Skill UI

This expert skill analyzes codebases to identify, quantify, and prioritize all forms of technical debt—including code complexity, architectural flaws, outdated dependencies, and testing gaps. It calculates the measurable impact of this debt on development velocity, bug rates, and overall business risk. The output provides a comprehensive, actionable, and ROI-driven roadmap for systematic remediation.

A comprehensive expert system for analyzing software codebases to identify, quantify, and prioritize technical debt across various dimensions (code, architecture, testing, infrastructure). It provides detailed metrics, impact assessments (development velocity, quality loss), and actionable, prioritized remediation roadmaps with clear ROI projections.

Serve production-grade LLM APIs with vLLM, leveraging PagedAttention, continuous batching, quantization, and tensor parallelism to maximize throughput while keeping latency, GPU usage, and scalability under control for OpenAI-compatible deployments.

This framework provides a comprehensive methodology for defining, measuring, and implementing Service Level Indicators (SLIs), Service Level Objectives (SLOs), and managing error budgets. It helps engineering teams quantify service reliability (e.g., availability, latency) and establish clear, measurable targets (SLOs). By tracking error budgets, teams can strategically balance rapid feature development (innovation velocity) against maintaining high system stability and reliability.

This comprehensive guide outlines best practices for optimizing vector indexes for production systems. It covers critical techniques such as tuning HNSW parameters, implementing quantization strategies, and optimizing memory usage. Use this when you need to balance search latency, recall, and scalability for large-scale vector databases.

Cirq is Google Quantum AI’s Python framework for building, simulating, and deploying noise-aware quantum circuits on both simulators and real hardware, complete with experiment templates, transformation utilities, and hardware-specific toolkits.

PyOpenMS provides Python bindings for OpenMS to drive complete mass spectrometry workflows, covering data IO, spectral processing, feature/peptide-protein identification, quantitation, and metabolomics pipelines.

Qiskit is the world's leading open-source framework for building, optimizing, and executing quantum circuits. It provides comprehensive capabilities for quantum error mitigation, running algorithms on diverse hardware backends (including IBM Quantum and simulators), and supporting applications in chemistry and machine learning. Essential for researchers entering the quantum computing field.

Use this command to set up a structured multi-agent collaboration environment within AgentHub. It allows you to define the core task, specify the required number of agents, and configure detailed evaluation criteria (metrics, directions, and commands) for both quantitative benchmarking and qualitative LLM judging. This is the starting point for any agent competition or complex AI workflow.

This skill maps observed adversary behaviors, security alerts, and detection rules to the MITRE ATT&CK framework. It is essential for quantifying detection coverage, building ATT&CK heatmaps, tagging SIEM alerts, and prioritizing security controls based on known threat actor playbooks. Use it for comprehensive gap analysis and risk reporting.

A specialized audit skill designed to identify and quantify resource leakage, excessive costs, and billing vulnerabilities within complex development tool workflows (e.g., GitHub Apps). It traces webhook events, queue processing, and model calls to pinpoint where token burn or unauthorized resource usage is occurring, ensuring cost efficiency and clean billing practices.

This skill enables users to create new AI skills from scratch, modify existing ones, and optimize performance through evaluation and benchmarking. It supports iterative development loops, including drafting, testing with prompts, quantitative analysis, and refining descriptions for better triggering accuracy. Ideal for developers building custom agent workflows.