| name | brainstorming-six-thinking-hats |
| description | Facilitate a Six Thinking Hats session to examine a project decision or proposal from six structured perspectives, preventing premature convergence and surfacing blind spots. Invoke when the team needs to evaluate a significant decision without collapsing into debate. |
Adapted from bmad-method:bmad-brainstorming (MIT, © 2025 BMad Code, LLC). See THIRD_PARTY_NOTICES.md.
When to use
Use this skill when a team must evaluate a significant decision, proposal, or change where multiple conflicting viewpoints are likely and debate tends to crowd out one or more perspectives. Typical triggers include:
- A go/no-go decision on a major scope change or architectural pivot
- A retrospective action plan that needs to survive skeptical review before commitment
- A stakeholder alignment session where optimists and risk managers routinely talk past each other
- A product roadmap prioritization where emotional investment in one initiative is suppressing critical analysis
Do not invoke when the primary need is to generate novel ideas without constraints; prefer Mind Mapping or Morphological Analysis for divergent generation. Do not invoke when a single root cause must be traced; prefer Five Whys.
Summon the SME
Before facilitating, load the canonical Six Thinking Hats reference to ground the session in established practice.
Reading the config. Check .pm-kit.config.json for the sourcesMode field:
- If
sourcesMode is "online" (opt-in): fetch the URL stored at the key sources.sixThinkingHats in vendor/pm-kit/sources-index.json using your available web-fetch capability. Do not name a specific tool — use whatever your runtime provides. Ground the facilitation in what you read. Do not fabricate quotations or page numbers from any version of that page.
- If
sourcesMode is "offline" or the field is absent (the default): rely on your general knowledge of the Six Thinking Hats technique as developed by Edward de Bono. Cite the canonical URL from vendor/pm-kit/sources-index.json at key sources.sixThinkingHats in the output. Do not fabricate quotations or page numbers.
In both cases, the URL to cite is https://www.debonogroup.com/services/core-programs/six-thinking-hats/.
Facilitation script
Walk the user through these steps in sequence. Do not skip steps or combine them.
Step 1 — Focus statement. Ask the user to state the proposal or decision under examination in one sentence. Confirm it is specific enough that each hat round will generate concrete outputs.
Step 2 — White Hat (facts). Ask: "What do we know for certain? What data and information are available?" Capture only verifiable facts and data gaps — no opinions, no predictions.
Step 3 — Red Hat (emotions). Ask: "What is your gut reaction? What emotions and intuitions does this proposal trigger?" Capture reactions without requiring justification. Both enthusiasm and unease are valid outputs.
Step 4 — Black Hat (caution). Ask: "What could go wrong? What are the risks, weaknesses, and reasons this might fail?" Capture all critical concerns. This is the hat where pessimism is productive — do not prematurely counter concerns.
Step 5 — Yellow Hat (optimism). Ask: "What are the benefits and reasons this could succeed?" Capture the genuine value and upside. If the Black Hat produced strong concerns, prompt the user to identify compensating benefits.
Step 6 — Green Hat (creativity). Ask: "What alternatives, improvements, or creative options exist?" Capture new ideas and modifications — including ideas that mitigate Black Hat risks or amplify Yellow Hat benefits.
Step 7 — Blue Hat (process). Ask the user to step back and reflect: "What have we learned from this session? What conclusions or next steps does the evidence support?" Synthesize outputs from all five preceding hats into a summary and recommended action.
Step 8 — Output. Produce the completed analysis using the structure in TEMPLATE.md (sibling file). Fill every section. Leave no placeholder unfilled.
Step 9 — Save the artifact. Save the filled artifact to docs/pm-kit/outputs/brainstorming-six-thinking-hats/<short-slug>.md. <short-slug> is a kebab-case ASCII slug (max 40 characters) derived from the focus statement (e.g., migrate-to-microservices). Confirm the final path with the user before writing. If the target file already exists, ask the user whether to overwrite, append a date suffix (e.g., -2026-04-20), or choose a different slug. The artifact must begin with the three-line provenance header below (preserved as HTML comments so they do not render):
<!-- Generated by agentic-pm-kit:brainstorming-six-thinking-hats on YYYY-MM-DD -->
<!-- Languages: communication=<value>, output=<value> -->
<!-- Source mode: offline | online -->
Languages
The kit separates the language used for live agent–user dialogue from the language used in the saved artifact. Both values live in .pm-kit.config.json and are free-form strings — read each value verbatim, never infer a language from the conversation, and never select from a hardcoded list.
Facilitation dialogue. Speak to the user during facilitation in the language at language.communication. Use the string verbatim.
Filled artifact (saved TEMPLATE.md output). Produce the written artifact in the language at language.output. If language.output is absent or empty, fall back to language.communication.
Example values either field might contain: "en-US", "es-MX", "Português brasileiro", "Mandarin Chinese". Accept any string as given. This bifurcation is the normative pattern for every skill in the kit.
Acceptance gate
When the analysis is complete, point the user to CHECKLIST.md (sibling file) and ask them to verify each item. Remind them that the output must be marked PASS or FAIL. On FAIL, invite the user to return with specific notes so the facilitation can be resumed or corrected.
