Skill UI

A comprehensive guide to building production-ready Apache Airflow Directed Acyclic Graphs (DAGs). This skill covers best practices for operators, sensors, testing, deployment, and designing robust data pipelines. Use this when orchestrating complex workflows, managing ETL processes, or ensuring reliable batch job execution in a production environment.

This comprehensive framework allows users to validate and test both crypto and traditional trading strategies against extensive historical market data. It calculates essential performance metrics (Sharpe Ratio, Sortino Ratio, Max Drawdown), simulates trade execution, generates equity curves, and includes advanced parameter grid search optimization tools for robust strategy validation.

Configure automated Continuous Integration and Continuous Deployment (CI/CD) pipelines for Juicebox AI data analysis integrations. This setup utilizes GitHub Actions to run comprehensive unit tests (with mocked datasets) and integration tests (connecting to live APIs) on every PR and merge to main. It ensures that data upload logic, analysis execution, and result parsing workflows are robust and reliable before deployment.

This guide details how to implement comprehensive observability for AI agents. It covers monitoring key metrics such as task success rates, step failures, execution duration, and credit consumption. Use this when setting up performance dashboards, configuring real-time alerts (via webhooks/Prometheus), or tracking agent reliability over time.

Streamlines Simple Analytics tasks by orchestrating Composio toolkits through Rube MCP, guiding tool discovery, connection checks, schema-aware arguments, and execution workflows.

This advanced tool simulates complex DeFi flash loan strategies across major protocols like Aave, dYdX, and Balancer. It calculates net profitability, estimates gas costs, and assesses comprehensive risks (MEV, liquidity, execution). Use it to evaluate arbitrage opportunities, analyze liquidation potential, or compare multiple lending providers before executing real transactions.

A specialized tool for digital forensics investigators that parses the Windows Amcache.hve registry hive. It extracts crucial evidence regarding program execution history, application installation metadata, and loaded driver binaries. By correlating SHA-1 hashes and reconstructing timelines, users can determine which executables ran on a system, aiding in incident response and threat detection.

This skill provides a method to parse Windows Prefetch files (.pf) using Python, allowing security analysts to reconstruct detailed application execution histories. It is crucial for incident response, enabling the detection of renamed binaries, identifying suspicious execution patterns, and building accurate chronological timelines of system activity for deep forensic investigation.

This skill detects WMI-based lateral movement by analyzing key Windows Security Event ID 4688 and Sysmon Event ID 1 logs. It focuses on identifying suspicious process execution patterns, such as WmiPrvSE.exe spawning unauthorized child processes (cmd.exe, powershell.exe), suspicious command lines, and WMI event subscriptions used for persistence. Ideal for security incident response and threat detection.

This workflow bridges the gap between an abstract experiment plan and concrete, executable code. It reads structured experiment roadmaps (e.g., EXPERIMENT_PLAN.md), automatically generates or modifies necessary code scripts, handles prerequisite setup (like cloning base repositories), deploys the experiments to compute resources (GPU), and meticulously collects initial results. It includes optional steps for cross-model code review, ensuring robustness and correctness before execution. Ideal for moving from research hypotheses to measurable, running results.

Provides systematic Power BI performance troubleshooting guidance covering model optimization, DAX design, report layout, and capacity diagnostics, plus tool-driven measurement tips for faster page loads, interactions, and query execution.

Polars is a lightning-fast DataFrame library built for Python and Rust, leveraging Apache Arrow. It provides an expression-based API and lazy evaluation framework for highly efficient data manipulation. It is ideal for complex data pipelines, large-scale ETL tasks, and migrating from Pandas due to its superior performance, parallel execution capabilities, and optimized query planning.