzing machine learning training experiments. It provides multi-interface support: a Python API for real-time metric logging and alert firing during training; a Command Line Interface (CLI) for retrieving historical metrics and alerts; and synchronization capabilities to Hugging Face Spaces for persistent dashboards. This tool is crucial for debugging, diagnosing training issues (like loss spikes), and automating ML workflow iteration.

Collection of battle-tested PyTorch training recipes covering architecture selection, optimizers, LR scheduling, precision tips, and debugging to train or fine-tune LLMs, vision, diffusion, and biomedical models with high GPU throughput.

Utilize Modal, a serverless GPU cloud, for running complex machine learning workloads, including training, fine-tuning, and inference. This tool provides a zero-config environment, eliminating the need for SSH setup or Docker management. It features automatic scale-to-zero billing and local-first execution, making high-powered GPU compute accessible for debugging and small-scale experiments.

This expert tool provides deep, systematic auditing of datasets to assess completeness, consistency, accuracy, and structural validity. It performs full data profiling, detects anomalies (outliers), analyzes missing data mechanisms (MCAR/MAR/MNAR), and calculates a Data Quality Score (DQS). Use it when validating data for model training, debugging pipelines, or establishing ongoing monitoring checks.

This skill provides a comprehensive framework for building, registering, debugging, and operating complex bioinformatics workflows on the Latch platform. It supports multiple industry-standard pipelines (Nextflow, Snakemake) and utilizes the Python SDK, CLI, and Latch Data/Registry. Use this when developing, deploying, or managing robust, data-intensive computational pipelines in a controlled environment.

This tool collects comprehensive diagnostic data from ClickHouse system tables. It gathers crucial metrics, query logs, merge statuses, and disk usage information. It is essential for troubleshooting performance bottlenecks, preparing detailed support tickets, or investigating complex database infrastructure issues.

This guide provides a quick reference for diagnosing and fixing the top common errors encountered in ClickHouse, including syntax errors, memory limit issues, write permission failures, and data type mismatches. It offers specific error codes, root causes, and actionable SQL solutions for smooth database operation and complex analytics.

This guide provides comprehensive solutions for diagnosing and resolving common errors and exceptions encountered while using the Hex data platform. It covers critical areas such as API authentication failures (401, 403), resource not found issues (404), rate limiting, and various run status errors (ERRORED, KILLED). This is essential for debugging failed data requests, optimizing integration workflows, and ensuring stable data analytics pipelines.

This tool collects a comprehensive diagnostic archive for the Hex platform. It gathers crucial evidence, including API connectivity status, project inventory, recent run histories, data connection health, and current rate limit information. Use this bundle when encountering persistent bugs, preparing detailed support tickets, or troubleshooting complex data flow issues.