skills.rest
mguinada
mguinadaCOMMUNITY
Explore all skills by this author →
GitHub

phoenix-observability

Trace, evaluate, and monitor LLM applications with OpenTelemetry instrumentation.

Updated Feb 5, 2026
Search Tags:#monitoring#llm#evaluation#observability#tracing#opentelemetry
One-click install
npx skills add https://github.com/mguinada/ai-coding-toolkit --skill phoenix-observability-mguinada
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: phoenix-observability
Source: https://github.com/mguinada/ai-coding-toolkit/tree/main/skills/phoenix-observability
Command: npx skills add https://github.com/mguinada/ai-coding-toolkit --skill phoenix-observability-mguinada

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Open-source AI observability platform that provides end-to-end tracing, evaluation, and monitoring for LLM applications, enabling developers to debug, validate, and optimize AI pipelines.

Core Features & Use Cases

  • Tracing: OpenTelemetry-based trace collection for LLM frameworks and agent deployments
  • Evaluation: LLM-as-judge evaluators and dataset-driven monitoring
  • Monitoring & Instrumentation: Open-source, self-hosted observability with alerts, dashboards, and instrumentation patterns

Quick Start

Install Phoenix observability packages and initialize the Phoenix tracer in your application to begin collecting traces, evaluations, and metrics.

Frequently Asked Questions about phoenix-observability

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up LLM tracing for my AI application?▼

Set up LLM tracing by installing Phoenix observability packages and initializing the tracer in your application to collect end-to-end OpenTelemetry traces for your agent frameworks.

What is OpenTelemetry-based observability for LLM pipelines?▼

OpenTelemetry-based observability for LLM pipelines is the process of collecting end-to-end traces, evaluations, and metrics to debug, validate, and optimize AI deployments.

Can I run LLM evaluation workflows using datasets?▼

Yes, you can run LLM evaluation workflows using dataset-driven monitoring and LLM-as-judge evaluators to validate and optimize your AI pipelines.

Does this observability platform support self-hosted deployment?▼

Yes, the observability platform supports open-source, self-hosted deployment configurations, allowing you to securely run tracing and monitoring within your own infrastructure.

What's the best way to debug LLM agent performance issues?▼

Debug LLM agent performance issues by instrumenting your agent frameworks with OpenTelemetry, collecting end-to-end traces, and analyzing metrics via dashboards and alerts.

When do I need end-to-end tracing for LLM applications?▼

You need end-to-end tracing for LLM applications during debugging, performance monitoring, and production assessments to validate AI pipelines and identify bottlenecks.

Related Skills

Explore More Software Engineering Skills→
WrongStackWrongStack
224

observability

Instrument WrongStack applications with structured logs, traces, and metrics.

Official
Advanced
therealbilltherealbill
3

monitoring-setup

Configure Prometheus scrapes, Grafana dashboards, and Alertmanager rules for Temporal clusters.

Community
Advanced
jxtngxjxtngx
2

langsmith-evaluator

Create and deploy LLM agent evaluation pipelines within the LangSmith ecosystem.

Community
Advanced
OpenLAIROpenLAIR
1.0k

phoenix-observability

Trace, evaluate, and monitor LLM applications with OpenTelemetry and self-hosted storage.

Official
Advanced