borghei/Claude-Skills / project-management/discovery/brainstorm-ideas
brainstorm-ideas
VerifiedGenerates product ideas from PM, design and engineering angles, ties each to an opportunity and ranks the top five. Use when brainstorming features for an outcome, exploring a new product, or choosing which ideas to test first.
Product Ideation Expert
Overview
Structured product ideation for both new product creation and existing product enhancement. This skill combines the Product Trio approach (PM + Designer + Engineer perspectives) with Teresa Torres' Opportunity Solution Tree framework to generate, evaluate, and prioritize product ideas systematically.
Core Capabilities
- Product Trio ideation — generate ideas from PM, Designer, and Engineer perspectives (15+ per session)
- Opportunity Solution Trees — map desired outcomes → opportunities → solutions for existing products
- New-product lenses — core value, speed to validate, differentiation, market timing, scalability
- Weighted prioritization — score and rank the top 5 ideas across impact, alignment, feasibility, speed, differentiation
- Idea documentation — riskiest-assumption and validation plan per idea, ready for handoff
- Supplementary techniques — SCAMPER, How Might We, Crazy 8s, Worst Possible Idea
When to Use
- New Product Ideation -- Exploring greenfield opportunities where the focus is on core value delivery, speed to validate, and market differentiation.
- Existing Product Enhancement -- Identifying opportunities within a live product using the Opportunity Solution Tree to connect desired outcomes to concrete solutions.
Clarify First
Before ideating, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.
- New vs existing product: selects the approach (new-product lenses vs Opportunity Solution Tree mapping).
- Target outcome or problem: the desired outcome the session is anchored to (ungrounded ideation produces random ideas, not prioritizable ones).
- Hard constraints: tech stack, timeline, budget limits (bound the feasibility and speed scores in prioritization).
Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.
Workflow
- Settle the Clarify First inputs and write the target outcome as one measurable sentence.
- Map opportunities first (
opportunity_tree_builder.py), then generate ideas per opportunity from the three trio perspectives;references/ideation-process.mdhas the session plan. - Score the ideas (
idea_scorer.py) with a confidence value and riskiest assumption for each. - Done when every top-5 idea names its opportunity, its riskiest assumption with a matching test, its confidence and an owner for the next step.
Tools
Each tool prints a text report (--json for machine output). --example prints the input
shape; samples ship in assets/. Exit 0 on success, 2 on bad input (missing file, invalid
JSON, wrong shape, or no input given) with a one-line error.
python3 project-management/discovery/brainstorm-ideas/scripts/opportunity_tree_builder.py --tree project-management/discovery/brainstorm-ideas/assets/sample_opportunity_tree.json
python3 project-management/discovery/brainstorm-ideas/scripts/idea_scorer.py --ideas project-management/discovery/brainstorm-ideas/assets/sample_ideas.json
python3 project-management/discovery/brainstorm-ideas/scripts/scamper_generator.py --feature "team calendar"
| Tool | What it does |
|---|---|
opportunity_tree_builder.py | Renders outcome -> opportunities -> solutions; flags opportunities with no evidence or no solutions and trees with under 3 solutions per opportunity |
idea_scorer.py | Weighted score over impact (0.30), alignment (0.25), feasibility (0.20), speed to validate (0.15), differentiation (0.10); override with "weights". Classifies each riskiest assumption as value, usability, feasibility or viability risk (or takes assumption_type) and suggests the matching test; flags missing or low (<5) confidence |
scamper_generator.py | Prints the 35 SCAMPER question prompts with the feature name filled in. It is a checklist only: the ideas themselves must come from you, specific to the product |
Anti-Patterns
Ideas with no opportunity behind them
Mistake: The session produces a feature list ("dark mode, AI assistant, calendar integration") with no link to a customer opportunity or outcome. Why it happens: Features are concrete and easy to picture, so they come out first. Instead: Anchor every idea to a named opportunity on the Opportunity Solution Tree, and that opportunity to the target outcome. If you can't name the opportunity an idea serves, park it.
No confidence score
Mistake: Ideas get impact estimates, but nothing shows how sure the team is about those estimates. Why it happens: The weighted scoring covers impact and feasibility, so confidence seems already covered. Instead: Add a confidence score or evidence column for each idea before ranking the top 5. Note whether each estimate rests on customer interviews or one person's hunch, and test the low-confidence bets first.
Ideas with no next-step owner
Mistake: The workshop ends, the ideas stay on the board, and a month later nothing has happened.
Why it happens: Generating ideas feels like the output, so nobody plans what comes after.
Instead: Give each surviving idea an owner and a next step before the session ends. Hand each one's riskiest assumption to discovery/identify-assumptions.
Nine more, each with a bad and a good example: references/red-flags.md.
References
Load the reference that matches the task — keep this file lean and pull detail on demand:
- references/ideation-process.md — the full five-phase methodology (frame → trio → product-type approach → prioritize → document), output formats, supplementary techniques, troubleshooting table, success criteria, and further reading. Read when running a session end to end.
- references/ideation-frameworks.md — deep descriptions of the Product Trio methodology and each supplementary technique (SCAMPER, HMW, Crazy 8s, Worst Possible Idea). Read when you need technique detail or facilitation mechanics.
- references/red-flags.md — common ways ideation output goes wrong with bad/good examples. Read before publishing the idea list or moving to prioritization.
Integration with Other Discovery Skills
- After ideation, move top ideas to
identify-assumptions/to map and prioritize assumptions. - Use
brainstorm-experiments/to design validation experiments for key assumptions. - Run
pre-mortem/before committing to build, to surface hidden risks.
Scope & Limitations
In Scope: Structured ideation facilitation using Product Trio approach, Opportunity Solution Tree mapping, idea prioritization with weighted scoring, SCAMPER and HMW supplementary techniques, idea documentation with validation plans, integration with downstream discovery skills.
Out of Scope: Assumption testing and experiment design (hand off to brainstorm-experiments/ and identify-assumptions/), detailed product requirements (hand off to execution/create-prd/), market research and competitive analysis, financial modeling for ideas.
Limitations: Ideation quality is bounded by the diversity of perspectives in the room -- remote-only sessions may reduce creative energy. Scoring models provide structured comparison but are not objective truth; they encode the biases of the scorers. Opportunity Solution Trees require ongoing user research to populate -- they are not a substitute for customer interviews.
Files
| File | Purpose |
|---|---|
scripts/idea_scorer.py, scripts/opportunity_tree_builder.py, scripts/scamper_generator.py | See Tools |
assets/sample_ideas.json, assets/sample_opportunity_tree.json | Runnable inputs |
assets/ideation_workshop_template.md | Session template to fill in |
examples/b2b-onboarding-redesign-trio-session.md | Worked trio session |
references/*.md | See References |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |