Skip to main content
The Query metrics skill turns AI agents into metrics exploration experts:
  • Metrics query specification: Self-describing query endpoint that teaches the agent how to write metrics queries on demand
  • Metrics discovery: Explore available metrics, tags, and tag values in any OTel metrics dataset
  • Query execution: Compose and run metrics queries with filtering, aggregation, and grouping
  • Error handling: Structured error reporting with trace IDs for backend debugging

​
Prerequisites

The target dataset must be an OTel metrics dataset.

​
Install Query metrics skill

Choose one of the following ways to install the Query metrics skill:
Install all Axiom skills at once for Claude Code, Cursor, and other Claude-compatible agents:
npx skills add axiomhq/skills

​
Configure Axiom credentials

All Axiom Skills share the same credential configuration. Create a configuration file at ~/.axiom.toml:
~/.axiom.toml
[deployments.dev]
url = "https://api.axiom.co"
token = "API_TOKEN"
org_id = "ORGANIZATION_ID"
edge_url = "AXIOM_DOMAIN"
Replace API_TOKEN with the Axiom API token you have generated. For added security, store the API token in an environment variable.Replace ORGANIZATION_ID with your organization ID. For more information, see Determine organization ID.Replace AXIOM_DOMAIN with the base domain of your edge deployment. For more information, see Edge deployments.For token creation and scoping guidance, see Token hygiene for AI agents.

​
Use Query metrics skill

The Query metrics skill activates automatically when you ask your AI agent to:
  • Query metrics data from Axiom MetricsDB
  • Explore available metrics, tags, and tag values in a dataset
  • Investigate OTel metrics data
  • Check metric values for debugging or monitoring
Example prompts:
  • “Query the CPU usage metric from the app.metrics dataset”
  • “What metrics are available in the dataset?”
  • “Show the tag values for the service.name tag”
  • “Find metrics related to HTTP requests”

​
How it works

The Query metrics skill uses a structured workflow:
  1. Learn the query specification: The agent calls the self-describing query endpoint to fetch the full metrics query specification.
  2. Discover metrics: The agent searches for metrics matching relevant terms or lists available metrics in the target dataset using the discovery endpoints.
  3. Explore tags: The agent lists tags and tag values to understand the available filtering options.
  4. Write and execute query: The agent composes a metrics query and runs it against MetricsDB.
  5. Iterate: The agent refines filters, aggregations, and groupings based on results.