AI gives you advice. But is it good advice?

Most AI conversations go the same way: you ask a question, get an answer, maybe ask a follow-up. It's helpful, but it's not rigorous.
What if you could force the AI to see all angles before recommending?

The Problem with Freeform AI Advice

AI is amazing at generating options. It's less amazing at systematically tearing them apart. You get:

• "It depends" answers
• Confirmation of what you already think
• Nice lists of pros and cons that don't actually help you decide ## Enter: The Six Hats Method

Edward de Bono's Six Hats is a structured thinking framework. Each "hat" represents a different perspective:

I Built a Skill That Runs This Automatically

Just tell the agent: "Run a six hats debate on [your decision]."
It runs 3 rounds, then outputs a markdown file with:

• Final recommendation (Blue Hat)
• Key agreements
• Unresolved tensions
• Next steps

Real Example

"Should I stay in frontend tooling or move to an AI company?"
The debate went through 3 rounds and concluded:

"Phased optionality — not an immediate pivot. Ship a small AI UI experiment, run exploratory interviews, talk to your current employer about AI-adjacent growth, then judge any offer on team and day-to-day work rather than the 'AI company' label."
That's a real recommendation, not generic advice.

Try It

Clone: github.com/juanallo/six-hats-skill
Add it to your agent skills folder and try: "Run a six hats debate on [your decision]"