fimoklei/pm-ai-playbook/six-hats
Claude Code and agent skill by fimoklei/pm-ai-playbook
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Structured six-hats thinking sessions for debating decisions. Use when user says \"six hats\", \"six hats debate\", or wants to explore a decision through six colored-perspective lenses in sequential rounds with a final recommendation.
Install
npx vskill@latest install fimoklei/pm-ai-playbook/six-hatsSKILL.md
Six Hats Debate Skill
How It Works
- User submits the topic — paste the decision, plan, or question in chat.
- User specifies output path — e.g.
Projects/my-debate/or any path. - Skill runs 3 rounds of sequential debate, one hat at a time.
- Blue hat moderates — summarizes and provides the final recommendation.
- Summary written to `{output_path}/debate-{timestamp}.md`.
The Six Hats
| Hat | Role | Focus | |
|---|---|---|---|
| White | Facts & Information | What do we know? What's unknown? What data exists? | |
| Red | Emotion & Intuition | Gut feelings, hunches, what feels wrong even without evidence | |
| Yellow | Optimism & Benefits | Why could this work? What's the best outcome? | |
| Black | Caution & Risks | What could go wrong? What are the failure modes? | |
| Green | Creativity & Alternatives | New ideas, different approaches, lateral thinking | |
| Blue | Process & Moderation | Orchestrates the debate, manages time, writes final summary |
Debate Rules
- Each hat speaks sequentially: White → Red → Yellow → Black → Green → Blue
- Round 1: Each hat responds to the original topic
- Round 2: Each hat sees Round 1 output and can counter, amplify, or concede
- Round 3: Final statements — hats can shift positions based on the debate
- Blue hat does not contribute opinions during rounds; only moderates and summarizes at the end
Output Format
Workflow
- Read this SKILL.md
- Ask user for the topic and output path
- Run Round 1 — prompt each hat sequentially, collect responses
- Run Round 2 — feed Round 1 back to each hat, collect responses
- Run Round 3 — feed Round 2 back to each hat, collect responses
- Blue hat synthesizes → writes final recommendation
- Write complete debate file to
{output_path}/debate-{timestamp}.md - Report file path to user
Hat Prompt Templates
White Hat (Facts)
Red Hat (Emotion)
Yellow Hat (Optimism)
Black Hat (Caution)
Green Hat (Creativity)
Blue Hat (Moderation)
Notes
- Do not run hats in parallel — sequential builds better debate momentum
- If the topic is too vague, ask the user to clarify before starting
- Each round must complete fully before moving to the next round
- Always write the output file — do not skip this step
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/meta-skills/six-hats/SKILL.md
Popularity
- Repository stars
- 42
- Repository forks
- 8
- 7-day trend score
- 19
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 24 Sep 2026, a month ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/fimoklei/pm-ai-playbook/six-hats)