six-hats
Skill1 starsChanged 20 days agoMITView on GitHub
Work through a decision or problem with Edward de Bono's Six Thinking Hats (White facts, Red feelings, Black risks, Yellow benefits, Green ideas, Blue process), one hat at a time. Use when the user says "six hats", "6 hats", "thinking hats", "de Bono", "red hat / black hat this", "look at this from every angle", "help me decide between", or asks for a structured pros, cons and options review of a choice.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- engelmandel/claude-skillstheir own version, first seen Oct 15, 2026
- danium/lateral-thinkingtheir own version, first seen Jul 9, 2026
- fimoklei/pm-ai-playbooktheir own version, first seen May 31, 2026
- esdrasmalinoski/six-hats-squadtheir own version, first seen Apr 12, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- danium/lateral-thinking★ 311same name
- fimoklei/pm-ai-playbook★ 42same name
- esdrasmalinoski/six-hats-squad★ 1same name
- engelmandel/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- .team/CLAUDE.mdCLAUDE.md
- agile-teamSkill
- example-skillSkill
- house-rulesSkill
- render-markdownSkill
- routed-group-chatSkill
- unattendedSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
Yellow before Black: when judging an idea, so it isn't killed before its value is stated.
- Distinctive: line 41
Don't decide for the user on value judgements.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
six-hats
Parallel thinking: look at the problem through one hat at a time, never
mixing them. Each hat is a mode, not a person or a verdict. What each hat
covers, what it must not do and the questions it asks are in
reference/hats.md next to this file. Read it before the first hat.
Steps
- Blue: frame it. State the decision as one question, its constraints and
what "decided" looks like. If the question is vague, ask until it is one
sentence. Pick a sequence from
reference/sequences.mdand say which. - Pick the mode. Solo: you wear every hat on the user's facts. Facilitated: for each hat, give your points, then ask the user for theirs before moving on. Default to solo unless the user wants to take part or holds facts you don't.
- Run the hats in order. One heading per hat. Stay strictly in that hat; anything that belongs to another hat is parked and raised there.
- Blue: close it. Summarise in the format at the end of
reference/sequences.md: the decision or recommendation, the risks that carry over with how to handle each, and the open questions with who answers them.
Rules
- One hat at a time. No "but" in Yellow, no fixes in Black, no justification in Red.
- Yellow before Black when judging an idea, so it isn't killed before its value is stated.
- Red is short: gut reactions in a line or two each, and label them as feelings.
- White marks its certainty. Separate known facts from assumptions, and list the facts still missing as questions.
- Green needs alternatives. At least three options, including one the user did not bring up.
- Don't decide for the user on value judgements; recommend, and say which hat the recommendation rests on.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.