Skip to main content
skill CX Codex

six-thinking-hats · proffesor-for-testing — Claude Code skill: testing analysis

Applies Six Thinking Hats to test strategy, failure analysis, and retrospectives. It separates facts, risks, benefits, ideas, feelings, and next actions.

MIT 131 installs ★ 533 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add proffesor-for-testing/agentic-qe --skill six-thinking-hats -a claude-code
Open on GitHub

What six-thinking-hats does

This skill applies Edward de Bono’s Six Thinking Hats to software testing. The White Hat gathers facts and metrics, Red captures team confidence and concerns, Black examines risks and gaps, Yellow identifies strengths, Green creates alternative test ideas, and Blue turns the discussion into an action plan. The result is a structured view of a testing question.

The workflow starts with a specific question, moves through the hats in sequence, records findings, and ends with prioritized actions. The skill includes templates for solo and team sessions, plus agent coordination examples for qe-quality-analyzer, qe-regression-risk-analyzer, and qe-test-generator. Its declared dependency list is empty, while the coordination examples rely on those named subagents.

Use it to review coverage, inspect untested scenarios, compare testing approaches, or plan follow-up work after failures. It structures the reasoning; it does not run tests or supply project metrics on its own.

What it helps with

  • build a test strategy for a feature
  • identify coverage gaps and release risks
  • review the causes of failing tests
  • run a structured testing retrospective
  • turn test findings into prioritized actions

Example prompts for the agent

  • Analyze the payment-module test strategy with all six hats and finish with prioritized actions.
  • Review the new authentication flow from the Black Hat perspective and list the main risks.
  • Generate alternative test ideas for this feature with the Green Hat, then create a Blue Hat action plan.

How to install six-thinking-hats

1Skills CLI (Vercel)

npx skills add proffesor-for-testing/agentic-qe --skill six-thinking-hats -a claude-code

2Manually: put the files in place

~/.claude/skills/six-thinking-hats/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/six-thinking-hats/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about six-thinking-hats

How do I install six-thinking-hats in Claude Code?

Run npx skills add proffesor-for-testing/agentic-qe --skill six-thinking-hats -a claude-code. The skill file will be available at ~/.claude/skills/six-thinking-hats/SKILL.md.

What does six-thinking-hats do?

It structures software testing analysis through six perspectives: facts, emotions, risks, benefits, creative options, and process. The perspectives lead to a documented action plan.

Which subagents are associated with six-thinking-hats?

The skill names qe-quality-analyzer, qe-regression-risk-analyzer, and qe-test-generator. They cover broad analysis, risk review, and test idea generation.

Source text

SKILL.md · MIT
---
name: six-thinking-hats
description: "Apply Edward de Bono's Six Thinking Hats methodology to software testing for comprehensive quality analysis. Use when designing test strategies, conducting test retrospectives, analyzing test failures, evaluating testing approaches, or facilitating testing discussions. Each hat provides a distinct testing perspective: facts (White), risks (Black), benefits (Yellow), creativity (Green), emotions (Red), and process (Blue)."
category: methodology
priority: medium
tokenEstimate: 1100
agents: [qe-quality-analyzer, qe-regression-risk-analyzer, qe-test-generator]
implementation_status: optimized
optimization_version: 1.0
last_optimized: 2025-12-03
dependencies: []
quick_reference_card: true
tags: [thinking, methodology, decision-making, collaboration, analysis]
trust_tier: 0
validation:
---

# Six Thinking Hats for Testing

<default_to_action>
When analyzing testing decisions:
1. DEFINE focus clearly (specific testing question)
2. APPLY each hat sequentially (5 min each)
3. DOCUMENT insights per hat
4. SYNTHESIZE into action plan

**Quick Hat Rotation (30 min):**
```markdown
🤍 WHITE (5 min) - Facts only: metrics, data, coverage
❤️ RED (3 min) - Gut feelings (no justification needed)
🖤 BLACK (7 min) - Risks, gaps, what could go wrong
💛 YELLOW (5 min) - Strengths, opportunities, what works
💚 GREEN (7 min) - Creative ideas, alternatives
🔵 BLUE (3 min) - Action plan, next steps
```

**Example for "API Test Strategy":**
- 🤍 47 endpoints, 30% coverage, 12 integration tests
- ❤️ Anxious about security, confident on happy paths
- 🖤 No auth tests, rate limiting untested, edge cases missing
- 💛 Good docs, CI/CD integrated, team experienced
- 💚 Contract testing with Pact, chaos testing, property-based
- 🔵 Security tests first, contract testing next sprint
</default_to_action>

## Quick Reference Card

### The Six Hats

| Hat | Focus | Key Question |
|-----|-------|--------------|
| 🤍 **White** | Facts & Data | What do we KNOW? |
| ❤️ **Red** | Emotions | What do we FEEL? |
| 🖤 **Black** | Risks | What could go WRONG? |
| 💛 **Yellow** | Benefits | What's GOOD? |
| 💚 **Green** | Creativity | What ELSE could we try? |
| 🔵 **Blue** | Process | What should we DO? |

### When to Use Each Hat

| Hat | Use For |
|-----|---------|
| 🤍 White | Baseline metrics, test data inventory |
| ❤️ Red | Team confidence check, quality gut feel |
| 🖤 Black | Risk assessment, gap analysis, pre-mortems |
| 💛 Yellow | Strengths audit, quick win identification |
| 💚 Green | Test innovation, new approaches, brainstorming |
| 🔵 Blue | Strategy planning, retrospectives, decision-making |

---

## Hat Details

### 🤍 White Hat - Facts & Data
**Output: Quantitative testing baseline**

Questions:
- What test coverage do we have?
- What is our pass/fail rate?
- What environments exist?
- What is our defect history?

```
Example Output:
Coverage: 67% line, 45% branch
Test Suite: 1,247 unit, 156 integration, 23 E2E
Execution Time: Unit 3min, Integration 12min, E2E 45min
Defects: 23 open (5 critical, 8 major, 10 minor)
```

### 🖤 Black Hat - Risks & Cautions
**Output: Comprehensive risk assessment**

Questions:
- What could go wrong in production?
- What are we NOT testing?
- What assumptions might be wrong?
- Where are the coverage gaps?

```
HIGH RISKS:
- No load testing (production outage risk)
- Auth edge cases untested (security vulnerability)
- Database failover never tested (data loss risk)
```

### 💛 Yellow Hat - Benefits & Optimism
**Output: Strengths and opportunities**

Questions:
- What's working well?
- What strengths can we leverage?
- What quick wins are available?

```
STRENGTHS:
- Strong CI/CD pipeline
- Team expertise in automation
- Stakeholders value quality

QUICK WINS:
- Add smoke tests (reduce incidents)
- Automate manual regression (save 2 days/release)
```

### 💚 Green Hat - Creativity
**Output: Innovative testing ideas**

Questions:
- How else could we test this?
- What if we tried something completely different?
- What emerging techniques could we adopt?

```
IDEAS:
1. AI-powered test generation
2. Chaos engineering for resilience
3. Property-based testing for edge cases
4. Production traffic replay
5. Synthetic monitoring
```

### ❤️ Red Hat - Emotions
**Output: Team gut feelings (NO justification needed)**

Questions:
- How confident do you feel about quality?
- What makes you anxious?
- What gives you confidence?

```
FEELINGS:
- Confident: Unit tests, API tests
- Anxious: Authentication flow, payment processing
- Frustrated: Flaky tests, slow E2E suite
```

### 🔵 Blue Hat - Process
**Output: Action plan with owners and timelines**

Questions:
- What's our strategy?
- How should we prioritize?
- What's the next step?

```
PRIORITIZED ACTIONS:
1. [Critical] Address security testing gap - Owner: Alice
2. [High] Implement contract testing - Owner: Bob
3. [Medium] Reduce flaky tests - Owner: Carol
```

---

## Session Templates

### Solo Session (30 min)
```markdown
# Six Hats Analysis: [Topic]

## 🤍 White Hat (5 min)
Facts: [list metrics, data]

## ❤️ Red Hat (3 min)
Feelings: [gut reactions, no justification]

## 🖤 Black Hat (7 min)
Risks: [what could go wrong]

## 💛 Yellow Hat (5 min)
Strengths: [what works, opportunities]

## 💚 Green Hat (7 min)
Ideas: [creative alternatives]

## 🔵 Blue Hat (3 min)
Actions: [prioritized next steps]
```

### Team Session (60 min)
- Each hat: 10 minutes
- Rotate through hats as group
- Document on shared whiteboard
- Blue Hat synthesizes at end

---

## Agent Integration

```typescript
// Risk-focused analysis (Black Hat)
const risks = await Task("Identify Risks", {
  scope: 'payment-module',
  perspective: 'black-hat',
  includeMitigation: true
}, "qe-regression-risk-analyzer");

// Creative test approaches (Green Hat)
const ideas = await Task("Generate Test Ideas", {
  feature: 'new-auth-system',
  perspective: 'green-hat',
  includeEmergingTechniques: true
}, "qe-test-generator");

// Comprehensive analysis (All Hats)
const analysis = await Task("Six Hats Analysis", {
  topic: 'Q1 Test Strategy',
  hats: ['white', 'black', 'yellow', 'green', 'red', 'blue']
}, "qe-quality-analyzer");
```

---

## Agent Coordination Hints

### Memory Namespace
```
aqe/six-hats/
├── analyses/*        - Complete hat analyses
├── risks/*           - Black hat findings
├── opportunities/*   - Yellow hat findings
└── innovations/*     - Green hat ideas
```

### Fleet Coordination
```typescript
const analysisFleet = await FleetManager.coordinate({
  strategy: 'six-hats-analysis',
  agents: [
    'qe-quality-analyzer',        // White + Blue hats
    'qe-regression-risk-analyzer', // Black hat
    'qe-test-generator'           // Green hat
  ],
  topology: 'parallel'
});
```

---

## Related Skills
- [risk-based-testing](../risk-based-testing/) - Black Hat deep dive
- [exploratory-testing-advanced](../exploratory-testing-advanced/) - Green Hat exploration
- [context-driven-testing](../context-driven-testing/) - Adapt to context

---

## Anti-Patterns

| ❌ Avoid | Why | ✅ Instead |
|----------|-----|-----------|
| Mixing hats | Confuses thinking | One hat at a time |
| Justifying Red Hat | Kills intuition | State feelings only |
| Skipping hats | Misses insights | Use all six |
| Rushing | Shallow analysis | 5 min minimum per hat |

---

## Remember

**Separate thinking modes for clarity.** Each hat reveals different insights. Red Hat intuition often catches what Black Hat analysis misses.

**Everyone wears all hats.** This is parallel thinking, not role-based. The goal is comprehensive analysis, not debate.

© proffesor-for-testing · MIT · proffesor-for-testing/agentic-qe

Similar skills

All skills for Testing and QA →

six-thinking-hats by other authors comes first.

six-thinking-hats ysskrishna This Claude Code skill applies the Six Thinking Hats method to decisions and ideas. It separates evidence, reactions, risks, benefits, and fresh options before drawing them together. CX Codex +1 ★ 25repo stars thinking-lindy-effect tjboudreaux thinking-lindy-effect — a skill for Claude Code, Cursor and other platforms that teaches the agent to choose technologies and practices by survival time: the longer a solution has lasted, the longer it will last. CX Codex +1 643installs thinking-steel-manning tjboudreaux thinking-steel-manning builds the strongest opposing argument before rejecting or adopting a technical plan. Useful for architecture reviews and preventing sycophantic AI agreement. CX Codex +1 708installs critical-thinking-logical-reasoning sammcj critical-thinking-logical-reasoning is a Claude Code skill that examines arguments in articles, reports and transcripts. It runs after an explicit request for critique. CX Codex +1 2,500installs thinking-partner mattnowdev thinking-partner — a skill that pushes back on your assumptions and picks mental models for the problem at hand. Useful when you are stuck on a decision or want a plan stress-tested. CX Codex +1 564installs think johnlindquist A skill for in-depth analysis of complex problems using Gemini. Applies multiple thinking frameworks—first principles, systems thinking, inversion, second-order effects—to uncover blind spots and surface a grounded recommendation. CX Codex +1 260installs balanced glebis Skill for multi-perspective analysis: surfaces merits, challenges logic, suggests alternatives. Triggers on /balanced or requests for honest feedback. CX Codex +1 243installs

From the same set73

The whole set →
chaos-engineering-resilience chaos-engineering-resilience — a skill for injecting controlled failures into distributed systems, verifying recovery mechanisms, and validating resilience. Catches weaknesses before users do. CX Codex +1 138installs localization-testing The localization-testing skill checks translation coverage, locale-specific formats, RTL layouts, and Unicode handling. Use it when adding languages or preparing an international release. CX Codex +1 137installs sherlock-review sherlock-review is a skill for investigating code changes through evidence and deduction. It helps find bug root causes or verify fixes. CX Codex +1 135installs wms-testing-patterns wms-testing-patterns is a Claude Code skill with patterns for testing inventory accuracy, pick waves, EDI documents, and WMS-ERP integration. CX Codex +1 134installs a11y-ally The a11y-ally skill audits pages for WCAG issues and suggests fixes based on page context. Use it to review a site or assess video accessibility. CX Codex +1 131installs contract-testing Guides consumer-driven contract testing for microservices using Pact, catching breaking API changes before deploy. CX Codex +1 130installs qe-quality-assessment qe-quality-assessment reviews code quality through complexity, lint, code smells, and test health. Use it for release scoring, quality gates, and deployment checks. CX Codex +1 129installs qe-defect-intelligence qe-defect-intelligence identifies high-risk code before bugs escape by analyzing change frequency, complexity metrics, and past defect patterns. Flags risky PRs and runs root cause analysis on test failures. CX Codex +1 129installs

Project sponsors

Companies that keep this analytics open