Skill UI

This guide provides a comprehensive framework for minimizing cloud expenditure on Databricks. It covers identifying cost drivers via system billing tables, implementing cluster policies, utilizing spot instances for batch processing, right-sizing SQL warehouses, and automating the shutdown of idle development clusters. Use it when managing cloud spending or optimizing data platform usage.

This skill provides a comprehensive framework for monitoring Mistral AI API usage in production. It includes an instrumented client wrapper (TypeScript) to automatically capture critical metrics like latency, token consumption, cost, and error rates. Furthermore, it integrates with Prometheus for metric storage and Grafana for visualization, allowing users to set up sophisticated alerting rules for performance degradation, rate limiting, or cost spikes.

This skill provides comprehensive monitoring capabilities for GPU instances running on Vast.ai. It collects key metrics including GPU utilization, instance uptime, temperature, and accumulated costs. Use this when setting up operational monitoring dashboards, configuring critical alerts (e.g., idle GPUs, high temperature, budget overruns), or automating resource usage tracking in a cloud computing environment.

This skill guides SOC analysts and detection engineers on how to correlate complex, multi-stage attacks within the IBM QRadar SIEM platform. It covers advanced usage of AQL (Ariel Query Language) for deep event investigation, building custom correlation rules (Building Blocks and Offenses), and cross-source data correlation (e.g., auth failures with network flows). It is essential for reducing false positives and improving threat detection accuracy.

This skill provides a comprehensive guide for identifying and exploiting insecure local data storage vulnerabilities in Android and iOS applications. It covers analyzing plaintext credentials, unencrypted SQLite databases, insecure SharedPreferences, and improper keychain/keystore usage. Essential for performing robust mobile penetration testing focused on OWASP M9.

This skill helps detect NTLM relay attacks (T1557.001) by analyzing Windows Security Event ID 4624 (logon type 3) for NTLMSSP usage. It flags critical anomalies such as IP-to-hostname mismatches, evidence of LLMNR/NBT-NS poisoning, rapid cross-domain authentication, and verifies SMB signing status. It is essential for proactive threat hunting and security incident investigation in Active Directory environments.

This guide details the deployment and usage of OPA Gatekeeper, a powerful Kubernetes admission controller. Gatekeeper enforces custom policies written in Rego using ConstraintTemplates and Constraints. It validates, mutates, or denies resource requests at admission time, ensuring that non-compliant workloads are blocked before scheduling. Ideal for organizations requiring robust, code-based policy enforcement to meet strict security and compliance standards.

This guide outlines a comprehensive methodology for hardening AWS Lambda execution roles. It focuses on implementing the principle of least privilege by auditing existing roles, analyzing actual API usage via CloudTrail and IAM Access Analyzer, and programmatically creating scoped IAM policies. Use this when deploying new serverless functions, remediating over-privileged roles found during security audits, or building secure, reusable role templates.

A comprehensive guide for diagnosing production performance issues in Qdrant vector databases. Learn how to systematically check the optimizer status, analyze high memory usage (OOM crashes), and troubleshoot slow query latencies using key metrics and dedicated API endpoints. Essential for maintaining optimal operational health.

This guide provides expert principles for designing and auditing system-level experiments in computer architecture (e.g., for ASPLOS-level conferences). It details the proper usage of various instruments—from real silicon and FPGAs to cycle-level simulators and analytical models—ensuring that every claim is matched to a valid, stated error model. It emphasizes workload selection, establishing strong baselines, performing rigorous ablation studies, and honestly reporting measurement noise and limitations to maintain scientific credibility.