Skip to content
Get packs

Query Axiom Metrics

Lets an agent explore and query Axiom MetricsDB OpenTelemetry metrics using MPL.

Source Download skill
Repository
openclaw/clawhub
Stars
9,546
Licence
MIT
Files
2 files

What it does

Once installed, the agent can list metric datasets, discover metric names, tags and tag values, and run MPL (Metrics Pipeline Language) queries against Axiom's metrics database through bundled scripts. It is taught to read each metric's type, temporality and unit before writing a query, so it picks sensible aggregations such as rates for cumulative counters and quantiles for histograms.

Great for

  • Engineers who monitor services in Axiom and want to ask questions in plain language
  • Site reliability or observability staff investigating OpenTelemetry metrics data
  • Anyone who already has an Axiom account and a configured ~/.axiom.toml file

Skip it if

  • People without an Axiom account, since the scripts can only query an existing Axiom deployment (no reason to install it)
  • Teams that need to query other metrics backends such as Prometheus, because it only targets Axiom MetricsDB datasets of kind otel:metrics:v1
  • Use on production credentials without review: the scripts run queries that can return large outputs and use stored API access, so review the scripts before granting access

Try asking

  • “Show me the p95 latency of http.server.duration for the frontend service over the last day”
  • “List the metrics datasets available in my prod deployment”
  • “What tag values does the service.name tag have in the otel-metrics dataset?”
  • “Find the metrics that carry the value checkout-api and chart their error rate over the last hour”
Step-by-step guide: how to use Query Axiom MetricsInstall, 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.

    query-metrics.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip query-metrics.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip query-metrics.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

  • Name a deployment from ~/.axiom.toml and a time range such as now-1h so the agent can run queries immediately.
  • Ask the agent to start with plain group using aggregations on high-cardinality tags, since grouping by a tag can return one series per value.
  • Give a chart width with -w so the $__interval step matches the display.

What's inside

  • README.md
  • SKILL.md

Redistributed unmodified from openclaw/clawhub 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.