brainstorm-diverge-converge
$
npx mdskill add lyndonkl/claude/brainstorm-diverge-convergeGenerate, cluster, and select the best ideas for complex problems.
- Helps solve open-ended problems by creating many creative options.
- Groups ideas into themes before evaluating them against criteria.
- Decides on the strongest choices through systematic filtering.
- Delivers a ranked list of refined solutions ready for action.
SKILL.md
.github/skills/brainstorm-diverge-convergeView on GitHub ↗
---
name: brainstorm-diverge-converge
description: Applies structured divergent-convergent thinking to generate many creative options, organize them into meaningful clusters, then systematically evaluate and narrow to the strongest choices. Balances creative exploration with disciplined decision-making. Use when exploring product ideas, solving open-ended problems, generating strategic alternatives, developing research questions, designing experiments, or when user mentions brainstorming, ideation, divergent thinking, generating options, or evaluating alternatives.
---
# Brainstorm Diverge-Converge
## Table of Contents
- [Workflow](#workflow)
- [1. Gather Requirements](#1--gather-requirements)
- [2. Diverge (Generate Ideas)](#2--diverge-generate-ideas)
- [3. Cluster (Group Themes)](#3--cluster-group-themes)
- [4. Converge (Evaluate & Select)](#4--converge-evaluate--select)
- [5. Document & Validate](#5--document--validate)
- [Common Patterns](#common-patterns)
- [Guardrails](#guardrails)
- [Quick Reference](#quick-reference)
Three phases: Diverge (generate many ideas without judgment), Cluster (group into themes), Converge (evaluate against criteria and select).
**Quick Example:**
```markdown
# Problem: How to improve customer onboarding?
## Diverge (30 ideas)
- In-app video tutorials
- Interactive walkthroughs
- Email drip campaign
- Live webinar onboarding
- 1-on-1 concierge calls
- ... (25 more ideas)
## Cluster (6 themes)
1. **Self-serve content** (videos, docs, tooltips)
2. **Interactive guidance** (walkthroughs, checklists)
3. **Human touch** (calls, webinars, chat)
4. **Motivation** (gamification, progress tracking)
5. **Timing** (just-in-time help, preemptive)
6. **Social** (community, peer examples)
## Converge (Top 3)
1. Interactive walkthrough (high impact, medium effort) - 8.5/10
2. Email drip campaign (medium impact, low effort) - 8.0/10
3. Just-in-time tooltips (medium impact, low effort) - 7.5/10
```
## Workflow
Copy this checklist and track your progress:
```
Brainstorm Progress:
- [ ] Step 1: Gather requirements
- [ ] Step 2: Diverge (generate ideas)
- [ ] Step 3: Cluster (group themes)
- [ ] Step 4: Converge (evaluate and select)
- [ ] Step 5: Document and validate
```
**Step 1: Gather requirements**
Clarify topic/problem (what are you brainstorming?), goal (what decision will this inform?), constraints (must-haves, no-gos, boundaries), evaluation criteria (what makes an idea "good" - impact, feasibility, cost, speed, risk, alignment), target quantity (suggest 20-50 ideas), and rounds (single session or multiple rounds, default: 1).
**Step 2: Diverge (generate ideas)**
Generate 20-50 ideas without judgment or filtering. Suspend criticism (all ideas valid during divergence), aim for quantity and variety (different types, scales, approaches), and use creative prompts: "What if unlimited resources?", "What would competitor do?", "Simplest approach?", "Most ambitious?", "Unconventional alternatives?". Output: Numbered list of raw ideas. For simple topics → generate directly. For complex topics → Use `resources/template.md` for structured prompts.
**Step 3: Cluster (group themes)**
Organize ideas into 4-8 distinct clusters by identifying patterns, creating categories (mechanism, user/audience, timeline, effort, risk, strategic objective), naming clusters clearly, and checking coverage (distinct approaches). Fewer than 4 = not enough variety, more than 8 = too fragmented. Output: Ideas grouped under cluster labels.
**Step 4: Converge (evaluate and select)**
Define criteria (from step 1), score ideas on criteria (1-10 or Low/Med/High scale), rank by total/weighted score, select top 3-5 options, and document tradeoffs (why chosen, what deprioritized). Evaluation patterns: Impact/Effort matrix, weighted scoring, must-have filtering, pairwise comparison. See [Common Patterns](#common-patterns) for domain-specific approaches.
**Step 5: Document and validate**
Create `brainstorm-diverge-converge.md` with: problem statement, diverge (full list), cluster (organized themes), converge (scored/ranked/selected), and next steps. Validate using `resources/evaluators/rubric_brainstorm_diverge_converge.json`: verify 20+ ideas with variety, distinct clusters, explicit criteria, consistent scoring, top selections clearly better, actionable next steps. Minimum standard: Score ≥ 3.5.
## Common Patterns
**For product/feature ideation:**
- Diverge: 30-50 feature ideas
- Cluster by: User need, use case, or feature type
- Converge: Impact vs. effort scoring
- Select: Top 3-5 for roadmap
**For problem-solving:**
- Diverge: 20-40 solution approaches
- Cluster by: Mechanism (how it solves problem)
- Converge: Feasibility vs. effectiveness
- Select: Top 2-3 to prototype
**For research questions:**
- Diverge: 25-40 potential questions
- Cluster by: Research method or domain
- Converge: Novelty, tractability, impact
- Select: Top 3-5 to investigate
**For strategic planning:**
- Diverge: 20-30 strategic initiatives
- Cluster by: Time horizon or strategic pillar
- Converge: Strategic value vs. resource requirements
- Select: Top 5 for quarterly planning
## Guardrails
**Do:**
- Generate at least 20 ideas in diverge phase (quantity matters)
- Suspend judgment during divergence (criticism kills creativity)
- Create distinct clusters (avoid overlap and confusion)
- Use explicit, relevant criteria for convergence (not vague "goodness")
- Score consistently across all ideas
- Document why top ideas were selected (transparency)
- Include "runner-up" ideas (for later consideration)
**Don't:**
- Filter ideas during divergence (defeats the purpose)
- Create clusters that are too similar or overlapping
- Use vague evaluation criteria ("better", "more appealing")
- Cherry-pick scores to favor pet ideas
- Select ideas without systematic evaluation
- Ignore constraints from requirements gathering
- Skip documentation of the full process
## Quick Reference
- **Template**: `resources/template.md` - Structured prompts and techniques for diverge-cluster-converge
- **Quality rubric**: `resources/evaluators/rubric_brainstorm_diverge_converge.json`
- **Output file**: `brainstorm-diverge-converge.md`
- **Typical idea count**: 20-50 ideas → 4-8 clusters → 3-5 selections
- **Common criteria**: Impact, Feasibility, Cost, Speed, Risk, Alignment
More from lyndonkl/claude
- abstraction-concrete-examplesBuilds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.
- academic-letter-architectGuides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
- adr-architectureDocuments significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
- adverse-selection-priorProduces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it. Applies Akerlof market-for-lemons logic -- if they offered it, they believe it is +EV for them, so the prior that it is +EV for us is materially below 50%. Reusable across trade evaluation, waiver drops (another team dropping a player is also adverse selection), job-offer analysis, M&A, and any "someone offered me this" situation. Use when you receive an unsolicited trade/offer/proposal, analyzing incoming trade prior, evaluating why a counterparty proposed a deal, or when user mentions adverse selection, market for lemons, why did they offer this, incoming trade prior, they proposed it, Bayesian adjustment on received offer.
- alignment-values-north-starCreates actionable alignment frameworks that give teams a shared North Star (direction), values (guardrails), and decision tenets (behavioral standards). Enables autonomous decision-making while maintaining organizational coherence. Use when starting new teams, scaling organizations, defining culture, establishing product vision, resolving misalignment, creating strategic clarity, or when user mentions North Star, team values, mission, principles, guardrails, decision framework, or cultural alignment.
- analogy-weight-checkFor every analogy in a substacker draft, verifies it carries mechanical weight — the analogy does real work explaining the mechanism, not merely decorates it. Cross-references analogy-catalog.md for novelty (is this analogy reused from a prior post?) and domain fit (biology > organizational > sports preferred; physics/military disfavored). Use whenever an analogy appears in the draft. Trigger keywords: analogy weight, decorative, mechanical weight, reused analogy, catalog check, metaphor check.
- answer-uncomfortable-questionTakes one strategic question about substacker ("should we launch paid?", "is this section dead?", "are we writing for the wrong audience?") and produces the mandatory evidence + reasoning + downside triad plus a recommendation. Used 3 times per Growth Strategist review. Trigger keywords: uncomfortable question, strategic question, evidence reasoning downside, triad.
- attribute-performanceFor each substacker post that materially over- or under-performs the rolling baseline (|z| ≥ 1.0), produces a plain-English attribution paragraph with calibrated confidence (high / medium / low / unexplained). Considers subject-line effect, topic zeitgeist, external share, day-of-week, length effect, and audience-notes signals. Labels unexplained outliers explicitly rather than fabricating a story. Use after compute-baseline when outlier posts exist. Trigger keywords: attribution, why did this post work, outlier explanation, performance analysis.
- auction-first-price-shadingComputes the optimal shaded bid for a first-price sealed-bid auction given a true private value, an estimate of the number of competing bidders N, and a value-distribution assumption. Implements the `(N-1)/N` equilibrium shading rule for uniform private values, adjusts for log-normal or empirical value distributions, layers a risk-aversion adjustment, and caps output against the bidder's remaining budget. Domain-neutral auction theory reusable across fantasy sports (baseball FAAB, NBA/NHL waiver auctions), prediction-market limit sizing, sealed procurement bids, and any blind-bid context. Use when user mentions "first-price auction bid", "sealed bid shading", "(N-1)/N", "FAAB bid amount", "auction shading", "optimal bid first-price", "bid for sealed-bid", "blind bid sizing", or when downstream logic needs a principled shade factor rather than an ad-hoc heuristic.
- auction-winners-curse-haircutApplies a Bayesian haircut to a bid valuation for common-value auctions where winning is itself evidence the bidder over-estimated. Takes a raw valuation, a value-type classification (common_value / private_value / mixed), the number of informed bidders N, and a signal-dispersion estimate, and returns an adjusted valuation. Domain-neutral and reusable across fantasy FAAB, prediction markets, M&A bids, ad-auction budgets, and any generic bidding context. Use when user mentions "winner's curse", "common value auction", "valuation haircut", "adverse valuation", "Bayesian bid adjustment", or "over-paying in auction".