System Observability Bundle

This bundle provides skills to monitor, analyze, and debug complex systems for optimal performance and reliability.

Browse all skill bundles

Included Skills (61)

  1. PCB Defect Generator — Generates synthetic PCB inspection images with defects for quality control teams.
  2. Gke AI Troubleshooting Node Unresponsive Timeout — Diagnose and mitigate GKE TPU or GPU nodes stuck in NotReady / NodeStatusUnknown ("Kubelet stopped posting node status") due to host kernel panics, hardware lockups, or disabled node auto-repair. Use when nodes stop heartbeating beyond the node auto-repair threshold and pods remain stuck in Terminating. Don't use for healthy nodes, pod-only application crashes, or routine GKE upgrades.
  3. Arize Trace Inspector — This tool enables developers to export and analyze LLM application traces, spans, and sessions to effectively debug runtime behavior and performance issues.
  4. Doca Telemetry Exporter — Use this skill when the user is doing hands-on DOCA Telemetry Exporter programming on a host where DOCA is installed — defining a doca_telemetry_exporter_schema and event types, creating sources, picking a publish surface (typed events / opaque events / the metrics counter-gauge-histogram API / OTLP logs / NetFlow), walking the schema-then-source lifecycle, or debugging DOCA_ERROR_* failures from the exporter API. Trigger even when the user does not explicitly mention "DOCA Telemetry Exporter" or "doca_telemetry_exporter_*" — typical implicit phrasings include "publishing counters from my DOCA app", "BAD_STATE when I report an event", "consumer/DTS sees nothing but my report succeeded", "how do I export NetFlow/IPFIX records", or "should I link the exporter or the telemetry service". Refuse and route elsewhere for the receiving DOCA Telemetry Service (DTS), plain stdout logging via doca_log, or real-time event subscription back into the app via doca-comch — those belong to other skills.
  5. Doca Telemetry Utils — doca_telemetry_utils command line on a host with DOCA: discover the diagnostic-counter schema, translate counter names to binary Data IDs and back, and check per-device counter support before committing a DOCA Telemetry exporter config. Use this skill when telemetry counters vanish between the exporter and the collector: "my exporter ships but the collector sees nothing", "this metric silently drops downstream", "which counters does this BlueField expose", "translate this 0x... back to a counter name", "what do node / pcie_index / depth mean here", or "is this counter supported on this device", even without naming the tool. Route exporter or collector code to doca-telemetry-exporter / doca-telemetry, DTS deployment to doca-dts, and DOCA install or repair to doca-setup.
  6. Grafana Dashboard Architect — This skill enables engineers to design and implement production-ready Grafana dashboards for effective system observability, infrastructure monitoring, and business metric tracking.
  7. Monitoring Advisor — Helps data teams analyze coverage and create monitors for warehouse tables and AI agents.
  8. Applicationinsights Web Ts — Instrument browser/web apps with the Application Insights JavaScript SDK (@microsoft/applicationinsights-web).
  9. Kubernetes Compliance Auditor — This tool analyzes kube-bench output to generate comprehensive CIS benchmark audits, providing remediation guidance and compliance evidence for security professionals and auditors.
  10. Monte Carlo Ingestion — This tool assists data engineers in pushing metadata, lineage, and query logs to Monte Carlo from any custom data warehouse source.
  11. Production Deployment Assistant — Helps developers prepare for production launches with checklists, monitoring, and rollback strategies.
  12. Monitor Tuner — Analyzes Monte Carlo monitors to recommend configuration changes that reduce alert noise.
  13. Splunk Security Analyst — This skill assists security professionals in investigating incidents by performing log correlation, anomaly detection, and complex SPL query generation within Splunk Enterprise Security.
  14. Implementing Vulnerability Sla Breach Alerting — Build an automated SLA breach alerting system for vulnerability remediation,
  15. Root Cause Analyzer — Guides users through systematic data incident investigations using Monte Carlo's tools.
  16. USB Forensics Analyzer — This tool reconstructs USB device connection history by correlating Windows registry keys and event logs to assist digital forensic investigators in tracking data exfiltration.
  17. Jetson Diagnostic — Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
  18. Database Migrations Migration Observability — Migration monitoring, CDC, and observability infrastructure
  19. Observability Designer — Design production-ready observability strategies combining metrics, logs, and traces. Includes SLI/SLO design, golden-signals monitoring, alert optimization. Use when adding observability to a new service, refactoring alerting that is too noisy, or designing an SLO program before scaling production load.
  20. Asset Health Checker — Generates a structured health report for data assets using Monte Carlo's observability platform.
  21. Uncertainty And Units — The Uncertainty And Units skill tracks physical units and propagates measurement uncertainty in scientific calculations, enabling precise unit conversion and dimensional validation. Researchers and engineers use it for Monte Carlo propagation, error analysis through curve fits, and order‑of‑magnitude plausibility checks with dimensionless groups and characteristic scales.
  22. Sci-Fi Interface Designer — This tool provides technical implementation guidelines for developers creating immersive, tactical heads-up displays and futuristic dashboard interfaces for web and mobile applications.
  23. JSON Data Shuffler — This tool assists data engineers by safely randomizing repetitive JSON objects while ensuring structural integrity and schema consistency throughout the entire process.
  24. Nemo Relay Plugin Observability — Use this skill when choosing or configuring NeMo Relay 0.6 or 0.7 observability through the built-in plugin, subscribers, or exporters, including raw ATOF events, ATIF trajectories, OpenTelemetry, OpenInference, or custom event handling.
  25. Rive — Build interactive animations with Rive — load .riv files, control state machines, respond to user input, and embed runtime animations in web and mobile apps. Use when tasks involve interactive UI animations, character animations with state logic, animated icons with hover/click states, or game-like interactions in production apps.
  26. Loki — Loki is a horizontally scalable log aggregation system built by Grafana Labs. Unlike traditional log platforms that index the full text of every log line, Loki indexes only metadata labels, making it significantly cheaper to operate. It integrates natively with Grafana for querying and visualization, and uses LogQL — a query language inspired by PromQL — to filter, parse, and aggregate log streams.
  27. Agent Run Auditor — This tool independently verifies agent execution success by auditing available traces, logs, and artifacts to ensure claims align with objective evidence.
  28. Structured Logging Enabler — Implements structured logging in Python using structlog, aiding developers in creating context-rich, easily processed logs for improved observability.
  29. MCP Server Architect — This tool helps developers rapidly build and validate production-ready MCP servers by automatically generating robust, type-safe tool definitions directly from OpenAPI contracts.
  30. Alert Optimizer — Optimize alert rules and escalation policies for monitoring platforms to reduce alert fatigue.
  31. Soda Data Validator — Assists developers in writing YAML-based data quality checks using Soda, ensuring data freshness, completeness, and validity for reliable data pipelines.
  32. LLM Observability Expert — Assists developers in tracing and monitoring LLM applications using Langtrace, an open-source observability platform built on OpenTelemetry.
  33. LLM Observability Expert — Assists developers using Langfuse, the open-source LLM engineering platform, to trace calls, evaluate quality, and manage prompts for AI applications.
  34. Cold Outreach Assistant — This tool helps founders craft personalized cold emails and LinkedIn messages to effectively engage prospects, investors, and partners for better response rates.
  35. Appinsights Instrumentation — The skill guides developers through integrating Azure Application Insights into web applications, covering SDK setup, configuration, and telemetry patterns. It provides practical examples and best practices for monitoring performance, enabling software engineers and DevOps professionals to obtain reliable, actionable insights into their app’s behavior.
  36. Performance Diagnostic Tool — Helps data engineers diagnose pipeline bottlenecks and regressions using Monte Carlo's observability.
  37. Cloud Storage Anomaly Detector — This skill identifies abnormal cloud storage access patterns for security analysts by monitoring audit logs and analytics to detect potential data exfiltration activities.
  38. Azure Threat Analyzer — This tool assists security analysts by querying Azure Monitor logs to identify suspicious administrative activity and potential threats within cloud environments.
  39. Langfuse Observability Expert — This skill assists developers in instrumenting, debugging, and monitoring LLM applications by implementing robust tracing, prompt management, and evaluation workflows using Langfuse.
  40. RDP Brute-Force Detector — This tool analyzes Windows Security Event Logs to identify and correlate RDP brute-force attack patterns, assisting security analysts in detecting compromised accounts.
  41. PowerShell Threat Hunter — This tool assists cybersecurity analysts in identifying malicious activity by parsing Windows Event Logs to detect obfuscated PowerShell commands and bypass techniques.
  42. Product Metrics Architect — This tool helps product managers and data analysts design actionable metrics dashboards, define key performance indicators, and establish effective data monitoring strategies.
  43. Web Log Intrusion Analyzer — This tool parses Apache and Nginx logs to identify malicious patterns and anomalies, assisting security analysts in detecting web-based cyber attacks.
  44. AKS GPU Diagnostics — Diagnoses day-two AKS GPU and KAITO incidents for DevOps engineers using profile-aware evidence.
  45. NeMo Relay Instrumentation — This skill helps developers integrate NeMo Relay managed execution APIs into existing tool and LLM call sites to enable lifecycle events and guardrails.
  46. AI Readiness Auditor — This tool executes repository AI readiness assessments and generates a comprehensive HTML dashboard to help developers evaluate and improve their codebase's AI compatibility.
  47. Financial Digest Generator — This tool generates comprehensive monthly financial summaries, including spending trends and anomaly detection, to help users quickly assess their personal financial health.
  48. WMI Lateral Movement Hunter — This tool identifies WMI-based lateral movement and persistence by analyzing process creation and activity logs to assist security analysts in threat hunting.
  49. Error Observability Expert — This expert assists developers in implementing robust error tracking, structured logging, and alerting systems to ensure rapid identification and resolution of production issues.
  50. Network Traffic Baseliner — Analyzes NetFlow and IPFIX data to establish normal traffic patterns and detect security anomalies for SOC analysts using statistical profiling.
  51. Distributed Systems Debugger — This expert diagnostic tool assists engineers in performing root-cause analysis, investigating production incidents, and implementing robust observability solutions for complex distributed software systems.
  52. Empire Artifact Analyzer — This tool identifies PowerShell Empire post-exploitation framework activity within Windows event logs to assist security analysts in detecting malicious C2 staging and execution.
  53. Azure Telemetry Integrator — This tool helps developers instrument Node.js or ASP.NET Core web applications to enable comprehensive telemetry monitoring within Azure App Insights.
  54. API Load Tester — This tool stress-tests API endpoints under progressive concurrency to identify performance bottlenecks and provide actionable optimization recommendations for developers and engineers.
  55. Manifest — Install and configure the Manifest observability plugin for your agents. Use when setting up telemetry, configuring API keys, or troubleshooting the plugin.
  56. Statsmodels — Statsmodels is Python's premier library for statistical modeling, providing tools for estimation, inference, and diagnostics across a wide range of statistical methods.
  57. Ecommerce Performance Monitor — This framework provides proactive monitoring, alerting, and diagnostic tools to help engineering and merchandising teams maintain optimal site speed and uptime.
  58. Angular State Architect — This skill assists Angular developers in implementing, migrating, and optimizing state management solutions using Signals, NgRx, and RxJS for scalable application architecture.
  59. Email Sequence Validator — This tool helps marketing and operations teams ensure email sequences meet rigorous standards for content, data accuracy, compliance, and monitoring before launch.
  60. Experiment Guardrail Manager — This framework helps data scientists and product managers define, monitor, and enforce critical performance metrics to ensure safe and compliant experiment launches.
  61. Linux Automation Toolkit — This skill provides production-ready shell script templates to help system administrators automate Linux maintenance, monitoring, security operations, and routine infrastructure management tasks.

Opening your workspace…