brainstorming-brain-writing-round-robin

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 needs to generate ideas but verbal brainstorming is producing uneven participation or groupthink. Typical triggers include:

• A retrospective or planning session is dominated by a few voices while others remain silent
• The team is geographically distributed and synchronous discussion is impractical
• A sensitive topic (scope reduction, team restructuring, sponsor pressure) makes open verbal discussion difficult
• A previous brainstorming session produced few ideas or ideas that closely mirrored whoever spoke first

Do not invoke when a small team is already equally engaged in open discussion; reserve this skill for situations where the silent, sequential format adds real equity value.

Summon the SME

Before facilitating, load the canonical reference to ground the session in established brainwriting 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.brainWritingRoundRobin 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.
• If sourcesMode is "offline" or the field is absent (the default): rely on your general knowledge of the Brainwriting / 6-3-5 technique developed by Bernd Rohrbach (1969) and its round-robin pass structure. Cite the canonical URL from vendor/pm-kit/sources-index.json at key sources.brainWritingRoundRobin in the output. Do not fabricate quotations or page numbers.

In both cases, the URL to cite is https://en.wikipedia.org/wiki/6-3-5_Brainwriting.

Facilitation script

Walk the user through these steps in sequence. Do not skip steps or combine them.

Step 1 — State the prompt. Ask the user to provide a single, focused ideation prompt for the session. Example: "What could we do to recover one week of schedule before the next milestone?" Confirm the prompt is specific enough that participants will generate comparable ideas.

Step 2 — Confirm participants. Ask the user to list the participants (by role or name). Confirm that each participant will contribute independently in writing before anyone reviews others' ideas. Note the total count; sessions work well with four to eight participants.

Step 3 — Round one — initial ideas. Instruct each participant to write three ideas in response to the prompt, silently and without discussing. Set a time limit (five minutes is standard). Record all ideas without filtering or attributing them to individuals.

Step 4 — Pass and build. Pass each participant's idea sheet to the next participant (round-robin order). Each participant reads what they received and writes two to three additional ideas inspired by or building on the existing entries. Repeat for two to three more rounds, or until idea generation diminishes.

Step 5 — Collect and deduplicate. Aggregate all ideas from all rounds. Remove exact duplicates. Preserve variations even when closely related.

Step 6 — Cluster. Group related ideas into themes. Present the themes and ideas to the group. Ask: "Are there ideas that do not fit any cluster? Should any cluster be split?" Adjust as needed.

Step 7 — Prioritize. Ask participants to vote on the most promising ideas (dot-voting or equivalent). Identify the top three to five ideas for further development.

Step 8 — Output. Produce the completed session summary 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-brain-writing-round-robin/<short-slug>.md. <short-slug> is a kebab-case ASCII slug (max 40 characters) derived from the session prompt (e.g., schedule-recovery-sprint-5). Confirm the final path with the user before writing. If the file exists, ask: overwrite, append a date suffix (e.g., -2026-04-20), or pick a new slug. The artifact begins with the three-line provenance header below (HTML comments, do not render):

<!-- Generated by agentic-pm-kit:brainstorming-brain-writing-round-robin 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 session 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.