Structured group-decision mechanic that captures silent ideation, voting summaries, and Decider sign-off in a single bundled artifact. Use when a small team needs to make a fast decision with diverse input, when groupthink is a risk, or when a workshop moment demands silent contribution before discussion. Applicable to Foundation Sprint, Design Sprint, and any participatory decision context.
npx skills add https://github.com/product-on-purpose/pm-skills --skill tool-note-and-vote
<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->
Run a structured group decision in 20-30 minutes. Silent contribution surfaces independent thinking before group dynamics narrow the option space; explicit Decider supervote closes the choice. Produces a written audit trail of the decision and the alternatives considered.
1. Frame the question (1-2 min)
2. Silent ideation (3-7 min, depending on complexity)
3. Silent voting (2-5 min, multi-vote or single-vote)
4. Brief discussion of the vote distribution (5-10 min)
5. Decider supervote (1 min)
Total: 12-25 minutes depending on time allocations. Default is 25 minutes for a non-trivial decision.
flowchart TB
Start([Decision needed])
Start --> S1[Step 1: Frame the question<br/>1-2 min, spoken]
S1 --> S2[Step 2: Silent ideation<br/>3-7 min, silent]
S2 --> S3[Step 3: Silent voting<br/>2-5 min, silent]
S3 --> S4[Step 4: Brief discussion<br/>5-10 min, spoken]
S4 --> S5{Step 5: Decider supervote<br/>1 min}
S5 -->|Most common| TopVote[Pick top vote-getter]
S5 -->|Sometimes| Override[Pick different option<br/>with stated rationale]
S5 -->|Rare| Revote[Call re-vote after re-framing]
TopVote --> Record[Decision recorded in artifact]
Override --> Record
Revote --> S2
style S2 fill:#e1f5ff
style S3 fill:#e1f5ff
style S5 fill:#fff4e1
style Record fill:#e1ffe1
Silent steps (blue) protect against anchoring. The Decider supervote (amber) has three legal outcomes; the loop back to silent ideation is the recovery path when the framing was wrong.
Write the decision question on the board, one sentence, unambiguous. Examples:
Bad framings to avoid:
Every participant contributes options silently and independently. Sticky notes on a wall, cells in a Miro board, or rows in a shared doc. No talking. No reading others' contributions until the timer ends.
The facilitator MUST enforce silence. Verbal contribution defeats the purpose.
Display all contributions anonymously (or with attribution if the team has agreed). Each participant gets N votes (often 2-3 for a multi-vote round, 1 for a single-vote tiebreaker). Vote silently using dots, stickers, reactions, or numbers. No discussion during voting.
Surface the top 2-3 vote-getters. Each person who voted for the top options briefly explains why. The facilitator times this (5-10 minutes max). If discussion expands beyond the top options, the facilitator pulls it back.
This is the place where the team can detect surprises ("I didn't realize we were aligned on X") or unsurprises ("we're split between A and B for known reasons"). It is not the place to relitigate the framing.
The Decider names the chosen option. The Decider may pick the top vote-getter (most common), pick a different option with stated rationale (sometimes), or call for a re-vote after the discussion (rare).
The supervote is the decision. Record it explicitly in the artifact. Do not let the supervote blur into continued discussion; the team needs to see the close.
The skill produces a single bundled artifact containing:
See references/TEMPLATE.md for the canonical structure and references/EXAMPLE.md for a worked example using the Brainshelf book-catalog Foundation Sprint thread.
The Decider has three responsibilities in Note-and-Vote:
A Decider who consistently rubber-stamps the team's top vote is not adding value. A Decider who consistently overrides without rationale is not building trust. Both are signals the wrong person is in the seat.
Character Capital publishes the canonical Note-and-Vote guide at https://www.character.vc/guide/note-and-vote. Knapp and Zeratsky describe Note-and-Vote variants in both *Sprint* (Design Sprint context) and *Click* (Foundation Sprint context).
This pm-skills implementation follows the Character protocol with the Five-Step structure named explicitly.
tool-note-and-vote is a standalone tool, not a member of any sprint family. It is invoked many times across both foundation-sprint-skills and design-sprint-skills family members at decision moments. SKILL.md files in those families reference tool-note-and-vote inline rather than embedding the protocol.
The skill is also useable outside sprint contexts: any participatory decision in a meeting, planning session, or workshop can invoke it.
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Take product-on-purpose/tool-note-and-vote from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.