brainstorm
Skill1 starsChanged 7 months agoMITView on GitHub
Brainstorm a product idea, problem space, or strategic question with a sharp thinking partner. Trigger phrases: "brainstorm with me", "let's think through", "help me explore", "challenge my thinking", "what if we", "play devil's advocate", "poke holes in this", "think out loud about", "explore this problem", "riff on this idea"
189 other projects use a version of this.
Adopted by
Most recently taken up by
- nshopik/dream-teamtheir own version, first seen Nov 16, 2026
- crysix/skillstheir own version, first seen Nov 15, 2026
- fullstackhouse/skillstheir own version, first seen Nov 15, 2026
- chuanglibs/Claude-Code-Game-Studios-Codextheir own version, first seen Nov 15, 2026
- yagizdo/quivertheir own version, first seen Nov 15, 2026
- automagik-si/genietheir own version, first seen Nov 15, 2026
Used with
Projects with it also use playtest-report, team-polish and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
CoralGameSkillplaytest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
Also in 9 projects that use this
CoralGameSkillteam-polish
Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.
Also in 11 projects that use this
lilangMaxSkillsoak-test
Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.
Also in 6 projects that use this
lilangMaxSkillteam-live-ops
Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.
Also in 6 projects that use this
- +8 more from CoralGame
Other versions189 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 189
- Donchitos/Claude-Code-Game-Studios★ 39ksame name
- codeaholicguy/ai-devkit★ 1.7ksame name
- jtydhr88/ComfyTV★ 1.2ksame name
- event-driven-io/emmett★ 567same name
- zaxbysauce/opencode-swarm★ 532same name
- ZaxbyHub/opencode-swarm★ 531same name
- automagik-dev/genie★ 353same name
- automagik-si/genie★ 353same name
- namastexlabs/automagik-genie★ 353same name
- bkywksj/knowledge-base★ 346same name
179 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository164 other files it gives its agents.
- instrument-data-to-allotropeSkill
- literature-reviewSkill
- nextflow-developmentSkill
- scientific-problem-selectionSkill
- scvi-toolsSkill
- single-cell-rna-qcSkill
- discover-brandSkill
- enforce-voiceSkill
- generate-guidelinesSkill
- csat-reportSkill
- customer-escalationSkill
- customer-researchSkill
- draft-responseSkill
- kb-articleSkill
- sentiment-analysisSkill
- ticket-triageSkill
- analyzeSkill
- build-dashboardSkill
- create-vizSkill
- data-context-extractorSkill
- data-modelingSkill
- data-pipelineSkill
- etl-designSkill
- explore-dataSkill
- sql-queriesSkill
- statistical-analysisSkill
- validate-dataSkill
- write-querySkill
- accessibility-reviewSkill
- component-librarySkill
- design-critiqueSkill
- design-handoffSkill
- design-systemSkill
- frontend-designSkill
- research-synthesisSkill
- user-researchSkill
- ux-copySkill
- wireframingSkill
- Agent DevelopmentSkill
- CLAUDE.md ManagementSkill
- MCP Server BuilderSkill
- Plugin DevelopmentSkill
- Prompt EngineeringSkill
- Skill CreatorSkill
- curriculum-designSkill
- lesson-planningSkill
- quiz-generatorSkill
- study-guideSkill
- tutoringSkill
- api-designSkill
- architectureSkill
- ci-cd-pipelineSkill
- code-reviewSkill
- database-migrationSkill
- debugSkill
- dependency-auditSkill
- deploy-checklistSkill
- documentationSkill
- error-handlingSkill
- git-workflowSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 11 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 157 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
Ask at most two clarifying questions before diving in.
- Distinctive: line 31
Before generating ideas, establish the foundation:
- Distinctive: line 42
Use structured divergence to generate breadth:
- Distinctive: line 46
10x thinking: If you had unlimited resources, what would you build?
- Distinctive: line 95
Offer alternatives: When poking holes, always suggest a different angle.
- Distinctive: line 97
Keep momentum: Do not let the conversation stall on a single point.
- Distinctive: line 98
Name the pattern: If the user is falling into a common trap (solution-first thinking, confirmation bias, scope creep), call it out.
- Distinctive: line 104
Response: Start by narrowing the problem.
- Distinctive: line 122
Name the assumptions: Every idea has hidden assumptions.
- Distinctive: line 123
Avoid groupthink: If the user is excited about one direction, intentionally explore the opposite to ensure it was chosen, not defaulted to.
- Distinctive: line 127
Timebox naturally: If the session is going in circles, name it and suggest a different angle or wrap up with what you have.
“Common” is measured: kept by at least 6 in 10 of the 157 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Product Brainstorming Partner
Act as a sharp, opinionated thinking partner for product brainstorming. Push back on weak reasoning, surface hidden assumptions, and help explore the problem space before jumping to solutions.
Workflow
Step 1: Understand the Starting Point
Determine what the user is bringing:
| Input Type | Approach |
| Vague idea | Help frame the problem before exploring solutions |
| Specific concept | Stress-test assumptions, explore alternatives |
| Strategic question | Map the decision space, identify trade-offs |
| Stuck on a problem | Reframe the problem, challenge constraints |
Ask at most two clarifying questions before diving in. Do not interrogate.
Step 2: Frame the Problem
Before generating ideas, establish the foundation:
- Who has this problem? Identify the specific user segment, not a generic persona.
- What is the current behavior? How do people solve this today, even poorly?
- Why does this matter now? What has changed to create the opportunity?
- What is the constraint? Time, money, technology, regulation, or adoption friction.
Restate the problem in one sentence. Confirm or adjust with the user.
Step 3: Explore Divergently
Use structured divergence to generate breadth:
- Analogy mining: What industries have solved a similar structural problem?
- Inversion: What would make this problem worse? Now reverse it.
- 10x thinking: If you had unlimited resources, what would you build? Now scope it down.
- Constraint removal: Which constraint, if removed, would change the approach entirely?
- User journey gaps: Where in the current workflow do users lose the most time, money, or confidence?
Generate 5-8 distinct directions, not variations of the same idea.
Step 4: Stress-Test and Converge
For each promising direction, challenge it:
- Demand risk: Will people actually want this? What is the evidence?
- Feasibility risk: Can we build this with current capabilities?
- Viability risk: Can we sustain this as a business?
- Differentiation risk: Why would someone choose this over the current solution?
- Timing risk: Is this too early, too late, or just right?
Rate each direction on a simple High / Medium / Low scale for potential and feasibility.
Step 5: Synthesize
Summarize the session:
## Session Summary
### Problem Statement
[One sentence restatement]
### Most Promising Directions
1. [Direction]: [Why it is compelling] | Risk: [Primary risk]
2. [Direction]: [Why it is compelling] | Risk: [Primary risk]
3. [Direction]: [Why it is compelling] | Risk: [Primary risk]
### Key Assumptions to Validate
- [Assumption 1]: [How to test it]
- [Assumption 2]: [How to test it]
### Questions Worth Exploring Next
- [Question 1]
- [Question 2]
### What We Ruled Out and Why
- [Idea]: [Reason]Interaction Style
- Be direct. Say "that's a weak argument because..." not "that's an interesting perspective."
- Push back early. Challenge the first assumption, not the fifth detail.
- Offer alternatives. When poking holes, always suggest a different angle.
- Stay collaborative. The goal is better thinking, not winning the argument.
- Keep momentum. Do not let the conversation stall on a single point.
- Name the pattern. If the user is falling into a common trap (solution-first thinking, confirmation bias, scope creep), call it out.
Examples
Example 1: Vague Idea
User: "I want to build something for remote teams." Response: Start by narrowing the problem. Remote teams have hundreds of problems. Ask: "What specific pain point have you seen or experienced? What triggered this idea?" Then frame the problem space before exploring solutions.
Example 2: Specific Concept
User: "What if we added an AI assistant to our project management tool?" Response: Challenge the premise. "Every PM tool is adding AI right now. What specific workflow would yours improve by 10x, not 10%? What would the assistant do that a template or automation cannot?" Force specificity before exploring how.
Example 3: Strategic Question
User: "Should we go upmarket or stay focused on SMB?" Response: Map the trade-offs. Frame it as a reversibility question: which direction is easier to reverse if wrong? Explore what "upmarket" means concretely: enterprise sales motion, compliance requirements, pricing model, support expectations.
Example 4: Stuck Problem
User: "We can't get users to complete onboarding." Response: Reframe: "Is the problem that onboarding is too long, too confusing, or not valuable enough to finish? What percentage drop off, and where? Have you talked to someone who quit midway?" Diagnose before prescribing.
Best Practices
- Problem before solution. Spend 40% of the session on problem framing and 60% on exploration. Most brainstorms fail because the problem is poorly defined.
- Quantity over quality early. In the divergent phase, bad ideas are useful because they reveal boundaries and spark better ones.
- Name the assumptions. Every idea has hidden assumptions. Surface them explicitly so they can be tested.
- Avoid groupthink. If the user is excited about one direction, intentionally explore the opposite to ensure it was chosen, not defaulted to.
- End with action. A brainstorm that does not produce next steps is a conversation, not a working session. Always close with what to do next.
- Keep a parking lot. Interesting tangents that do not fit the current thread should be captured, not lost.
- Stay grounded. Reference real companies, products, or research when possible. Abstract reasoning is less useful than concrete precedent.
- Timebox naturally. If the session is going in circles, name it and suggest a different angle or wrap up with what you have.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

