Analytics & Monitoring Claudeスキル

Workflow Event Emitter

Emits structured, searchable workflow events to provide cross-project visibility and execution tracking.

Log Analyzer

Extracts actionable insights, patterns, and errors from operational logs using type-specific analysis templates.

Cloud Infrastructure Monitor

Monitors and analyzes the health, performance, and metrics of deployed cloud infrastructure to prevent incidents and optimize resource usage.

Agent Chain Analyzer

Detects and analyzes inefficient agent chain anti-patterns to optimize context usage and architectural performance.

Performance Budget Checker

Analyzes code for performance bottlenecks and anti-patterns like N+1 queries and nested loops to ensure high-performance production releases.

Systematic Debugging Strategies

Master professional root cause analysis and profiling techniques to solve complex software bugs using a scientific methodology.

Python Performance Optimization

Profiles and optimizes Python code to eliminate bottlenecks, reduce memory usage, and improve application execution speed.

SLO Implementation & SRE Framework

Defines and implements Service Level Indicators (SLIs) and Service Level Objectives (SLOs) to establish measurable reliability targets.

Grafana Dashboard Architect

Generates and manages production-ready Grafana dashboards for real-time system observability and metrics visualization.

Distributed Tracing for Microservices

Implements distributed tracing with Jaeger and Tempo to track requests across microservices and identify performance bottlenecks.

Prometheus Configuration

Configures and optimizes Prometheus for robust metric collection, alerting, and observability across diverse infrastructure and applications.

Log Summarizer

Generates structured Markdown summaries of Claude Code session logs to capture technical decisions, accomplishments, and file changes.

Distributed Tracing Implementation

Implements comprehensive distributed tracing using Jaeger and Tempo to monitor request flows and resolve performance bottlenecks in microservices.

Dual-Channel Watchexec Notifications

Automates multi-channel alerts via Telegram and Pushover for watchexec events and process restarts.

Prometheus Configuration

Configures Prometheus for comprehensive metric collection, alerting, and infrastructure monitoring.

Grafana Dashboards

Generates and manages production-grade Grafana dashboards for real-time observability of system and application metrics.

Earnings Calendar

Generates structured weekly earnings reports for US stocks with market caps over $2B using real-time Financial Modeling Prep data.

Debugging Strategies

Master systematic debugging techniques and root cause analysis to efficiently resolve bugs and performance issues across any tech stack.

Market News Analyst

Analyzes financial news events from the past 10 days to evaluate their impact on global equity markets, commodities, and interest rate regimes.

SLO Implementation Framework

Defines and implements measurable reliability targets using Service Level Indicators (SLIs) and Service Level Objectives (SLOs).

Error Tracking

Implements comprehensive Sentry v8 error tracking and performance monitoring across project services to ensure no error goes unrecorded.

Dividend Growth Pullback Screener

Identifies high-quality dividend growth stocks experiencing temporary price pullbacks to find optimal long-term investment entry points.

Structured Log Writer

Automates the creation of standardized, validated log files using type-specific templates and automatic sensitive data redaction.

Layer Cake Svelte Visualization

Simplifies data visualization in Svelte by managing scales, coordinate systems, and responsive dimensions across SVG, Canvas, and HTML contexts.

Retention Optimization Expert

Reduces user churn and improves long-term retention through detailed cohort analysis, predictive health scoring, and actionable win-back strategies.

Performance Optimizer

Analyzes and optimizes parallel development workflows to maximize execution speed and minimize operational costs.

Gemini JSON Parser

Parses and extracts data from Gemini CLI programmatic output, including token usage, tool call statistics, and stream-JSON events.

Standard Out Setup

Implements critical console logging and error visibility to ensure AI agents can observe application state and self-correct.

Performance Optimization

Optimizes backend application performance using advanced caching, load balancing, and database scaling strategies.

Mazza Loki Logging Configuration

Configures Grafana Loki logging for Python and Flask applications using the mazza-base library for structured observability.