agentleFS
Tony363Tony363/SuperClaude/.claude/skills/sc-brainstorm/SKILL.md

sc-brainstorm

Skill19 starsChanged 8 months agoMITView on GitHub

Interactive requirements discovery through Socratic dialogue and systematic exploration. Use when transforming ambiguous ideas into concrete specifications, validating concepts, or coordinating multi-persona analysis.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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
  1. Distinctive:

    Handoff: - Create actionable briefs for implementation

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Brainstorming & Requirements Discovery Skill

Transform ambiguous ideas into concrete specifications through structured exploration.

Quick Start

# Basic brainstorm
/sc:brainstorm [topic]

# Deep systematic exploration
/sc:brainstorm "AI project management tool" --strategy systematic --depth deep

# Parallel exploration with multiple personas
/sc:brainstorm "real-time collaboration" --strategy agile --parallel

Behavioral Flow

  1. Explore - Transform ambiguous ideas through Socratic dialogue
  2. Analyze - Coordinate multiple personas for domain expertise
  3. Validate - Apply feasibility assessment across domains
  4. Specify - Generate concrete specifications
  5. Handoff - Create actionable briefs for implementation

Flags

FlagTypeDefaultDescription
--strategystringsystematicsystematic, agile, enterprise
--depthstringnormalshallow, normal, deep
--parallelboolfalseEnable parallel exploration paths
--validateboolfalseInclude feasibility validation

Personas Activated

  • architect - System design and technical feasibility
  • analyzer - Requirements analysis and complexity assessment
  • frontend - User experience and interface considerations
  • backend - API and data architecture
  • security - Security requirements and compliance
  • devops - Infrastructure and deployment considerations
  • project-manager - Timeline and resource planning

MCP Integration

PAL MCP (Collaborative Intelligence)

ToolWhen to UsePurpose
mcp__pal__consensusConflicting prioritiesMulti-model resolution of trade-offs
mcp__pal__chatBrainstormingCollaborative idea exploration with external model
mcp__pal__thinkdeepComplex problemsMulti-stage deep analysis
mcp__pal__plannerSolution designSequential planning with branching
mcp__pal__challengeValidate ideasForce critical thinking on proposed solutions

PAL Usage Patterns

# Consensus on conflicting priorities
mcp__pal__consensus(
    models=[
        {"model": "gpt-5.2", "stance": "for", "stance_prompt": "Prioritize user experience"},
        {"model": "gemini-3-pro", "stance": "against", "stance_prompt": "Prioritize technical simplicity"},
        {"model": "deepseek", "stance": "neutral"}
    ],
    step="Evaluate: Should we use real-time sync or eventual consistency?"
)

# Deep exploration of complex idea
mcp__pal__thinkdeep(
    step="Exploring AI-powered analytics dashboard concept",
    hypothesis="Users need predictive insights, not just historical data",
    confidence="medium",
    focus_areas=["user_needs", "technical_feasibility", "market_fit"]
)

# Collaborative brainstorming
mcp__pal__chat(
    prompt="Help me explore innovative approaches for real-time collaboration in document editing",
    model="gpt-5.2",
    thinking_mode="high"
)

# Challenge assumptions
mcp__pal__challenge(
    prompt="We assume users want AI-generated summaries. Is this assumption valid?"
)

# Plan solution architecture
mcp__pal__planner(
    step="Planning architecture for real-time notification system",
    step_number=1,
    total_steps=4,
    is_branch_point=True,
    branch_id="websocket-approach"
)

Rube MCP (Research & Persistence)

ToolWhen to UsePurpose
mcp__rube__RUBE_SEARCH_TOOLSMarket researchFind web search, competitor analysis tools
mcp__rube__RUBE_MULTI_EXECUTE_TOOLDocumentationSave ideas to Notion, share in Slack
mcp__rube__RUBE_CREATE_UPDATE_RECIPEWorkflowsSave brainstorming processes
mcp__rube__RUBE_REMOTE_WORKBENCHData analysisAnalyze market data, user research

Rube Usage Patterns

# Research market and competitors
mcp__rube__RUBE_SEARCH_TOOLS(queries=[
    {"use_case": "web search", "known_fields": "query:AI analytics dashboard competitors 2025"}
])

# Document brainstorming session
mcp__rube__RUBE_MULTI_EXECUTE_TOOL(tools=[
    {"tool_slug": "NOTION_CREATE_PAGE", "arguments": {
        "title": "Brainstorm: AI Analytics Dashboard",
        "content": "## Key Ideas\n- Predictive insights\n- Natural language queries\n\n## Decisions\n- Real-time sync chosen over eventual consistency"
    }},
    {"tool_slug": "SLACK_SEND_MESSAGE", "arguments": {
        "channel": "#product",
        "text": "New brainstorm session documented: AI Analytics Dashboard"
    }}
])

# Create user research tasks
mcp__rube__RUBE_MULTI_EXECUTE_TOOL(tools=[
    {"tool_slug": "JIRA_CREATE_ISSUE", "arguments": {
        "project": "PROD",
        "summary": "User research: AI analytics preferences",
        "issue_type": "Task",
        "description": "Interview 10 users about analytics needs"
    }},
    {"tool_slug": "ASANA_CREATE_TASK", "arguments": {
        "name": "Competitor analysis: analytics dashboards",
        "project": "Research"
    }}
])

# Analyze existing user feedback
mcp__rube__RUBE_REMOTE_WORKBENCH(
    thought="Analyze user feedback data for patterns",
    code_to_execute='''
import json
# Load user feedback from file
feedback_data = json.load(open("/tmp/user_feedback.json"))
# Analyze with LLM
analysis, error = invoke_llm(f"Analyze this user feedback for analytics feature requests: {feedback_data[:5000]}")
output = {"analysis": analysis, "feedback_count": len(feedback_data)}
output
'''
)

Flags (Extended)

FlagTypeDefaultDescription
--pal-consensusboolfalseUse PAL consensus for trade-offs
--pal-deepboolfalseUse PAL thinkdeep for complex exploration
--researchboolfalseUse Rube for market/competitor research
--documentstring-Document to Rube (notion, confluence, google-docs)
--notifystring-Notify via Rube (slack, teams, email)

Evidence Requirements

This skill does NOT require hard evidence. Focus on:

  • Documenting exploration paths and decisions
  • Recording stakeholder input and priorities
  • Capturing specifications and requirements

Exploration Strategies

Systematic (--strategy systematic)

  • Structured question-driven discovery
  • Comprehensive domain coverage
  • Documentation-heavy approach

Agile (--strategy agile)

  • Rapid iteration cycles
  • User story focused
  • Minimal viable specification

Enterprise (--strategy enterprise)

  • Compliance and governance focus
  • Stakeholder alignment
  • Risk assessment integration

Examples

Product Discovery

/sc:brainstorm "AI-powered analytics dashboard" --strategy systematic --depth deep
# Multi-persona analysis with comprehensive feasibility

Feature Exploration

/sc:brainstorm "real-time notifications" --strategy agile --parallel
# Parallel paths: frontend UX, backend architecture, security implications

Enterprise Solution

/sc:brainstorm "enterprise data platform" --strategy enterprise --validate
# Compliance-aware exploration with security and devops input

Tool Coordination

  • Read/Write - Requirements documentation
  • TodoWrite - Exploration progress tracking
  • Task - Parallel exploration delegation
  • WebSearch - Market research and technology validation

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.