Skip to content
Get packs

Axiom SRE Incident Investigator

Guides hypothesis-driven incident triage and root-cause analysis using logs, metrics, and traces

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

What it does

When installed, the agent works like a disciplined site reliability engineer during outages or production bugs. It first tries to stop the damage (for example by recommending a rollback), then forms hypotheses and checks them against real data from observability tools such as Axiom, Grafana, Pyroscope, Kubernetes, and Slack, rather than guessing. It is instructed to discover available datasets and names before querying, and to keep secrets out of visible commands by routing authenticated requests through a helper script.

Great for

  • On-call engineers handling a live production incident who want a structured triage process
  • Developers doing root-cause analysis on logs or performance problems in a team that already uses Axiom or Grafana
  • Teams that want consistent postmortems using the included template

Skip it if

  • Teams without any configured observability tools, since the skill's main value depends on querying real data and it will only prompt for setup
  • Anyone wanting a fully autonomous fix: it runs shell scripts and queries live systems, so changes should be reviewed by a human first

Try asking

  • “Our checkout API error rate spiked at 14:30 UTC. Help me triage and find the root cause.”
  • “Investigate why p99 latency on orders-api doubled after yesterday's deploy.”
  • “Write a blameless postmortem for last night's database outage using our template.”
  • “Help me debug unexpected 500 errors by checking logs in our prod Axiom datasets.”
Step-by-step guide: how to use Axiom SRE Incident InvestigatorInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the MIT licence and an attribution note.

    axiom-sre.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

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

    Claude Code / Agent SDK (this project only)

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

  • Run the init script first and add at least one tool to the config; the skill will guide you through it
  • Give the agent a concrete time window and service name so it can discover the right datasets quickly
  • Review the scripts and the config file before first use, and use read-only credentials for observability tools

What's inside

  • README.md
  • reference/api-capabilities.md
  • reference/api-methods.md
  • reference/apl-functions.md
  • reference/apl-operators.md
  • reference/apl.md
  • reference/axiom.md
  • reference/blocks.md
  • reference/failure-modes.md
  • reference/grafana.md
  • reference/memory-system.md
  • reference/metrics.md
  • reference/postmortem-template.md
  • reference/pyroscope.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.