本文へ移動
cccskills
無料GitHub で公開

nw-five-whys-methodology

Toyota 5 Whys methodology with multi-causal branching, evidence requirements, and validation techniques

インストール方法を見る

含まれるファイル(1)

  • SKILL.md3.1 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Five Whys Methodology

Philosophical Foundation

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

Multi-Causal Investigation

Complex problems have multiple root causes. Investigate comprehensively:

  • Parallel: investigate all symptoms/conditions simultaneously
  • Branch: follow each cause through all five WHY levels
  • Cross-cause: ensure multiple causes don't contradict
  • Comprehensive: address all root causes, not just primary

WHY Level Definitions

WHY 1: Symptom Investigation

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 2: Context Analysis

Why does this condition exist? Follow each WHY 1 through context. Check if factors connect multiple causes. Examine system/environment/operational context.

WHY 3: System Analysis

Why do conditions persist? How system enables multiple failure modes. How causes interact systemically. Analyze design/architecture decisions.

WHY 4: Design Analysis

Why not anticipated? Review design assumptions. Identify all design blind spots. Trace decisions to original context.

WHY 5: Root Cause Identification

Fundamental causes. Multiple root causes expected for complex issues. Ensure all contributing causes identified. Focus on deepest level.

Validation and Verification

Evidence Requirements

Each WHY level must have verifiable evidence for all causes. Root causes must explain all symptoms collectively. Solutions must address all root causes.

Backwards Chain Validation

  1. Trace each root cause forward to symptom | 2. "If this exists, would it produce this symptom?" = must be yes
  2. Cross-validate: multiple roots must not contradict | 4. Completeness: "Missing contributing factors?" at each level

Solution Completeness

Every root cause -> corresponding solution | Prevent recurrence, not just mitigate | Use findings for system improvement

Branch Documentation Format

PROBLEM: [clear problem statement]

WHY 1A: [symptom] [Evidence: ...]
  WHY 2A: [context] [Evidence: ...]
    WHY 3A: [system factor] [Evidence: ...]
      WHY 4A: [design factor] [Evidence: ...]
        WHY 5A: [root cause] [Evidence: ...]
        -> ROOT CAUSE A: [fundamental cause]
        -> SOLUTION A: [prevention strategy]

WHY 1B: [symptom] [Evidence: ...]
  WHY 2B: [context] [Evidence: ...]
    ...

CROSS-VALIDATION:
- Root Cause A + Root Cause B: [consistent/contradictory]
- All symptoms explained: [yes/no, gaps if any]

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation

日本語の概要は準備中です。原文の説明を表示しています。

nWave-ai/nWave6162026年9月16日 更新

Review dimensions for validating agent quality - template compliance, safety, testing, and priority validation

日本語の概要は準備中です。原文の説明を表示しています。

nWave-ai/nWave6162026年9月16日 更新

Review dimensions for acceptance test quality - happy path bias, GWT compliance, business language purity, coverage completeness, walking skeleton user-centricity, priority validation, observable behavior assertions, traceability coverage, and walking skeleton boundary proof

日本語の概要は準備中です。原文の説明を表示しています。

nWave-ai/nWave6162026年9月16日 更新

Detailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinement

日本語の概要は準備中です。原文の説明を表示しています。

nWave-ai/nWave6162026年9月16日 更新

5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance

日本語の概要は準備中です。原文の説明を表示しています。

nWave-ai/nWave6162026年9月16日 更新

Architectural style selection decision matrices, trade-off analysis, structural enforcement rules, and combination patterns. Load when choosing or evaluating architecture styles.

日本語の概要は準備中です。原文の説明を表示しています。

nWave-ai/nWave6162026年9月16日 更新

nWave-ai のスキルをすべて見る

このスキルの問題を報告する