creative-thinking-for-research by orchestra-research/ai-research-skills
npx skills add https://github.com/orchestra-research/ai-research-skills --skill creative-thinking-for-research源自认知科学的八个实证支撑框架,应用于计算机科学和人工智能研究。与临时性的头脑风暴不同,这里的每个框架都有数十年的创造力研究作为后盾——从 Koestler 的异类联想到 Kauffman 的相邻可能。它们针对不同的认知操作:组合、重构、类比、约束、反转、抽象、探索边界以及容纳矛盾。
在以下情况请勿使用此技能:
brainstorming-research-ideas)scientific-skills:literature-review)与头脑风暴技能的关系:头脑风暴技能提供操作性的工作流程(发散 → 收敛 → 精炼)和实用的过滤器。此技能则提供驱动创造性飞跃的更深层次的认知引擎。将它们结合使用:用创造性思维产生原始见解,用头脑风暴来构建和评估它。
新颖的想法源于以意想不到的方式组合现有概念。Arthur Koestler 称之为异类联想——连接两个先前无关的参照系,这与单一参照系内的常规联想不同。
其原理:元研究一致表明,知识的广度是创造性产出的先决条件。跨学科阅读的人能产生更多新颖的工作。组合本身就是创造性的行为。
在计算机科学研究中:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
系统性异类联想工作流程:
叉积示例:
| 缓存 | 负载均衡 | 容错
---|---|---|---
自然选择 | 淘汰最不适应的条目 | 通过适应度进行自适应分配 | 群体级冗余
免疫记忆 | 学习到的威胁特征 | 分布式检测 | 自我/非我识别
共生 | 协作式预取 | 互惠资源共享 | 相互依赖的弹性
质量检验:一个强大的异类联想不是表面的隐喻("网络就像大脑"),而是一种结构映射,其中机制可以迁移("注意力机制实现了一种选择性门控形式,类似于认知注意力过滤")。
自检:
格式塔心理学家发现,突破往往不是来自解决陈述的问题,而是来自重新表述问题本身。Kaplan 和 Simon 关于顿悟的研究表明,改变问题空间——约束、抽象层次、形式化——通常是创造力的所在。
关键转变:从"我如何解决这个问题?"到"我是否正确地思考了这个问题?"
重构策略:
| 策略 | 示例 |
|---|---|
| 改变目标 | "使算法更快" → "消除这种计算的需要" |
| 改变形式化方法 | 图问题 → 线性代数问题(谱方法) |
| 改变粒度 | 按标记预测 → 按跨度预测 |
| 改变主体 | "模型应该如何学习?" → "数据应该如何教学?"(课程学习) |
| 改变时间尺度 | 实时优化 → 摊销推理 |
| 反转方向 | 前向模拟 → 逆问题(从观察中学习) |
工作流程:
经典的计算机科学示例:
Dedre Gentner 的结构映射理论和 Kevin Dunbar 对真实科学家的研究表明,类比是科学创造力的核心引擎。关键发现是:表面层次的类比很常见但很弱;结构或关系类比——深层因果/关系结构跨领域映射——产生最强大的见解。
Dunbar 的发现:在最成功的实验室中,来自遥远领域的类比驱动了最重要的发现。邻近的类比完善了想法;遥远的类比则产生了它们。
类比深度层次:
| 层次 | 描述 | 价值 | 示例 |
|---|---|---|---|
| 表面 | 事物看起来相似 | 低 | "神经网络就像大脑" |
| 关系 | 实体之间的关系匹配 | 中 | "模型中的注意力分配类似于经济学中的资源分配" |
| 结构 | 深层因果机制映射 | 高 | "扩散模型逆转了一个热力学过程;非平衡统计力学的数学直接适用" |
结构映射工作流程:
验证清单:
Margaret Boden 的框架根据与约束的交互方式区分了三种形式的创造力:
| 类型 | 操作 | 计算机科学示例 |
|---|---|---|
| 探索性 | 在现有概念空间内搜索 | 超参数调优,固定范式内的架构搜索 |
| 组合性 | 组合来自不同空间的元素 | 多任务学习,神经符号方法 |
| 变革性 | 改变空间本身的规则 | 放弃训练需要标签的假设(自监督学习) |
变革性创造力是最罕见且影响最大的。 它发生在你改变什么被视为有效解决方案的时候。
约束分析工作流程:
约束转换的经典示例:
取你所在领域的一个核心假设并否定它。这在 De Bono 的水平思考和工程中的 TRIZ 方法论中得到了形式化。
模式:"如果[广泛持有的假设]是错误的、不必要的或可逆的,会怎样?"
系统性否定工作流程:
计算机科学中的否定名人堂:
| 假设 | 否定 | 结果 |
|---|---|---|
| "我们需要强一致性" | 如果我们不需要呢? | 最终一致性,CRDTs |
| "我们需要精确答案" | 如果近似也可以呢? | 草图,LSH,近似最近邻 |
| "标签是必要的" | 如果我们没有标签也能学习呢? | 自监督学习,对比方法 |
| "更多参数 = 更多计算" | 如果我们不使用所有参数呢? | 专家混合,稀疏模型 |
| "训练和推理是分开的" | 如果模型持续学习呢? | 在线学习,测试时训练 |
| "错误必须被防止" | 如果我们接受并纠正它们呢? | 推测解码,自我纠正 |
受 TRIZ 启发的计算机科学原则:
| TRIZ 原则 | 计算机科学应用 |
|---|---|
| 反转 | 逆转过程(生成式 vs. 判别式) |
| 分割 | 将整体分解为模块化(微服务,专家混合) |
| 合并 | 合并独立的步骤(端到端学习) |
| 通用性 | 一个组件服务于多个功能(多任务模型) |
| 嵌套 | 将一个系统放在另一个内部(元学习) |
| 动态化 | 使静态事物具有适应性(动态架构,自适应计算) |
在抽象阶梯上上下移动是一种基本的创造性行为。Polya 的启发式方法将其形式化:"你能解决一个更一般的问题吗?一个更具体的问题吗?一个类似的问题吗?"
三种移动:
| 移动 | 问题 | 结果 |
|---|---|---|
| 泛化 | "我的解决方案是更广泛事物的特例吗?" | 框架论文,统一理论 |
| 特化 | "当我添加极端约束时会发生什么?" | 利基应用,令人惊讶的边缘情况 |
| 类比 | "这个抽象模式还出现在哪里?" | 跨领域迁移(参见框架 3) |
泛化工作流程:
特化工作流程:
何时泛化 vs. 特化:
Stuart Kauffman 提出、由 Steven Johnson 推广的概念:创新发生在当前可达到的边界——相邻可能。一旦其先决条件存在,新想法就变得可思考。这解释了为什么同时独立发现如此普遍——多人到达了相同的边界。
实际意义:映射最近变得可能的事物,并探索这些使能因素所打开的空间。
相邻可能映射工作流程:
当前的相邻可能(2025-2026):
| 使能因素 | 新近可能 |
|---|---|
| 100 万+ token 的上下文窗口 | 全代码库推理,书籍长度分析 |
| 推理成本下降(2 年内 100 倍) | 实时智能体循环,常开 AI 助手 |
| 达到 GPT-4 水平的开放权重模型 | 关于前沿能力的可复现研究 |
| 多模态模型(视觉 + 语言 + 音频) | 统一的感知-推理系统 |
| 大规模合成数据 | 用于没有自然数据领域的训练数据 |
| 使用工具模型 | 研究自动化,自我改进系统 |
时机信号:如果你的想法需要尚不存在的技术,它就超出了相邻可能——搁置它。如果你的想法在 5 年前就可以实现,可能已经有人做了——查阅文献。最佳时机是那些在过去 6-18 个月内变得可行的想法。
Albert Rothenberg 对杰出创造者的研究发现,同时持有两个相互矛盾的想法是创造性思维的一个标志。以罗马双面神 Janus 命名,这种思维模式不是通过选择一方来解决矛盾——而是生成超越对立的新框架。
在计算机科学中:最具影响力的结果往往来自先前被认为不可调和的张力。
| 矛盾 | 解决方案 | 影响 |
|---|---|---|
| 一致性 AND 可用性(分布式系统) | CAP 定理:形式化了权衡,然后 Raft/CRDTs 找到了实际的中间地带 | 分布式系统理论的基础 |
| 安全性 AND 可用性 | 零知识证明:证明知识而不泄露知识 | 实现了隐私计算 |
| 表达力 AND 可处理性 | 概率编程:表达复杂模型,自动化推理 | 新的编程范式 |
| 记忆化 AND 泛化 | 顿悟:模型先记忆,然后通过更多训练进行泛化 | 对学习动态的新理解 |
| 压缩 AND 质量 | 神经编解码器通过学习的先验压缩到信息论极限之外 | 重新定义了压缩研究 |
辩证思维工作流程:
自检:
这些框架在组合使用时最为强大。以下是一个用于深度创造性思维会议的系统性协议:
应用两句话测试(来自头脑风暴技能):
"[领域] 目前因 [原因] 而在 [问题] 上挣扎。 我们通过 [机制] 采用 [方法],这之所以有效是因为 [见解]。"
任何通过所有四个阶段并通过两句话测试的想法都值得追求。
| 障碍 | 症状 | 应应用的框架 |
|---|---|---|
| 思维定势 | 无法停止以一种方式思考问题 | 问题重构(F2)——强制采用不同的表征 |
| 隧道视野 | 所有想法都来自同一子领域 | 异类联想(F1)或类比推理(F3)——从其他地方引入 |
| 自我审查 | 在探索之前就将想法视为"太奇怪"而驳回 | 否定(F5)——奇怪正是关键;生成后再评估 |
| 渐进主义 | 每个想法都是"在基准 X 上提升 2%" | 约束操作(F4)——改变规则,而不是参数 |
| 分析瘫痪 | 选项太多,无法决定 | 相邻可能(F7)——当前什么是可行的? |
| 错误二分法 | 困于在两种方法之间选择 | 两面神思维(F8)——寻求综合,而非选择 |
当研究人员请求帮助进行创造性思维或新颖构思时:
关键原则:
每周安装次数
87
仓库
GitHub 星标数
5.6K
首次出现
2026 年 2 月 23 日
安全审计
安装于
opencode78
gemini-cli76
kimi-cli76
codex76
amp76
github-copilot76
Eight empirically grounded frameworks from cognitive science, applied to computer science and AI research. Unlike ad-hoc brainstorming, each framework here is backed by decades of creativity research — from Koestler's bisociation to Kauffman's adjacent possible. They target distinct cognitive operations: combining, reformulating, analogizing, constraining, inverting, abstracting, exploring boundaries, and holding contradictions.
Do NOT use this skill when :
brainstorming-research-ideas)scientific-skills:literature-review)Relationship to Brainstorm skill : The brainstorm skill provides operational workflows (diverge → converge → refine) and practical filters. This skill provides the deeper cognitive engines that power creative leaps. Use them together: creative-thinking to generate raw insight, brainstorm to structure and evaluate it.
Novel ideas arise from combining existing concepts in unexpected ways. Arthur Koestler called this bisociation — connecting two previously unrelated frames of reference, as distinct from routine association within a single frame.
Why it works : Meta-research consistently shows that breadth of knowledge is a precursor to creative output. People who read across disciplines produce more novel work. The combination itself is the creative act.
In CS Research :
Systematic Bisociation Workflow :
Cross-Product Example :
| Caching | Load Balancing | Fault Tolerance
---|---|---|---
Natural Selection | Evict least-fit entries | Adaptive allocation via fitness | Population-level redundancy
Immune Memory | Learned threat signatures | Distributed detection | Self/non-self discrimination
Symbiosis | Cooperative prefetching | Mutualistic resource sharing | Co-dependent resilience
Quality Test : A strong bisociation is not a surface metaphor ("the network is like a brain") but a structural mapping where the mechanism transfers ("attention mechanisms implement a form of selective gating analogous to cognitive attention filtering").
Self-Check :
Gestalt psychologists identified that breakthroughs often come not from solving the problem as stated, but from re-representing the problem itself. Kaplan and Simon's work on insight shows that changing the problem space — the constraints, the abstraction level, the formalism — is often where creativity lives.
The Key Shift : From "How do I solve this problem?" to "Am I even thinking about this problem correctly?"
Reformulation Strategies :
| Strategy | Example |
|---|---|
| Change the objective | "Make the algorithm faster" → "Eliminate the need for this computation" |
| Change the formalism | Graph problem → linear algebra problem (spectral methods) |
| Change the granularity | Per-token prediction → per-span prediction |
| Change the agent | "How should the model learn?" → "How should the data teach?" (curriculum learning) |
| Change the timescale | Real-time optimization → amortized inference |
| Invert the direction | Forward simulation → inverse problem (learning from observations) |
Workflow :
Classic CS Examples :
Dedre Gentner's structure-mapping theory and Kevin Dunbar's studies of real scientists show that analogy is the core engine of scientific creativity. The critical finding: surface-level analogies are common but weak; structural or relational analogies — where the deep causal/relational structure maps across domains — produce the most powerful insights.
Dunbar's Finding : In the most successful labs, analogies from distant domains drove the most important discoveries. Nearby analogies refined ideas; distant analogies generated them.
Levels of Analogical Depth :
| Level | Description | Value | Example |
|---|---|---|---|
| Surface | Things look similar | Low | "A neural network is like a brain" |
| Relational | Relationships between entities match | Medium | "Attention allocation in models parallels resource allocation in economics" |
| Structural | Deep causal mechanisms map | High | "Diffusion models reverse a thermodynamic process; the math of non-equilibrium stat-mech directly applies" |
Structure-Mapping Workflow :
Validation Checklist :
Margaret Boden's framework distinguishes three forms of creativity based on how they interact with constraints:
| Type | Operation | CS Example |
|---|---|---|
| Exploratory | Search within the existing conceptual space | Hyperparameter tuning, architecture search within a fixed paradigm |
| Combinational | Combine elements from different spaces | Multi-task learning, neuro-symbolic methods |
| Transformational | Change the rules of the space itself | Dropping the assumption that training requires labels (self-supervised learning) |
Transformational creativity is the rarest and highest-impact. It happens when you change what is even considered a valid solution.
Constraint Analysis Workflow :
Classic Examples of Constraint Transformation :
Take a core assumption in your field and negate it. This is formalized in De Bono's lateral thinking and the TRIZ methodology from engineering.
The Pattern : "What if [widely held assumption] is wrong, unnecessary, or invertible?"
Systematic Negation Workflow :
Negation Hall of Fame in CS :
| Assumption | Negation | Result |
|---|---|---|
| "We need strong consistency" | What if we don't? | Eventual consistency, CRDTs |
| "We need exact answers" | What if approximate is fine? | Sketches, LSH, approximate nearest neighbors |
| "Labels are necessary" | What if we learn without them? | Self-supervised learning, contrastive methods |
| "More parameters = more compute" | What if we don't use all parameters? | Mixture of Experts, sparse models |
| "Training and inference are separate" | What if the model keeps learning? | Online learning, test-time training |
| "Errors must be prevented" | What if we embrace and correct them? | Speculative decoding, self-correction |
TRIZ-Inspired Principles for CS :
| TRIZ Principle | CS Application |
|---|---|
| Inversion | Reverse the process (generative vs. discriminative) |
| Segmentation | Break monolithic into modular (microservices, mixture of experts) |
| Merging | Combine separate steps (end-to-end learning) |
| Universality | One component serves multiple functions (multi-task models) |
| Nesting | Place one system inside another (meta-learning) |
| Dynamization | Make static things adaptive (dynamic architectures, adaptive computation) |
Moving up and down the abstraction ladder is a fundamental creative act. Polya's heuristics formalize this: "Can you solve a more general problem? A more specific one? An analogous one?"
Three Moves :
| Move | Question | Outcome |
|---|---|---|
| Generalize | "Is my solution a special case of something broader?" | Framework papers, unifying theories |
| Specialize | "What happens when I add extreme constraints?" | Niche applications, surprising edge cases |
| Analogize | "Where else does this abstract pattern appear?" | Cross-domain transfer (see Framework 3) |
Generalization Workflow :
Specialization Workflow :
When to Generalize vs. Specialize :
Stuart Kauffman's concept, popularized by Steven Johnson: innovation happens at the boundary of what is currently reachable — the adjacent possible. New ideas become thinkable once their prerequisites exist. This explains why simultaneous independent discovery is so common — multiple people reach the same boundary.
Practical Implication : Map what has recently become possible and explore the space those enablers open.
Adjacent Possible Mapping Workflow :
Current Adjacent Possibles (2025-2026) :
| Enabler | Newly Possible |
|---|---|
| 1M+ token context windows | Full-codebase reasoning, book-length analysis |
| Inference cost drops (100x in 2 years) | Real-time agentic loops, always-on AI assistants |
| Open-weight models at GPT-4 level | Reproducible research on frontier capabilities |
| Multimodal models (vision + language + audio) | Unified perception-reasoning systems |
| Synthetic data at scale | Training data for domains with no natural data |
| Tool-using models | Research automation, self-improving systems |
Timing Signal : If your idea requires technology that doesn't exist yet, it's beyond the adjacent possible — park it. If your idea could have been done 5 years ago, someone probably did — check the literature. The sweet spot is ideas that became feasible in the last 6-18 months.
Albert Rothenberg's studies of eminent creators found that holding two contradictory ideas simultaneously is a hallmark of creative thinking. Named after Janus, the two-faced Roman god, this mode of thinking doesn't resolve contradictions by choosing a side — it generates new frameworks that transcend the opposition.
In CS : The most influential results often emerge from tensions previously thought irreconcilable.
| Contradiction | Resolution | Impact |
|---|---|---|
| Consistency AND Availability (distributed systems) | CAP theorem: formalized the trade-off, then Raft/CRDTs found practical middle grounds | Foundation of distributed systems theory |
| Security AND Usability | Zero-knowledge proofs: prove knowledge without revealing it | Enabled private computation |
| Expressiveness AND Tractability | Probabilistic programming: express complex models, automate inference | New programming paradigm |
| Memorization AND Generalization | Grokking: models memorize first, then generalize with more training | New understanding of learning dynamics |
| Compression AND Quality | Neural codecs that compress beyond information-theoretic limits via learned priors | Redefined compression research |
Dialectical Thinking Workflow :
Self-Check :
These frameworks are most powerful in combination. Here is a systematic protocol for a deep creative thinking session:
Apply the two-sentence test (from the brainstorm skill):
"[Domain] currently struggles with [problem] because [reason]. We [approach] by [mechanism], which works because [insight]."
Any idea that survives all four phases and passes the two-sentence test is worth pursuing.
| Block | Symptom | Framework to Apply |
|---|---|---|
| Fixation | Cannot stop thinking about the problem one way | Problem Reformulation (F2) — force a different representation |
| Tunnel vision | All ideas come from the same subfield | Bisociation (F1) or Analogical Reasoning (F3) — import from elsewhere |
| Self-censoring | Dismissing ideas as "too weird" before exploring | Negation (F5) — weird is the point; evaluate after generating |
| Incrementalism | Every idea is "+2% on benchmark X" | Constraint Manipulation (F4) — change the rules, not the parameters |
| Analysis paralysis | Too many options, cannot commit | Adjacent Possible (F7) — what is feasible right now? |
| False dichotomy | Stuck choosing between two approaches | Janusian Thinking (F8) — seek synthesis, not selection |
When a researcher asks for help with creative thinking or novel ideation:
Key Principles :
Weekly Installs
87
Repository
GitHub Stars
5.6K
First Seen
Feb 23, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
opencode78
gemini-cli76
kimi-cli76
codex76
amp76
github-copilot76
AI 代码实施计划编写技能 | 自动化开发任务分解与 TDD 流程规划工具
50,900 周安装