# Query metrics skill





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 />

<Note>
  The target dataset must be an OTel metrics dataset.
</Note>

<SkillsCredentials />

## Use Query metrics skill [#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 [#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.