Skip to content
Get packs

Arize AX Tracing Setup

Adds Arize AX LLM tracing to an app in two phases: analyze first, then instrument after your approval.

Source Download skill
Repository
github/awesome-copilot
Stars
40,703
Licence
MIT
Files
2 files

What it does

When installed, the agent can add Arize AX observability to an LLM application you already have. It first reads your codebase without changing anything, summarizes the language, LLM providers, and frameworks it found, and waits for your confirmation before adding tracing code. It prefers the framework's built-in integration and uses environment variables instead of hardcoded API keys.

Great for

  • Developers who want to see LLM calls, tool use, and traces of an app in Arize AX for the first time
  • Teams with Python, TypeScript/JavaScript, Java, or Go LLM apps that need OpenTelemetry-based tracing
  • Monorepo owners who want the agent to ask which service to instrument before editing anything

Skip it if

  • Apps that already have a working tracing setup you do not want touched, since the skill checks for existing OTel config but may still add code
  • Projects without an Arize AX account, because the setup depends on Arize credentials and space or project IDs
  • Anyone expecting a purely offline tool: the instructions point to arize.com docs, which the agent may fetch

Try asking

  • “Follow the Arize setup prompt and instrument my Python LangChain app with tracing”
  • “Add OpenTelemetry tracing with openinference to my TypeScript service”
  • “Analyze my codebase first and tell me what Arize tracing integrations I need before changing anything”
  • “Add manual TOOL spans so each tool call in my agent loop shows its input and output”
Step-by-step guide: how to use Arize AX Tracing SetupInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    arize-instrumentation.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip arize-instrumentation.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip arize-instrumentation.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Say which service to instrument up front so the agent does not have to ask about scope in a monorepo
  • Review the Phase 1 summary before confirming, especially the list of proposed integrations and any existing tracing it found
  • Keep credentials in your own environment; the skill says the agent should never print raw secret values, but check generated code anyway

What's inside

  • references/ax-profiles.md
  • SKILL.md

Redistributed unmodified from github/awesome-copilot under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.