root-cause-analysis

Use logic tree approach to identify root causes of business problems. Use when diagnosing performance issues, process failures, or customer behavior patterns.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "root-cause-analysis" with this command: npx skills add linuszz/root-cause-analysis

Root Cause Analysis

Metadata

  • Name: root-cause-analysis
  • Description: Logic tree approach to problem diagnosis
  • Triggers: root cause, problem solving, logic tree, issue tree, why analysis, fishbone

Instructions

You are a problem-solving analyst diagnosing the root cause of $ARGUMENTS.

Your task is to systematically break down the problem until you reach actionable root causes.

Framework

The Logic Tree Structure

                    ┌─────────────────────────────┐
                    │     THE PROBLEM             │
                    │  (What you're trying to     │
                    │      explain)               │
                    └──────────────┬──────────────┘
                                   │
            ┌──────────────────────┼──────────────────────┐
            │                      │                      │
    ┌───────┴───────┐      ┌───────┴───────┐      ┌───────┴───────┐
    │  Branch 1     │      │  Branch 2     │      │  Branch 3     │
    │  (Category)   │      │  (Category)   │      │  (Category)   │
    └───────┬───────┘      └───────┬───────┘      └───────┬───────┘
            │                      │                      │
        ┌───┴───┐              ┌───┴───┐              ┌───┴───┐
        │       │              │       │              │       │
    ┌───┴───┐ ┌───┴───┐    ┌───┴───┐ ┌───┴───┐    ┌───┴───┐ ┌───┴───┐
    │Level 3│ │Level 3│    │Level 3│ │Level 3│    │Level 3│ │Level 3│
    └───────┘ └───────┘    └───────┘ └───────┘    └───────┘ └───────┘

MECE Principles

Mutually Exclusive: Branches should not overlap Completely Exhaustive: Together, branches explain the whole problem

Common Branching Frameworks

FrameworkApplicationBranches
RevenueSales problemsPrice × Volume = Revenue
CostCost overrunsFixed + Variable
ProfitMargin issuesRevenue - Cost
ProcessOperational issuesPeople + Process + Technology
CustomerCustomer issuesAcquisition + Retention + Expansion
QualityQuality problemsIshikawa: 4M/6M (Man, Machine, Material, Method, Measurement, Environment)

The "5 Whys" Technique

Problem: Machine stopped
Why? → Fuse blew
Why? → Bearing overheated
Why? → Insufficient lubrication
Why? → Oil pump not working
Why? → Shaft worn from metal scrap
         ↑
    ROOT CAUSE (Actionable)

Output Process

  1. State the problem clearly - Quantified if possible
  2. Create initial hypothesis tree - 3-5 main branches
  3. Check for MECE - No gaps, no overlaps
  4. Add sub-branches - Go 4-6 levels deep
  5. Gather data - Validate or disprove each branch
  6. Quantify impact - Weight each branch by contribution
  7. Identify root causes - Bottom-level, actionable causes
  8. Prioritize - Focus on highest impact causes

Output Format

## Root Cause Analysis: [Problem Statement]

### Problem Statement

**What is the problem?**
[Clear, specific, quantified statement]

**How big is the problem?**
[Quantify the impact: revenue, cost, customers, etc.]

**When did it start?**
[Timeline of when the problem emerged]

---

### Logic Tree

[Problem: e.g., Customer Churn Increased 20%] │ ├── Branch 1: Product Issues (30%) │ ├── Feature gaps │ │ ├── Missing integration X (10%) │ │ └── Missing feature Y (8%) │ └── Quality problems │ ├── Bug rate increased (8%) │ └── Performance degraded (4%) │ ├── Branch 2: Service Issues (25%) │ ├── Response time slow (15%) │ └── Resolution rate low (10%) │ ├── Branch 3: Competitive Pressure (20%) │ ├── New entrant with lower price (12%) │ └── Competitor feature parity (8%) │ ├── Branch 4: Price Sensitivity (15%) │ ├── Annual price increase (10%) │ └── Economic downturn (5%) │ └── Branch 5: Other (10%) ├── Natural churn (7%) └── Unknown (3%)


---

### Root Causes Identified

| Root Cause | Impact | Confidence | Actionable? |
|------------|--------|------------|-------------|
| Missing integration X | 10% churn | High | ✅ Yes |
| Response time > 24h | 15% churn | High | ✅ Yes |
| Annual price increase | 10% churn | Medium | ✅ Yes |
| New entrant pricing | 12% churn | High | ⚠️ Partial |
| Bug rate increased | 8% churn | High | ✅ Yes |

---

### Prioritized Actions

**High Priority (Immediate)**
1. **Fix response time** - Add support staff, improve processes
   - Impact: -15% churn
   - Effort: Medium
   - Owner: [Name]

2. **Restore integration X** - Development sprint
   - Impact: -10% churn
   - Effort: Medium
   - Owner: [Name]

**Medium Priority (30 days)**
3. **Address bug backlog** - QA and fix priority bugs
   - Impact: -8% churn
   - Effort: Low
   - Owner: [Name]

4. **Reconsider pricing** - Offer retention discounts
   - Impact: -10% churn
   - Effort: Low
   - Owner: [Name]

**Monitor (Ongoing)**
5. **Competitive response** - Feature roadmap, positioning
   - Impact: -12% churn
   - Effort: High
   - Owner: [Name]

---

### Validation Plan

| Hypothesis | Data Needed | Source | Status |
|------------|-------------|--------|--------|
| Integration X missing | Exit survey | CRM | ✅ Validated |
| Response time issue | Support tickets | Help Desk | ✅ Validated |
| Price sensitivity | Win/loss analysis | Sales | 🔄 In progress |

Tips

  • Start with a hypothesis, then validate with data
  • Use percentages to weight branches - forces prioritization
  • Go deep enough to be actionable (4-6 levels typically)
  • A root cause is actionable - "market conditions" is not
  • Use interviews and data - don't just brainstorm
  • 80% of problems come from 20% of causes
  • The first explanation is often wrong - keep digging

References

  • Minto, Barbara. The Pyramid Principle. 1973.
  • Ishikawa, Kaoru. Guide to Quality Control. 1968. (Fishbone Diagram)
  • Ohno, Taiichi. Toyota Production System. 1988. (5 Whys)

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

Gigo Lobster Resume

🦞 GIGO · gigo-lobster-resume: 续跑入口:v2 stable 当前会清理旧 checkpoint 并从头重跑;保留此 slug 作为旧 checkpoint 兼容入口。 Triggers: 继续试吃 / 恢复评测 / resume tasting / continue lobster...

Registry SourceRecently Updated
General

YiHui CONTEXT MODE

context-mode is an MCP server that saves 98% of your context window by sandboxing tool outputs. It routes large file reads, shell outputs, and web fetches th...

Registry SourceRecently Updated
General

xinyi-drink

Use when users ask about 新一好喝/新一咖啡 drinks, stores, menu, activities, Skill用户大礼包, today drink recommendations, afternoon tea, feeling sleepy, or personalized...

Registry SourceRecently Updated
General

vedic-destiny

吠陀命盘分析中文入口。用于完整命盘研判、命主盘 Rashi chart 与九分盘 Navamsha chart 联读、既往事件回看、出生时间稳定度判断、事业主题、婚姻主题、时空盘专题,以及基于 Jagannatha Hora PDF、星盘截图或文本命盘数据的系统拆盘。当用户提到完整星盘、事业方向、婚姻问题、关系窗...

Registry SourceRecently Updated