Analytics & Monitoring Claude 技能

Claude Code Session Data Extractor

Extracts structured metadata, statistics, and interaction logs from Claude Code native session files for auditing and retrospective analysis.

Debugging with Tools

Facilitates systematic, tool-driven code investigation and error resolution through logs, search, and iterative testing.

AI Runtime Toolkit

Manages and integrates internal professional utilities and external CLI tools to extend AI cognitive capabilities through a metadata-driven discovery system.

Observability Fundamentals

Implements industry-standard logging, metrics, and tracing patterns to enhance system reliability and monitoring.

Finance Analyst

Automates financial reporting, revenue analysis, and business forecasting to drive data-informed product decisions.

Skill System Refactor

Audits, evaluates, and refactors Claude Code skill ecosystems through autonomous orchestration and multi-layered analysis.

Feedback Collector

Systematically gathers, categorizes, and analyzes user feedback to continuously improve AI agent performance and development workflows.

Billing Reporter

Analyzes LimaCharlie billing and usage data to identify cost drivers, track trends, and provide actionable optimization insights.

Guardian Quality Monitor

Monitors session health and automates code quality gates by spawning focused review agents when degradation or complexity thresholds are met.

Context Manager

Optimizes Claude Code performance and token usage through strategic file loading, budget monitoring, and efficient query patterns.

Plan Guardian

Monitors active development in real-time to detect and prevent architectural drift and scope creep.

Candidate Profile Summary

Generates detailed markdown reports analyzing candidate demographics, diversity metrics, and geographic distribution from profile data.

Grafana HTTP API

Programmatically manages Grafana resources including dashboards, data sources, alerting, and users via the HTTP API.

AI Runtime Toolkit

Manages and executes a curated collection of internal professional utilities and integrated CLI tools to extend AI cognitive capabilities during development and system operations.

Data Pipeline Monitoring

Monitor and troubleshoot dual-pipeline data collection systems on Google Cloud Platform to ensure reliable blockchain network metrics.

Project Dashboard

Visualizes progress and reports status for qualitative research projects following the sandwich methodology.

Datadog CLI

Triage incidents and debug applications by querying Datadog logs, metrics, and traces directly from your terminal.

GCP Cost Analysis

Analyzes and visualizes Google Cloud Platform spending from L'Oréal's BTDP infrastructure through automated BigQuery queries and custom spreadsheet exports.

Grafana Dashboard Architect

Builds and manages production-ready Grafana dashboards for real-time system observability and performance monitoring.

Distributed Tracing Implementation

Implements distributed tracing across microservices using Jaeger and Tempo to identify performance bottlenecks and visualize request flows.

Prometheus Configuration

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

SLO Implementation & SRE Framework

Defines and implements Service Level Indicators (SLIs) and Service Level Objectives (SLOs) with error budgets to ensure system reliability.

Python Performance Optimization

Profiles and optimizes Python codebases using advanced diagnostic tools and proven efficiency patterns.

SLO Implementation & Monitoring

Defines and implements Service Level Indicators (SLIs) and Objectives (SLOs) to measure and maintain service reliability.

Distributed Tracing Implementation

Implements end-to-end request tracing across microservices using OpenTelemetry, Jaeger, and Tempo for deep observability.

Prometheus Configuration & Monitoring

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

Grafana Dashboard Management

Generates and manages production-grade Grafana dashboards for real-time system observability and metric visualization.

Python Performance Optimization

Identifies and resolves performance bottlenecks in Python code using advanced profiling tools and high-efficiency implementation patterns.

Distributed Tracing & Observability

Implements end-to-end request tracking across microservices using Jaeger and Tempo to identify performance bottlenecks and debug complex distributed systems.

SLO & Reliability Implementation

Defines and implements measurable service level objectives and error budgets to optimize system reliability and engineering velocity.