Skip to content
Get packs

Root Cause Analysis

Investigate incidents and recurring failures with Five Whys, fishbone, fault trees and blameless postmortems.

Source Download skill
Repository
danielmiessler/LifeOS
Stars
19,682
Licence
MIT
Files
8 files

What it does

When installed, the agent approaches a failure as an investigation rather than a quick guess. It picks a structured method suited to the problem (such as asking 'why' repeatedly, sorting causes into categories, building a fault tree, or writing a blameless postmortem) and works from the evidence you supply. It aims to name systemic causes rather than blaming a person, and it is meant to flag gaps in evidence rather than invent explanations.

Great for

  • Engineers writing postmortems after a production outage or security incident
  • Teams trying to stop a bug or failure that keeps coming back
  • Anyone who wants a structured, evidence-based way to analyse why something went wrong

Skip it if

  • Feedback loops or long-term structural patterns, which the skill says should go to a separate SystemsThinking skill, since this one is not built for them
  • Urgent live incidents where the answer is needed right now, because a full analysis takes time and evidence gathering
  • Decisions that rely on facts the agent cannot check, since the skill itself warns that unsupported conclusions should be marked as gaps or hypotheses rather than treated as proven

Try asking

  • “Write a blameless postmortem for last night's payment API errors after the deploy.”
  • “5 whys on why the nightly backup keeps missing its window.”
  • “The export job fails only on the EU cluster. Use Kepner-Tregoe to find what is different.”
  • “Build a fishbone diagram of the causes behind our rising customer support ticket volume.”
Step-by-step guide: how to use Root Cause AnalysisInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 8 original files, the MIT licence and an attribution note.

    RootCauseAnalysis.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

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

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip RootCauseAnalysis.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

  • Give the agent concrete evidence such as log excerpts, timestamps, deploy records and what changed, since conclusions are meant to cite supplied facts.
  • State your own hypotheses as hypotheses; the skill is designed not to treat them as facts.
  • Name the failure class (single failure point, multi-path, subtle defect, outage) so the agent can pick the right method.

What's inside

  • Foundation.md
  • Intents/FaultTree.md
  • Intents/Fishbone.md
  • Intents/FiveWhys.md
  • Intents/KepnerTregoe.md
  • Intents/Postmortem.md
  • MethodSelection.md
  • SKILL.md

Redistributed unmodified from danielmiessler/LifeOS 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.