Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nwave-ai/nw-five-whys-methodology
Toyota 5 Whys methodology with multi-causal branching, evidence requirements, and validation techniques
Passed 19 of 22 test cases with the skill, and 18 of 22 without it.
and 1 more in the full report
4 fixed15 passed either way0 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
A web application experienced elevated latency and corrupted session cookies following a rolling deployment. Document the initial level 1 analysis for both symptoms, capturing immediate observable facts without jumping to conclusions.
| Checked | Without skill | With skill |
|---|---|---|
| Level 1 defines distinct symptom branches WHY 1A and WHY 1B. | Missed | Passed |
| Each branch records immediate observable telemetry evidence. | Passed | Passed |
The instructions your model reads when the skill loads.
Taiichi Ohno: "By repeating why five times, the nature of the problem as well as its solution becomes clear."
Core tenets: scientific evidence-based investigation | address fundamental causes not symptoms | solve to prevent recurrence | use findings for Kaizen
Complex problems have multiple root causes. Investigate comprehensively:
What is immediately observable? Investigate all symptoms. Each branch continues independently. Document verifiable evidence per symptom.
WHY 1A: Path not found [Evidence: file exists but wrong context -- Windows vs WSL paths]
WHY 1B: Permission denied [Evidence: user context mismatch between host and container]
WHY 1C: Timing issues [Evidence: race conditions with file system operations]
Why does this condition exist? Follow each WHY 1 through context. Check if factors connect multiple causes. Examine system/environment/operational context.
Why do conditions persist? How system enables multiple failure modes. How causes interact systemically. Analyze design/architecture decisions.
Why not anticipated? Review design assumptions. Identify all design blind spots. Trace decisions to original context.
Fundamental causes. Multiple root causes expected for complex issues. Ensure all contributing causes identified. Focus on deepest level.
test cases passed, vs 18 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.