Skip to content

Commit a518709

Browse files
narenkatakamclaude
andauthored
feat(product-management): add brainstorming skill and /brainstorm command (#93)
* feat(product-management): add brainstorming skill and /brainstorm command The product-management plugin covers structured PM outputs (specs, roadmaps, stakeholder updates) but lacks support for the divergent thinking that precedes them. This adds a brainstorming skill and command for exploring problem spaces, generating ideas, and stress-testing product thinking. New files: - skills/product-brainstorming/SKILL.md — brainstorming modes (problem exploration, solution ideation, assumption testing, strategy exploration), PM frameworks (HMW, JTBD, First Principles, SCAMPER, Opportunity Solution Trees, Reverse Brainstorming), session structure, thinking partner behaviors, and anti-patterns - commands/brainstorm.md — conversational brainstorming command with tool-augmented context gathering and structured session flow Updated: - README.md — added brainstorming to What It Does, Commands, Skills tables, and Example Workflows Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * Add OODA Loop framework to product-brainstorming skill Adds Observe-Orient-Decide-Act as a brainstorming framework for competitive and time-pressured product decisions. Focuses on decision tempo and when to use OODA to break analysis paralysis in sessions. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
1 parent 9659c68 commit a518709

File tree

3 files changed

+408
-0
lines changed

3 files changed

+408
-0
lines changed

product-management/README.md

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -18,6 +18,7 @@ This plugin gives you an AI-powered product management partner that can help wit
1818
- **User Research Synthesis** — Turn interview notes, survey data, and support tickets into structured insights. Identifies themes, builds personas, and surfaces opportunity areas with supporting evidence.
1919
- **Competitive Analysis** — Research competitors and generate briefs with feature comparisons, positioning analysis, and strategic implications.
2020
- **Metrics Review** — Analyze product metrics, identify trends, compare against targets, and surface actionable insights.
21+
- **Product Brainstorming** — Explore problem spaces, generate ideas, and stress-test product thinking with a sharp sparring partner. Supports divergent ideation, assumption testing, and strategy exploration using frameworks like How Might We, Jobs-to-be-Done, First Principles, and Opportunity Solution Trees.
2122

2223
## Commands
2324

@@ -29,6 +30,7 @@ This plugin gives you an AI-powered product management partner that can help wit
2930
| `/synthesize-research` | Synthesize user research from interviews, surveys, and tickets |
3031
| `/competitive-brief` | Create a competitive analysis brief |
3132
| `/metrics-review` | Review and analyze product metrics |
33+
| `/brainstorm` | Brainstorm a product idea, problem space, or strategic question with a thinking partner |
3234

3335
## Skills
3436

@@ -40,6 +42,7 @@ This plugin gives you an AI-powered product management partner that can help wit
4042
| `user-research-synthesis` | Thematic analysis, affinity mapping, persona development, opportunity sizing |
4143
| `competitive-analysis` | Feature comparison matrices, positioning analysis, win/loss analysis |
4244
| `metrics-tracking` | Product metrics hierarchy, goal setting (OKRs), dashboard design, review cadences |
45+
| `product-brainstorming` | Brainstorming modes (problem exploration, solution ideation, assumption testing, strategy), PM frameworks, session structure, thinking partner behaviors |
4346

4447
## Example Workflows
4548

@@ -73,6 +76,18 @@ Claude: [Identifies themes, patterns, and insights across interviews]
7376
Claude: [Generates synthesis with key findings, personas, opportunity areas, and evidence]
7477
```
7578

79+
### Brainstorming a Product Idea
80+
81+
```
82+
You: /brainstorm Should we add AI-powered search to our product?
83+
Claude: Before we jump to AI search — what problem are your users hitting with search today?
84+
You: They can't find things. Support tickets about "can't find X" are our #2 category.
85+
Claude: That's a discovery problem, not necessarily a search technology problem. Let me push on this...
86+
Claude: [Explores whether the issue is search quality, information architecture, or content discoverability]
87+
Claude: [Generates 5 distinct approaches ranging from better taxonomy to AI search to guided navigation]
88+
Claude: [Challenges assumptions, suggests cheapest experiment to test the riskiest one]
89+
```
90+
7691
### Competitive Analysis
7792

7893
```
Lines changed: 120 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,120 @@
1+
---
2+
description: Brainstorm a product idea, problem space, or strategic question with a sharp thinking partner
3+
argument-hint: "<topic, problem, or idea to explore>"
4+
---
5+
6+
# /brainstorm
7+
8+
> If you see unfamiliar placeholders or need to check which tools are connected, see [CONNECTORS.md](../CONNECTORS.md).
9+
10+
Brainstorm a product topic with a sharp, opinionated thinking partner. This is a conversation, not a deliverable — the goal is to push thinking further than the PM would get alone.
11+
12+
## Usage
13+
14+
```
15+
/brainstorm $ARGUMENTS
16+
```
17+
18+
## How It Works
19+
20+
```
21+
┌────────────────────────────────────────────────────────────────┐
22+
│ BRAINSTORM │
23+
├────────────────────────────────────────────────────────────────┤
24+
│ STANDALONE (always works) │
25+
│ ✓ Explore problem spaces and opportunity areas │
26+
│ ✓ Generate and challenge product ideas │
27+
│ ✓ Stress-test assumptions and strategies │
28+
│ ✓ Apply PM frameworks (HMW, JTBD, First Principles, etc.) │
29+
│ ✓ Capture key ideas, next steps, and open questions │
30+
├────────────────────────────────────────────────────────────────┤
31+
│ SUPERCHARGED (when you connect your tools) │
32+
│ + Knowledge base: Pull prior research, specs, and decisions │
33+
│ + Analytics: Ground ideas in actual usage data │
34+
│ + Project tracker: Check what has been tried before │
35+
│ + Chat: Review recent team discussions for context │
36+
└────────────────────────────────────────────────────────────────┘
37+
```
38+
39+
## Workflow
40+
41+
### 1. Understand the Starting Point
42+
43+
The PM might bring any of these — identify which one and adapt:
44+
45+
- **A problem**: "Our users drop off during onboarding" — start in problem exploration mode
46+
- **A half-formed idea**: "What if we added a marketplace?" — start in assumption testing mode
47+
- **A broad question**: "How should we think about AI in our product?" — start in strategy exploration mode
48+
- **A constraint to work around**: "We need to grow without adding headcount" — start in solution ideation mode
49+
- **A vague instinct**: "Something feels off about our pricing" — start in problem exploration mode
50+
51+
Ask one clarifying question to frame the session, then dive in. Do not front-load a list of questions. The conversation should feel like two PMs at a whiteboard, not an intake form.
52+
53+
### 2. Pull Context (if available)
54+
55+
If **~~knowledge base** is connected:
56+
- Search for prior research, specs, or decision documents related to the topic
57+
- Surface relevant user research findings or customer feedback
58+
- Find previous brainstorming notes or exploration documents
59+
60+
If **~~product analytics** is connected:
61+
- Pull relevant usage data, adoption metrics, or behavioral patterns
62+
- Ground the brainstorm in real numbers rather than assumptions
63+
64+
If **~~project tracker** is connected:
65+
- Check if similar ideas have been explored, attempted, or shelved before
66+
- Look for related tickets, epics, or strategic themes
67+
68+
If **~~chat** is connected:
69+
- Search for recent team discussions on the topic
70+
- Surface relevant customer conversations or feedback threads
71+
72+
If these tools are not connected, work entirely from what the PM provides. Do not ask them to connect tools.
73+
74+
### 3. Run the Session
75+
76+
See the **product-brainstorming** skill for detailed guidance on brainstorming modes, frameworks, and session structure.
77+
78+
**Key behaviors:**
79+
- Be a sparring partner, not a scribe. React to ideas. Push back. Build on them. Suggest alternatives.
80+
- Match the PM's energy. If they are excited about a direction, explore it before challenging it.
81+
- Use frameworks when they help, not as a checklist. If "How Might We" unlocks new thinking, use it. If the conversation is already flowing, do not interrupt with a framework.
82+
- Push past the first idea. If the PM anchors on a solution early, acknowledge it, then ask for 3 more.
83+
- Name what you see. If the PM is solutioning before defining the problem, say so. If they are stuck in feature parity thinking, call it out.
84+
- Shift between divergent and convergent thinking. Open up when exploring. Narrow down when the PM has enough options on the table.
85+
- Keep the conversation moving. Do not let it stall on one idea. If a thread is exhausted, prompt a new angle.
86+
87+
**Session rhythm:**
88+
1. **Frame** — What are we exploring? What do we already know? What would a good outcome look like?
89+
2. **Diverge** — Generate ideas. Follow tangents. No judgment yet.
90+
3. **Provoke** — Challenge assumptions. Bring in unexpected perspectives. Play devil's advocate.
91+
4. **Converge** — What are the strongest 2-3 ideas? What makes them interesting?
92+
5. **Capture** — Document what emerged and what to do next.
93+
94+
### 4. Close the Session
95+
96+
When the conversation reaches a natural stopping point, offer a concise summary:
97+
98+
- **Key ideas** that emerged (2-5 ideas, each in 1-2 sentences)
99+
- **Strongest direction** and why you think so — take a position
100+
- **Riskiest assumption** for the strongest direction
101+
- **Suggested next step**: the single most useful thing to do next (research, prototype, talk to users, write a one-pager, run an experiment)
102+
- **Parked ideas**: interesting ideas that are worth revisiting but not right now
103+
104+
Do not generate the summary unprompted mid-conversation. Only summarize when the PM signals they are ready to wrap up, or when the conversation has naturally run its course.
105+
106+
### 5. Follow Up
107+
108+
After the session, offer:
109+
- "Want me to turn the top idea into a one-pager?" → `/one-pager` or `/write-spec`
110+
- "Want me to map this into an opportunity solution tree?"
111+
- "Want me to draft a research plan to test the riskiest assumption?" → `/synthesize-research`
112+
- "Want me to check how competitors approach this?" → `/competitive-brief`
113+
114+
## Tips
115+
116+
1. **This is a conversation, not a report.** Do not generate a 20-item idea list and hand it over. Engage with each idea. React. Build. Challenge.
117+
2. **One good question beats five mediocre suggestions.** The right provocative question unlocks more than a list of options.
118+
3. **Take positions.** "I think approach B is stronger because..." is more useful than presenting all options neutrally.
119+
4. **Name the traps.** If you see the PM falling into feature parity thinking, solutioning before framing, or anchoring on constraints — say so directly.
120+
5. **Know when to stop.** A brainstorm that goes too long produces fatigue, not ideas. If the PM has 2-3 strong directions and a clear next step, the session is done.

0 commit comments

Comments
 (0)