Divergent Idea Generator
Brainstorm genuinely different ideas: isolated passes through distinct frames, duplicate cuts, novelty vs viability scores, cheap tests.
Before & after
Same prompt, same agent — the only difference is the skill.
Brainstorming can sometimes get stuck in patterns. You might try thinking about the problem from different angles or user segments. Breaking the group into smaller teams could help generate variety. Using prompts or frameworks to push thinking in new directions is useful. Looking at how competitors solve similar problems might spark ideas. It can help to set a quantity goal first before judging quality. Would you like some frameworks to structure the brainstorm?
ISOLATED AGENT BRAINSTORM PROCESS Challenge: Increase user engagement for an education SaaS Goal: 8-10 non-obvious ideas, scored on novelty and viability FRAME LIBRARY (3 isolated agents, each gets one frame) Agent 1 - Inversion Frame 'How would we decrease engagement intentionally? What if we made the app intentionally harder to use? Turn each friction point into a feature.' Output: Require daily commitment + streak counter Novelty score: 7/10 (habit-building angle novel, but common pattern) Agent 2 - Adjacent Market Frame 'What if we were building this for elite athletes or musicians, not students? What would they need differently?' Output: Achievement leaderboards by skill level with coach verification Novelty score: 9/10 (competitive framing new to education SaaS) Agent 3 - Constraint Frame 'What if we had zero budget for content, zero ability to hire, one engineer only? What's possible?' Output: User-generated problem sets with crowdsourced verification Novelty score: 8/10 (peer review model not in current product) CRITIC AGENT SCORING Scores each on: novelty (is this actually new to market), viability (can one engineer build in 3 weeks), business impact (does it move the needle) SHORTLIST (non-obvious ideas) 1. Competitive leaderboards by skill (score: 8.2/10) 2. Peer problem verification (score: 7.9/10) 3. Habit streak system (score: 7.1/10) TRAP LIST (ideas that sound good but fail viability) - AI tutor integration (requires licensing) - Real-time collaboration (complex infrastructure) - Mobile-first redesign (timeline conflict) Generated ideas are genuinely different from single-agent brainstorm.
About this skill
Most brainstorms produce ten versions of the first idea. This skill forces each pass through a different frame, cuts the near-duplicates, and hands you a short, scored list of genuinely different options with a cheap way to test each.
What it does
- Writes a banned list of the obvious answers first so the ideas have to go somewhere new
- Runs isolated passes through a 12-frame library: constraint removal, adjacent-industry analogy, worst-idea-then-invert, flip the actor, subtract, scale shift, flip the money, and more
- Uses separate subagents per frame when available, so passes cannot contaminate each other
- Merges ideas that share a mechanism and flags when the problem statement is too narrow
- Scores novelty and viability separately with an explicit 1-5 rubric and no inflation
What you get
For a quick ask, five one-line angles each tagged with its frame and a pick to try first. For a full session, a shortlist table of 3-5 ideas with frame, novelty and viability scores with reasons, the cheapest test for each, and what would kill it.
Best for
Founders, product managers, marketers, and teams stuck on a problem where every idea sounds the same, from growth and retention to operations and product direction.
SKILL.md preview
---
name: divergent-idea-generator
… (sign up to view the full skill)More business & ops skills
View all Business & Ops skills →Onboarding Drop-Off Diagnosis and Activation Fix Plan
Find where new users leak between signup and first value, explain why, and get a ranked fix and test plan with real sample-size math.
A/B Test Design, Build & Experiment Roadmap
Sizes A/B tests to your actual traffic, specifies assignment and exposure logging, and ranks a test roadmap you can actually run.
Lead Magnet Builder and Opt-In Fix
Builds a ready-to-ship lead magnet with contents, opt-in page, and delivery email, and diagnoses magnets that don't convert or sell.
SaaS Upgrade Prompts and Feature Gate Optimization
Find which step of your upgrade funnel is leaking, then redesign the gate, limit, or upsell copy and set up the test to prove it.