Six Thinking Hats

What it does

When your agent uses it

• Designing test strategies
• Conducting test retrospectives
• Analyzing test failures
• Evaluating testing approaches

Example prompts

• “/six-thinking-hats”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1DEFINE focus clearly (specific testing question)
2. 2APPLY each hat sequentially (5 min each)
3. 3DOCUMENT insights per hat
4. 4SYNTHESIZE into action plan

What it can do on your machine

Read from SKILL.md and the folder at commit 829d030. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and typescript).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Six Thinking Hats loads about 1.9k tokens when it runs. Until then it costs about 111 tokens; SKILL.md has 462 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~111

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from proffesor-for-testing/agentic-qe at commit 829d030, republished under its MIT licence (© proffesor-for-testing). 462 words, ~1,902 tokens.

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

last_optimized

2025-12-03

quick_reference_card

true

tags

thinking, methodology, decision-making, collaboration, analysis

trust_tier

0

🤍 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 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)

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

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)

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

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

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

# 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]

// 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");

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

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'
});

© proffesor-for-testing, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files in assets/skills/six-thinking-hats of proffesor-for-testing/agentic-qe.

• SKILL.md
• README.md
• resources/examples/api-testing-example.md
• resources/templates/solo-session-template.md
• resources/templates/team-session-template.md

Open the folder on GitHubat commit 829d030