Help us improve
Share bugs, ideas, or general feedback.
From personal-corp-skills
Structured divergent thinking session for product problems or opportunities using SCAMPER, 5-Whys, and cross-domain inspiration. Outputs ranked ideas with top-3 deep-dives.
npx claudepluginhub serejaris/personal-corp-skills --plugin personal-corp-skillsHow this skill is triggered — by the user, by Claude, or both
Slash command
/personal-corp-skills:pm-brainstormThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Part of the Personal Corp framework — running a one-person business through AI agents.
Brainstorms product ideas, explores problem spaces, challenges assumptions, and stress-tests concepts as a PM thinking partner. Use for new opportunities, product problem-solving, or idea validation.
Generates ideas for existing products from PM, designer, and engineer perspectives (5 each), prioritizing top 5 with rationale and key assumptions. For continuous product discovery and opportunity-solution trees.
Structured brainstorming that transforms vague ideas into actionable feature proposals using multi-persona ensemble and multi-critic convergence techniques.
Share bugs, ideas, or general feedback.
Part of the Personal Corp framework — running a one-person business through AI agents. Run a structured creative-divergence session on a specific product problem or opportunity. Not just listing ideas — challenges assumptions, borrows across domains, helps reach options you wouldn't have otherwise. Output is a screened idea list ready for next-step action.
| Field | Required | Notes |
|---|---|---|
| Topic | yes | Problem to solve or opportunity to explore — more specific = better |
| Background | no | Persona, current data, known constraints |
| Mode | no | Full divergence / single framework only; default full |
| Constraints | no | Tech, time, resource limits |
Good topic: "How might we make new users feel value within the first 5 minutes of first use?" Bad topic: "How do we improve the product?" (too vague)
Before diverging, sharpen the problem.
Probing checklist:
Restate as a How Might We:
Run each lens once; aim for 1-2 ideas per lens.
| Lens | Core question | Direction |
|---|---|---|
| S — Substitute | What component can be substituted? | Different tech / interaction / entry point? |
| C — Combine | Can we merge two features? | Merge steps / contexts / bundle features |
| A — Adapt | What from elsewhere can we borrow? | Method from social apps? From productivity tools? |
| M — Modify | What if we 10×'d or 0.1×'d this? | Minimal version? Maximal version? |
| P — Put to other use | What other context could this serve? | Other personas? Other scenarios? |
| E — Eliminate | What if we remove something? | Cut steps / fields / signup / friction? |
| R — Rearrange | What if we reorder? | Try first / signup later? Reverse order? |
Total: 7-14 initial ideas.
From a user pain, descend to the root, then ideate from each layer.
Example:
Pain: new users churn on day 2
Rules:
Don't copy competitors — look at what they do, then think "what could we do that's different".
Cross-domain prompts:
Differentiation prompts:
Deliberately set constraints to spark creativity.
| Constraint | Setup | Stimulus |
|---|---|---|
| Time | "Only 1 week of dev time" | Forces minimum viable approach |
| Tech | "Use only existing stack" | Reveals new uses of existing capabilities |
| Cost | "Zero dev investment" | Ops moves, config changes, copy tweaks |
| Extreme | "Change one line of code" | Find the highest-leverage single point |
| Inversion | "Let users design it" | Switch perspective |
1-2 ideas per constraint. Tighter constraints often produce more elegant ideas.
First think "how could we make this worse", then invert each idea.
Steps:
Example:
| Make-worse | Inverted |
|---|---|
| Require 20 fields at signup | Phone-only signup, progressive profile fill |
| Home is full of ads | Home shows only goal-relevant content |
| Hide all help entries | Surface guidance proactively at confusion points |
Reverse-brainstorm bypasses the "find the right answer" pressure — the divergence stage gets freer.
Drop all ideas into a 2×2:
| Quadrant | Impact | Effort | Strategy | Ideas |
|---|---|---|---|---|
| Quick Wins | High | Low | Validate first | {list} |
| Big Bets | High | High | Worth investing, plan carefully | {list} |
| Fill-ins | Low | Low | When idle | {list} |
| Money Pits | Low | High | Drop | {list} |
Scoring:
# Product Brainstorm
**Topic:** {problem}
**HMW:** How might we {restated as HMW}
**Date:** {today}
**Ideas generated:** {N} (kept after screening: {M})
## Idea List
| # | Idea | Pain solved | Source framework | Expected value | Effort | Quadrant | Validation |
|---|---|---|---|---|---|---|---|
| 1 | {desc} | {pain} | SCAMPER-Eliminate | High/Med/Low | High/Med/Low | Quick Win | {validation} |
## Top 3 Recommendations
### Idea 1: {name}
- **Description:** {detail}
- **Pain solved:** {specific pain}
- **Expected impact:** {quantified, e.g. "+5-10% D1 retention"}
- **Implementation path:** {brief tech / design approach}
- **Validation:** {how to validate fast — A/B test, gradual rollout, etc.}
- **Risk:** {risks and mitigation}
### Idea 2: {name}
…
### Idea 3: {name}
…
## Dropped Ideas (archived)
- {idea X}: dropped because — {reason}
- {idea Y}: dropped because — {reason}
## Next Actions
- [ ] {action 1}
- [ ] {action 2}
/pm-prd — Top idea → PRD/pm-prioritize — Idea list → formal ranking/pm-user-stories — Ideas → developable Stories/pm-feedback — Pain points from feedback → brainstorm fuel/pm-competitive — Validate differentiation level