Root cause analysis
Uncover root causes through recursive Why questioning and consequence exploration. Use before acting on problems.From its SKILL.md
npx -y skills add itseffi/agentic-os --skill root-cause-analysisAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
SKILL.md
1.6 KB, 331 tokens by cl100k_base, as published. Nobody here has run it
Root Cause Analysis
Uncover root causes and explore consequences through structured questioning.
When to Use
When you need to deeply understand a problem, decision, or situation before acting.
The Process
1. Recursive "Why" Questioning
Start with the initial question and ask "Why?" repeatedly:
- Ask "Why?" at least 5 times
- Go deeper until you reach fundamental causes
- If multiple reasons emerge, explore each branch
Example:
- Why did users churn? → Onboarding was confusing
- Why was it confusing? → Too many steps
- Why too many steps? → We added features without simplifying
- Why didn't we simplify? → No ownership of onboarding experience
- Why no ownership? → Org structure doesn't align to user journey
2. Consequence Exploration
After finding root causes, explore forward:
- 1st order: Immediate consequences
- 2nd order: What results from those?
- 3rd-5th order: Downstream effects
Consider both positive and negative outcomes.
3. First Principles Check
- What fundamental truths underlie this?
- What assumptions are we making?
- What alternative perspectives exist?
- Where are the gaps in logic?
Output Format
- Root causes (the "Why?" chain)
- Consequences (1st through 5th order)
- First principles (fundamental truths, assumptions)
- Conclusion (key insights)
When Not to Use
Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.
What ships with it: 1 file
196 B alongside SKILL.md
agents/
- openai.yaml196 B