Analytics & Monitoring Claudeスキル

Log Director

Orchestrates and executes batch operations across multiple logs in parallel for large-scale management.

Log Manager

Orchestrates sequential, multi-step workflows like creation, validation, and archiving for individual logs.

SLO Implementation Framework

Defines and implements reliability targets using SLIs, SLOs, and error budgets to optimize service performance and innovation velocity.

Grafana Dashboard Manager

Builds and optimizes production-grade Grafana dashboards for comprehensive system observability and real-time metric visualization.

Python Performance Optimization

Profiles and optimizes Python code using advanced diagnostic tools and proven implementation patterns to improve execution speed and resource efficiency.

Prometheus Configuration & Monitoring

Configures Prometheus for comprehensive metric collection, alerting, and observability across infrastructure and applications.

Sentry Error Tracking & Monitoring

Implements comprehensive Sentry v8 error tracking and performance monitoring across backend services, controllers, and automated workflows.

Distributed Tracing Implementation

Implements comprehensive distributed tracing using Jaeger and Tempo to monitor request flows and optimize microservice performance.

Market Analysis

Generates multi-dimensional stock analysis reports by synthesizing technical indicators, fundamental financials, and real-time sentiment data.

SLO Implementation & SRE Metrics

Defines and implements service reliability targets using SLIs, SLOs, and error budgets to balance innovation with system stability.

Error Tracking

Integrates comprehensive error handling and performance monitoring across services using industry-standard patterns for Sentry, Datadog, and other monitoring solutions.

Agent Smith

Automates financial management by integrating PocketSmith data for transaction categorization, Australian tax tracking, and predictive scenario analysis.

Agent Routing Debugger

Diagnoses and optimizes agent selection logic by analyzing keyword matches, confidence scores, and routing decision trees.

OpenWebF Performance Metrics

Instruments and diagnoses performance bottlenecks in OpenWebF applications within the Flutter ecosystem.

Claude Code Stack Analysis

Audits and optimizes Claude Code primitive structures, ensuring configuration health through deep quality analysis of skills, commands, and hooks.

Distributed Tracing Implementation

Implements end-to-end request tracking across microservices using Jaeger, Tempo, and OpenTelemetry to identify performance bottlenecks and resolve latency issues.

Telemetry Tagging & Production Traceability

Automates the instrumentation of logs, metrics, and distributed traces with requirement IDs to enable end-to-end production observability.

Risk Assessment

Evaluates portfolio risk, market volatility, and position sizing using a multi-perspective debate system to ensure safe trade execution.

Prometheus Configuration & Monitoring

Configures Prometheus for comprehensive metric collection, alerting, and observability across infrastructure and applications.

Debugging Strategies & Root Cause Analysis

Master systematic debugging techniques and profiling tools to efficiently resolve bugs and performance issues across any technology stack.

Grafana Dashboard Expert

Builds and manages production-ready Grafana dashboards for real-time observability and metric visualization.

Python Performance Optimization

Profiles and optimizes Python codebases to eliminate execution bottlenecks and reduce resource consumption.

Distributed Tracing

Implements end-to-end request tracking across microservices using Jaeger and Tempo to identify performance bottlenecks and system dependencies.

Grafana Dashboards

Create and manage production-ready Grafana dashboards for real-time visualization of system, infrastructure, and application metrics.

SLO Implementation Framework

Defines and implements Service Level Indicators (SLIs) and Service Level Objectives (SLOs) with error budgets and automated alerting.

Issue Review Agent

Orchestrates a specialized multi-agent workflow to perform systematic root-cause analysis and debugging for software issues.

Claude Code Administration & ROI

Monitors usage, tracks API costs, and measures the ROI of Claude Code using OpenTelemetry metrics and observability tools.

Sentry and OpenTelemetry Setup

Configures comprehensive error tracking and performance monitoring for Next.js applications using Sentry and OpenTelemetry.

Datadog Auto-Detector

Automatically detects and analyzes Datadog resource mentions to provide real-time observability context within your workflow.

Coherence Check

Ensures methodological and philosophical alignment in qualitative research by auditing language, analytical decisions, and AI interaction patterns.