Skip to content
Get packs

Axiom Alerting

Set up and tune Axiom monitors and notification channels through the Axiom API

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

What it does

This skill teaches an AI agent how to create, test, and maintain alerts in Axiom, a logging and monitoring service. Once installed, the agent can set up notification destinations such as email, Slack, or a custom webhook, then build monitors that watch query results and notify those destinations when something looks wrong. It also guides the agent to check monitor history and adjust thresholds until alerts behave sensibly.

Great for

  • Engineers who run Axiom and want an agent to set up alerts without clicking through the console
  • On-call or SRE teams who want consistent, repeatable alert configurations
  • Teams tuning noisy alerts who want the agent to check history and iterate on thresholds

Skip it if

  • People without an Axiom account or API token, since every operation requires one
  • Anyone who wants to change production alerting without review, because the scripts can create, update, and delete live monitors and notifiers
  • Users of other monitoring tools, since this is specific to Axiom's v2 API

Try asking

  • “Create an email notifier for the oncall address and attach it to a new monitor that fires when 5xx errors exceed 100 in five minutes”
  • “Review the existing monitors in my Axiom prod deployment and tell me which ones have been firing constantly”
  • “Check the last 24 hours of history for monitor 1234 and suggest threshold changes to reduce noise”
  • “Set up a Slack notifier and a MatchEvent monitor for error-level log lines”
Step-by-step guide: how to use Axiom AlertingInstall, 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.

    axiom-alerting.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip axiom-alerting.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip axiom-alerting.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

  • Test with a non-production deployment first, and review monitor JSON before running create, update, or delete scripts
  • Keep the API token in ~/.axiom.toml with restricted permissions and scope it to only the monitor and notifier actions needed
  • Use monitor-history over a realistic time window before trusting a new alert, and prefer explicit bin() over bin_auto() in queries

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.