Monitoring Error Rates
About
This skill enables Claude to monitor and analyze application error rates to improve reliability. It tracks various error types—including HTTP errors, application exceptions, and database errors—and sets up comprehensive monitoring with alerting based on defined thresholds. Use it when you need to "monitor errors," "analyze error rates," or establish proactive error tracking for your application.
Quick Install
Claude Code
Recommended/plugin add https://github.com/jeremylongshore/claude-code-plugins-plusgit clone https://github.com/jeremylongshore/claude-code-plugins-plus.git ~/.claude/skills/Monitoring Error RatesCopy and paste this command in Claude Code to install this skill
Documentation
Overview
This skill automates the process of setting up comprehensive error monitoring and alerting for various components of an application. It helps identify, track, and analyze different types of errors, enabling proactive identification and resolution of issues before they impact users.
How It Works
- Analyze Error Sources: Identifies potential error sources within the application architecture, including HTTP endpoints, database queries, external APIs, background jobs, and client-side code.
- Define Monitoring Criteria: Establishes specific error types and thresholds for each source, such as HTTP status codes (4xx, 5xx), exception types, query timeouts, and API response failures.
- Configure Alerting: Sets up alerts to trigger when error rates exceed defined thresholds, notifying relevant teams or individuals for investigation and remediation.
When to Use This Skill
This skill activates when you need to:
- Set up error monitoring for a new application.
- Analyze existing error rates and identify areas for improvement.
- Configure alerts to be notified of critical errors in real-time.
- Establish error budgets and track progress towards reliability goals.
Examples
Example 1: Setting up Error Monitoring for a Web Application
User request: "Monitor errors in my web application, especially 500 errors and database connection issues."
The skill will:
- Analyze the web application's architecture to identify potential error sources (e.g., HTTP endpoints, database connections).
- Configure monitoring for 500 errors and database connection failures, setting appropriate thresholds and alerts.
Example 2: Analyzing Error Rates in a Background Job Processor
User request: "Analyze error rates for my background job processor. I'm seeing a lot of failed jobs."
The skill will:
- Focus on the background job processor and identify the types of errors occurring (e.g., task failures, timeouts, resource exhaustion).
- Analyze the frequency and patterns of these errors to identify potential root causes.
Best Practices
- Granularity: Monitor errors at a granular level to identify specific problem areas.
- Thresholding: Set appropriate alert thresholds to avoid alert fatigue and focus on critical issues.
- Context: Include relevant context in error messages and alerts to facilitate troubleshooting.
Integration
This skill can be integrated with other monitoring and alerting tools, such as Prometheus, Grafana, and PagerDuty, to provide a comprehensive view of application health and performance. It can also be used in conjunction with incident management tools to streamline incident response workflows.
GitHub Repository
Related Skills
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
evaluating-llms-harness
TestingThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
content-collections
MetaThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
llamaguard
OtherLlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.