MCP HubMCP Hub
返回技能列表

brainstorming-skill

Jamie-BitFlight
更新于 Today
14 次查看
2
1
2
在 GitHub 上查看
aidesign

关于

This skill provides structured brainstorming capabilities using 30+ research-validated prompt patterns across 14 categories. It's designed for ideation tasks like content planning, product features, and creative problem-solving, offering exact templates with success metrics. Developers should activate it when users need systematic idea generation or creative solution exploration.

技能文档

Brainstorming Skill

Overview

This skill provides comprehensive, research-validated brainstorming patterns and prompt templates to help generate high-quality ideas across any domain. It contains 30+ documented patterns from 14 primary sources, organized into systematic categories with exact prompt wording, output format specifications, and proven success metrics.

When to Use This Skill

Activate this skill when users need:

<trigger_scenarios>

  • Idea generation for products, features, or content
  • Creative problem-solving approaches
  • Marketing campaign concepts
  • Strategic planning and decision-making
  • Content creation (blog posts, social media, presentations)
  • Product feature ideation
  • Business strategy development
  • Creative writing (plot development, character creation)
  • QA test case brainstorming
  • Innovation workshops or facilitation
  • Breaking through creative blocks
  • Systematic exploration of solution spaces </trigger_scenarios>

Pattern Categories

The skill organizes brainstorming patterns into 14 systematic categories. Each pattern includes exact prompt templates, output format specifications, concrete examples, and reported success metrics.

Core Pattern Categories

<category_index>

  1. Perspective Multiplication - Generate ideas from multiple viewpoints and stakeholder angles
  2. Constraint Variation - Explore idea space through artificial constraints
  3. Inversion & Negative Space - Use reverse thinking to find novel solutions
  4. Analogical Transfer - Apply patterns from different domains
  5. Systematic Feature Decomposition - SCAMPER and attribute-based ideation
  6. Scenario Exploration - Future-based and "what if" thinking
  7. Constraint-Based Structured Ideation - Build within hard constraints
  8. Chain-of-Thought Reasoning - Multi-step refinement processes
  9. Combination & Morphological Exploration - Force novel feature combinations
  10. Assumption Challenge - Question premises and invert assumptions
  11. Fill-in-the-Blank Templates - Structured completion formats
  12. Competitive Positioning - Differentiation matrix approaches
  13. Extreme Scaling - 10x thinking and exponential scenarios
  14. Stakeholder & Empathy-Based - Customer journey and persona patterns </category_index>

Quick Pattern Selection

<selection_guide> For rapid quantity (8-15 ideas): Use Perspective Multiplication patterns For quality/depth: Use Multi-stage refinement with constraint variation For breakthrough innovation: Combine Inversion + Extreme Scaling For practical implementation: Use Constraint-Based patterns For market differentiation: Use Competitive Positioning patterns For customer-centric features: Use Stakeholder & Empathy patterns </selection_guide>

Key Research Findings

<research_insights>

  • Constraint-based patterns generate 20-30% MORE ideas than open-ended prompts
  • Specifying output format (table/numbered list) improves quality without reducing quantity
  • Multiple perspective iteration (3-5 viewpoints) consistently outperforms single-perspective
  • Requiring reasoning visibility ("explain why") increases implementability by 40%
  • Successful patterns share: role definition, constraint specification, output format, reasoning requirements </research_insights>

Pattern Documentation

Complete pattern documentation is organized in reference files:

Main Pattern Categories

Pattern Categories and Documentation - All 14 categories with 30+ patterns, exact templates, examples, and success metrics (1,303 lines)

Domain Applications

Domain-Specific Applications - Marketing, Product Development, QA Testing, Business Strategy, Creative Writing patterns

Supporting Guides

Pattern Selection Guide - Decision framework for choosing appropriate patterns Synthesis: What Makes Patterns Work - Common structural elements and effectiveness analysis Comprehensive Prompt Library - Ready-to-use templates organized by use case Executive Summary - High-level overview and key findings

Bibliographic Research

Research from authoritative sources with verified prompt patterns:

Primary Pattern Sources:

Academic & Research Sources:

Practical Application Sources:

Source Documentation

Bibliography and Source Documentation - Complete citations with URLs Verification Note - Evidence strength assessment

Using This Skill

<usage_workflow> Step 1: Identify the brainstorming goal (quantity, quality, innovation level, domain) Step 2: Consult Pattern Selection Guide to choose appropriate pattern category Step 3: Load relevant pattern documentation for exact templates Step 4: Apply pattern with user's specific context Step 5: If needed, combine patterns or iterate with constraint variation </usage_workflow>

Pattern Application Examples

<example_simple> User: "Help me brainstorm marketing campaign ideas" Pattern: Perspective Multiplication (Pattern 1A: Role-Based Persona) Approach: Generate ideas from Customer Success Manager, Sales VP, and Product Manager perspectives Expected Output: 15 ideas with reasoning from each viewpoint </example_simple>

<example_constraint> User: "Generate product features with $20k budget, 4-week timeline" Pattern: Constraint Variation (Pattern 2B: Resource Type Constraints) Approach: Use exact budget/time constraints to force creative solutions within reality Expected Output: 5 implementable features with resource breakdowns </example_constraint>

<example_innovation> User: "Break through conventional thinking on user onboarding" Pattern: Inversion (Pattern 3A: Worst Possible Idea) + Analogical Transfer (Pattern 4A) Approach: First invert ("worst onboarding"), then apply cross-domain analogies (Netflix, hotel service) Expected Output: 3-5 genuinely novel approaches that competitors miss </example_innovation>

Output Format Optimization

<format_guidance> Successful brainstorming patterns specify exact output formats:

  • "Numbered list" > "bullet points" (better for idea tracking)
  • "Table format: Idea | Reasoning | Implementation | Trade-offs" (forces completeness)
  • "For each idea, explain your reasoning" (increases quality 40%)
  • Specify word count ranges (200-400 words prevents both brevity and verbosity) </format_guidance>

Skill Resources

This skill contains:

  • references/ - Pattern documentation, research sources, domain guides
  • scripts/ - (Optional: future automation for pattern selection, template generation)
  • assets/ - (Optional: future workshop templates, ideation canvases)

All pattern content is verified against original sources. No fabricated patterns or unverified claims.

Notes for Claude Instances

<ai_instructions> When using this skill:

  • Always verify pattern category matches user's actual need
  • Provide exact prompt templates from reference files, not paraphrased versions
  • Cite source files when referencing specific patterns
  • Combine patterns when single pattern insufficient
  • Adjust templates to user's specific context while preserving structural elements
  • Use progressive disclosure: start with pattern overview, load detailed references as needed </ai_instructions>

快速安装

/plugin add https://github.com/Jamie-BitFlight/claude_skills/tree/main/brainstorming-skill

在 Claude Code 中复制并粘贴此命令以安装该技能

GitHub 仓库

Jamie-BitFlight/claude_skills
路径: brainstorming-skill

相关推荐技能

llamaguard

其他

LlamaGuard是Meta推出的7-8B参数内容审核模型,专门用于过滤LLM的输入和输出内容。它能检测六大安全风险类别(暴力/仇恨、性内容、武器、违禁品、自残、犯罪计划),准确率达94-95%。开发者可通过HuggingFace、vLLM或Sagemaker快速部署,并能与NeMo Guardrails集成实现自动化安全防护。

查看技能

sglang

SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。

查看技能

evaluating-llms-harness

测试

该Skill通过60+个学术基准测试(如MMLU、GSM8K等)评估大语言模型质量,适用于模型对比、学术研究及训练进度追踪。它支持HuggingFace、vLLM和API接口,被EleutherAI等行业领先机构广泛采用。开发者可通过简单命令行快速对模型进行多任务批量评估。

查看技能

langchain

LangChain是一个用于构建LLM应用程序的框架,支持智能体、链和RAG应用开发。它提供多模型提供商支持、500+工具集成、记忆管理和向量检索等核心功能。开发者可用它快速构建聊天机器人、问答系统和自主代理,适用于从原型验证到生产部署的全流程。

查看技能