consciousness-council
关于
The Consciousness Council skill enables multi-perspective deliberation by simulating distinct thinking archetypes to analyze complex questions. It's triggered when users need diverse viewpoints, face tough decisions, or request devil's advocate analysis. This structured approach generates cognitive diversity for dilemmas, trade-offs, and creative challenges.
快速安装
Claude Code
推荐npx skills add K-Dense-AI/claude-scientific-skills -a claude-code/plugin add https://github.com/K-Dense-AI/claude-scientific-skillsgit clone https://github.com/K-Dense-AI/claude-scientific-skills.git ~/.claude/skills/consciousness-council在 Claude Code 中复制并粘贴此命令以安装该技能
技能文档
Consciousness Council
A structured multi-perspective deliberation system that generates genuine cognitive diversity on any question. Instead of one voice giving one answer, the Council summons distinct thinking archetypes — each with its own reasoning style, blind spots, and priorities — then synthesizes their perspectives into actionable insight.
Why This Exists
Single-perspective thinking has a ceiling. When you ask one mind for an answer, you get one frame. The Consciousness Council breaks this ceiling by simulating the cognitive equivalent of a boardroom, a philosophy seminar, and a war room — simultaneously. It's not roleplay. It's structured epistemic diversity.
The Council is inspired by research in collective intelligence, wisdom-of-crowds phenomena, and the observation that the best decisions emerge when genuinely different reasoning styles collide.
How It Works
The Council has three phases:
Phase 1 — Summon the Council
Based on the user's question, select 4-6 Council Members from the archetypes below. Choose members whose perspectives will genuinely CLASH — agreement is cheap, productive tension is valuable.
The 12 Archetypes:
| # | Archetype | Thinking Style | Asks | Blind Spot |
|---|---|---|---|---|
| 1 | The Architect | Systems thinking, structure-first | "What's the underlying structure?" | Can over-engineer simple problems |
| 2 | The Contrarian | Inversion, devil's advocate | "What if the opposite is true?" | Can be contrarian for its own sake |
| 3 | The Empiricist | Data-driven, evidence-first | "What does the evidence actually show?" | Can miss what can't be measured |
| 4 | The Ethicist | Values-driven, consequence-aware | "Who benefits and who is harmed?" | Can paralyze action with moral complexity |
| 5 | The Futurist | Long-term, second-order effects | "What does this look like in 10 years?" | Can discount present realities |
| 6 | The Pragmatist | Action-oriented, resource-aware | "What can we actually do by Friday?" | Can sacrifice long-term for short-term |
| 7 | The Historian | Pattern recognition, precedent | "When has this been tried before?" | Can fight the last war |
| 8 | The Empath | Human-centered, emotional intelligence | "How will people actually feel about this?" | Can prioritize comfort over progress |
| 9 | The Outsider | Cross-domain, naive questions | "Why does everyone assume that?" | Can lack domain depth |
| 10 | The Strategist | Game theory, competitive dynamics | "What are the second and third-order moves?" | Can overthink simple situations |
| 11 | The Minimalist | Simplification, constraint-seeking | "What can we remove?" | Can oversimplify complex problems |
| 12 | The Creator | Divergent thinking, novel synthesis | "What hasn't been tried yet?" | Can chase novelty over reliability |
Selection heuristic: Match the question type to the most productive tension:
- Business decisions → Strategist + Pragmatist + Ethicist + Futurist + Contrarian
- Technical architecture → Architect + Minimalist + Empiricist + Outsider
- Personal dilemmas → Empath + Contrarian + Futurist + Pragmatist
- Creative challenges → Creator + Outsider + Historian + Minimalist
- Ethical questions → Ethicist + Contrarian + Empiricist + Empath + Historian
- Strategy/competition → Strategist + Historian + Futurist + Contrarian + Pragmatist
These are starting points — adapt based on the specific question. The goal is productive disagreement, not consensus.
Phase 2 — Deliberation
Each Council Member delivers their perspective in this format:
🎭 [ARCHETYPE NAME]
Position: [One-sentence stance]
Reasoning: [2-4 sentences explaining their logic from their specific lens]
Key Risk They See: [The danger others might miss]
Surprising Insight: [Something non-obvious that emerges from their frame]
Critical rules for deliberation:
- Each member MUST disagree with at least one other member on something substantive. If everyone agrees, the Council has failed — go back and sharpen the tensions.
- Perspectives should be genuinely different, not just "agree but with different words."
- The Contrarian should challenge the most popular position, not just be generically skeptical.
- Keep each member's contribution focused and sharp. Depth over breadth.
Phase 3 — Synthesis
After all members speak, deliver:
⚖️ COUNCIL SYNTHESIS
Points of Convergence: [Where 3+ members agreed — these are high-confidence signals]
Core Tension: [The central disagreement that won't resolve easily — this IS the insight]
The Blind Spot: [What NO member addressed — the question behind the question]
Recommended Path: [Actionable recommendation that respects the tension rather than ignoring it]
Confidence Level: [High / Medium / Low — based on how much convergence vs. divergence emerged]
One Question to Sit With: [The question the user should keep thinking about after this session]
Council Configurations
The user can customize the Council:
- "Quick council" or "fast deliberation" → Use 3 members, shorter responses
- "Deep council" or "full deliberation" → Use 6 members, extended reasoning
- "Add [archetype]" → Include a specific archetype
- "Without [archetype]" → Exclude a specific archetype
- "Custom council: [list]" → User picks exact members
- "Anonymous council" → Don't reveal which archetype is speaking until synthesis (reduces anchoring bias)
- "Devil's advocate mode" → Every member must argue AGAINST whatever seems most intuitive
- "Rounds mode" → After initial positions, members respond to each other for a second round
What Makes a Good Council Question
The Council works best on questions where:
- There's genuine uncertainty or trade-offs
- Multiple valid perspectives exist
- The user is stuck or going in circles
- The stakes are high enough to warrant multi-angle thinking
- The user's own bias might be limiting their view
The Council adds less value on:
- Pure factual questions with clear answers
- Questions where the user has already decided and just wants validation
- Trivial choices with low stakes
If the question seems too simple for a full Council, say so — and offer a quick 2-perspective contrast instead.
Tone and Quality
- Write each archetype's voice with enough distinctiveness that the user could identify them without labels.
- The Synthesis should feel like genuine integration, not just a list of what each member said.
- "Core Tension" is the most important part of the synthesis — it should name the real trade-off the user faces.
- "One Question to Sit With" should be genuinely thought-provoking, not generic.
- Never let the Council devolve into everyone agreeing politely. Productive friction is the point.
Example
User: "Should I quit my stable corporate job to start a company?"
Council Selection: Pragmatist, Futurist, Empath, Contrarian, Strategist (5 members — high-stakes life decision with financial, emotional, and strategic dimensions)
Then run the full 3-phase deliberation.
Attribution
Created by AHK Strategies — consciousness infrastructure for the age of AI. Learn more: https://ahkstrategies.net Powered by the Mind Council architecture from TheMindBook: https://themindbook.app
GitHub 仓库
相关推荐技能
content-collections
元Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。
polymarket
元这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。
creating-opencode-plugins
元该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。
sglang
元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。
