Back to Details

generating-novel-ideas

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Generating Novel Ideas

生成新颖创意

This skill turns ideation into a search process, not a list-making exercise. The job is to discover a portfolio of distinct, high-potential concepts, not ten polished variations of the first plausible answer.
本Skill将创意构思转化为搜索过程，而非简单的列清单任务。核心目标是发掘一组各具特色、潜力十足的概念，而非对第一个可行答案进行十次打磨式的变体生成。

Critical rules

核心规则

  • Fight collapse. LLMs drift towards fluent sameness. Use independent idea pools before comparing ideas.
  • Prefer concrete mechanisms over vibes. Every finalist needs a sharp twist, an entry wedge, and a cheap test.
  • Separate divergence from judgement. Do not score too early.
  • Use ordinary stakeholder or practitioner perspectives when using personas. Do not imitate celebrity innovators.
  • Research late enough to preserve breadth, but early enough to kill obvious reinventions before the final recommendation.
  • Final outputs should usually be a portfolio with spread across mechanism, audience, and risk, unless the user explicitly asks for a single winner.
  • 避免创意同质化。大语言模型（LLMs）容易生成趋同的流畅内容。在对比创意前，先构建独立的创意池。
  • 优先具体机制而非模糊感觉。每个最终入选的概念都需要一个鲜明的创新点、初始切入点和低成本验证测试。
  • 将发散思考与评判环节分离。不要过早打分。
  • 使用角色视角时，采用普通利益相关者或从业者的视角，不要模仿知名创新者。
  • 适时开展研究：既要保留创意广度，又要在最终推荐前淘汰明显的重复创意。
  • 最终输出通常应是一个覆盖不同机制、受众和风险的创意组合，除非用户明确要求单一最优方案。

Internal roles

内部角色

Run these roles in sequence. Keep them separate until synthesis.
  1. Explorers widen the search space.
  2. Critics attack weak, generic, or unrealistic ideas.
  3. The synthesiser assembles the final portfolio.
Do not let the critic appear too early. Do not let the synthesiser merge everything into one blurry compromise.
按顺序执行以下角色，在合成阶段前保持角色独立：
  1. 探索者：拓宽搜索范围。
  2. 批判者：抨击薄弱、同质化或不切实际的创意。
  3. 合成者：整合最终的创意组合。
不要让批判者过早介入，也不要让合成者将所有内容融合成模糊的折中方案。

Default workflow

默认工作流程

  1. Build an opportunity model
  2. Partition the search space
  3. Generate independent idea pools
  4. Run an analogy transfer pass
  5. Resolve key contradictions
  6. Audit diversity and regenerate missing directions
  7. Critique and repair finalists
  8. Ground against reality
  9. Present a portfolio and experiments
  1. 构建机会模型
  2. 划分搜索范围
  3. 生成独立创意池
  4. 执行类比迁移环节
  5. 解决核心矛盾
  6. 审核创意多样性并补充缺失方向
  7. 批判并优化最终入选创意
  8. 结合现实校验
  9. 呈现创意组合及验证实验

Step 1: Build an opportunity model

步骤1：构建机会模型

Capture the minimum useful brief:
  • User goal
  • Target user or audience
  • Current status quo and what is frustrating, expensive, risky, slow, or emotionally flat
  • Hard constraints
  • Success criteria
  • Available assets, unfair advantages, channels, or capabilities
  • Hidden tensions and trade-offs
  • What to avoid
When the prompt is sparse, infer reasonable assumptions and state them briefly.
When the user brings an existing idea, do not start by polishing it directly. First extract the underlying job and generate at least two alternative mechanisms.
捕捉最核心的需求要点：
  • 用户目标
  • 目标用户或受众
  • 当前现状及其中令人沮丧、昂贵、高风险、低效或缺乏情感共鸣的环节
  • 硬性约束
  • 成功标准
  • 可用资源、独特优势、渠道或能力
  • 隐藏的矛盾与权衡
  • 需要规避的内容
当用户提示信息不足时，推断合理假设并简要说明。
若用户已有一个创意，不要直接开始打磨。首先提炼其背后的核心需求，然后生成至少两种替代机制。

Step 2: Partition the search space

步骤2：划分搜索范围

Choose 3 to 5 independent pools. Pools must differ on at least two axes.
Good axes include:
  • stakeholder viewpoint or ordinary persona
  • mechanism or value type
  • user moment or time horizon
  • adoption path or channel
  • ambition level
  • trust model or ownership model
Examples of useful pool labels:
  • frontline operator, zero new habit
  • approver or buyer, proof and risk reduction
  • novice user, immediate win
  • partner or embedded channel
  • bold long-shot system shift
Rules:
  • Generate each pool as if it has not seen the others.
  • Do not compare, deduplicate, or score until all pools are finished.
  • Produce 2 to 4 ideas per pool.
  • Keep raw ideas short at first: name, one-line concept, primary user, non-obvious move.
This blind partitioning is the main defence against idea collapse.
选择3至5个独立的创意池。各创意池需在至少两个维度上存在差异。
合适的维度包括：
  • 利益相关者视角或普通角色
  • 机制或价值类型
  • 用户场景或时间跨度
  • 采用路径或渠道
  • 目标野心级别
  • 信任模型或所有权模型
实用的创意池标签示例：
  • 一线操作人员，无需养成新习惯
  • 审批者或采购方，注重证据与风险降低
  • 新手用户，追求即时收益
  • 合作伙伴或嵌入式渠道
  • 大胆的长期系统变革
规则：
  • 生成每个创意池时，假设未参考其他创意池。
  • 完成所有创意池后再进行对比、去重或打分。
  • 每个创意池生成2至4个创意。
  • 初始原始创意要简洁：名称、一句话概念、核心用户、非显而易见的举措。
这种盲划分是防止创意同质化的主要手段。

Step 3: Generate the pools

步骤3：生成创意池

Inside each pool:
  1. Write 2 to 3 fertile reframing questions.
  2. Choose two lenses from 
    references/LENSES.md
    .
  3. Generate the first pass.
  4. Do a second internal pass and add at least one idea clearly outside the dominant pattern.
Always include one practical lens and one novelty lens.
If the task is complex, breadth comes before depth. Add new mechanism families before expanding any single family.
在每个创意池内：
  1. 撰写2至3个富有启发性的重构问题。
  2. 从
    references/LENSES.md
    中选择两个视角。
  3. 生成第一轮创意。
  4. 进行第二轮内部迭代，至少添加一个明显跳出主流模式的创意。
始终包含一个实用视角和一个创新视角。
若任务复杂，先追求广度再深挖。在扩展单一机制类别前，先新增机制类别。

Step 4: Run an analogy transfer pass

步骤4：执行类比迁移环节

Do not borrow surface style. Borrow mechanism.
  1. Abstract the problem into a mechanism, tension, or pattern.
  2. Pick 2 to 4 distant domains.
  3. Extract what makes those domains work.
  4. Map the mechanism back into the problem.
  5. Adapt it for the actual constraints and adoption path.
Every strong final set should contain at least one idea born from far analogy, unless the user explicitly wants only safe, incremental options.
For source domains and transfer patterns, use 
references/LENSES.md
.
不要借用表面风格，要借鉴机制逻辑。
  1. 将问题抽象为机制、矛盾或模式。
  2. 选择2至4个关联度较低的领域。
  3. 提炼这些领域的有效运作机制。
  4. 将该机制映射回当前问题。
  5. 根据实际约束和采用路径进行调整。
除非用户明确要求仅提供安全的增量方案，否则最终的优质创意组合中应至少包含一个源自跨领域类比的创意。
如需参考源领域和迁移模式，请使用
references/LENSES.md
。

Step 5: Resolve key contradictions

步骤5：解决核心矛盾

Write 1 to 3 contradictions at the heart of the task, such as:
  • more trust with less friction
  • more customisation with less complexity
  • more quality with less expert labour
  • faster decision-making with lower risk
  • more compliance with less manual work
Generate ideas that resolve the contradiction through separation, defaults, staging, guarantees, modularity, reversible commitment, human review only at critical moments, or new ownership boundaries.
For technical, scientific, or engineering prompts, use the structured contradiction method in 
references/LENSES.md
.
写出1至3个任务核心的矛盾，例如：
  • 更高信任度与更低摩擦
  • 更高定制化与更低复杂度
  • 更高质量与更少专业人力
  • 更快决策与更低风险
  • 更高合规性与更少人工操作
通过分离策略、默认设置、分阶段推进、担保机制、模块化设计、可逆承诺、仅在关键节点进行人工审核或重新界定所有权边界等方式，生成解决矛盾的创意。
针对技术、科学或工程类提示，请使用
references/LENSES.md
中的结构化矛盾解决方法。

Step 6: Audit diversity

步骤6：审核创意多样性

Before refinement, check for hidden sameness.
Look for:
  • near-duplicates hidden by new wording
  • too many ideas using the same mechanism
  • too many aimed at the same user moment
  • repeated crutches such as AI assistant, dashboard, marketplace, community, gamification, personalisation, subscription, or platform
  • no spread across pragmatic wedge, strategic differentiator, and bold bet
If the set is clustered, regenerate only the missing directions.
When scripts can run and the set is large, optionally use 
scripts/diversity_audit.py
before convergence.
在优化前，检查是否存在隐性同质化问题。
需关注：
  • 用新表述掩盖的近似重复创意
  • 过多使用同一机制的创意
  • 过多针对同一用户场景的创意
  • 反复依赖的通用元素，如AI助手、仪表盘、交易平台、社区、游戏化、个性化、订阅制或平台模式
  • 缺乏务实切入点、差异化战略和大胆赌注的分布
若创意集中在某一领域，仅补充缺失方向的创意即可。
当可运行脚本且创意数量较多时，可在收敛前选用
scripts/diversity_audit.py
进行辅助审核。

Step 7: Critique and repair finalists

步骤7：批判并优化最终入选创意

Choose 3 to 6 finalists. For each one, write:
  • strongest reason it could work
  • smartest sceptic objection
  • repair if possible
  • kill it if repair makes it generic or unrealistic
Every finalist card should contain:
  • Name
  • One-sentence pitch
  • Who it is for
  • Hidden insight or tension
  • Imported mechanism or pattern
  • Why it is not just the obvious solution
  • Entry wedge
  • Main risk
  • Cheapest disconfirming test
选择3至6个最终入选创意。针对每个创意，撰写：
  • 其可行的核心原因
  • 最犀利的质疑观点
  • 若可行则进行优化
  • 若优化会导致同质化或不切实际则直接淘汰
每个最终创意卡片应包含：
  • 名称
  • 一句话宣传语
  • 目标用户
  • 隐藏洞察或矛盾
  • 借鉴的机制或模式
  • 区别于常规方案的原因
  • 初始切入点
  • 主要风险
  • 最廉价的否定性验证测试

Step 8: Ground against reality

步骤8：结合现实校验

If current market, technical, cultural, or regulatory reality matters and research is available:
  • check whether the idea is already common
  • identify incumbents or substitutes
  • pressure-test feasibility and compliance
  • sharpen the why-now and distribution story
  • trim false differentiation claims
Do not research so early that the search space collapses into existing categories.
若当前市场、技术、文化或监管环境至关重要且有研究资料可查：
  • 检查该创意是否已普遍存在
  • 识别现有竞品或替代方案
  • 验证可行性与合规性
  • 强化“为何当下可行”及推广逻辑
  • 删除虚假的差异化主张
不要过早开展研究，以免搜索范围局限于现有类别。

Step 9: Present the result

步骤9：呈现结果

Default response structure:
  1. Working brief and assumptions
  2. Opportunity tensions
  3. Search partitions used
  4. Raw idea families
  5. Final portfolio
  6. Recommended next move
Use a portfolio, not just a ranking:
  • one pragmatic wedge
  • one strategic differentiator
  • one bold bet
If the user asks for a single winner, still mention the strongest runner-up and the specific reason it lost.
默认响应结构：
  1. 工作概要与假设
  2. 机会矛盾点
  3. 所用的搜索划分维度
  4. 原始创意类别
  5. 最终创意组合
  6. 推荐下一步行动
采用创意组合而非单一排名：
  • 一个务实切入点
  • 一个差异化战略方案
  • 一个大胆赌注方案
若用户要求单一最优方案，仍需提及最强备选方案及落选的具体原因。

Hard quality bar

严格质量标准

No finalist is complete without:
  • a clear non-obvious move
  • a believable first user and first context
  • a path to adoption or distribution
  • a cheap test that could disconfirm it
  • an explicit line in this format:
This is not just X. The new move is Y.
If Y is vague, decorative, or generic, the concept is not ready.
For the detailed rubric, use 
references/EVALUATION.md
.
每个最终入选创意必须包含：
  • 明确的非显而易见举措
  • 可信的首批用户及初始场景
  • 采用或推广路径
  • 可否定该创意的低成本测试
  • 如下格式的明确表述：
这不仅仅是X。创新点在于Y。
若Y模糊、装饰性过强或同质化，则该概念未达标。
如需详细评估标准，请使用
references/EVALUATION.md
。

Anti-generic rules

反同质化规则

  • Do not produce a flat list of features around one core mechanism and call it diversity.
  • Do not hide weak ideas behind fluent prose.
  • Do not use AI, agent, community, marketplace, dashboard, platform, personalisation, or gamification as decoration.
  • Do not let naming replace concept work.
  • Do not overvalue novelty with no adoption path.
  • Do not overvalue feasibility when the idea is indistinguishable from existing practice.
  • Prefer specific trade-offs to magical wins on every dimension.
  • 不要围绕单一核心机制生成一系列功能并声称具有多样性。
  • 不要用流畅的文字掩盖薄弱创意。
  • 不要将AI、Agent、社区、交易平台、仪表盘、平台模式、个性化或游戏化作为装饰元素。
  • 不要用命名替代概念构建。
  • 不要过度推崇无落地路径的新颖性。
  • 不要过度推崇与现有实践无差别的可行性。
  • 优先选择明确的权衡方案，而非在所有维度上的“完美胜利”。

Mode switching

模式切换

For domain-specific workflows, use 
references/MODES.md
.
Common modes:
  • startup or product opportunity
  • research hypothesis or scientific idea
  • campaign, content, or creative concept
  • naming and verbal concept development
  • process, service, or operations redesign
针对特定领域的工作流程，请使用
references/MODES.md
。
常见模式：
  • 初创企业或产品机会
  • 研究假设或科学创意
  • 营销活动、内容或创意概念
  • 命名与文字概念开发
  • 流程、服务或运营重构

Common failure modes

常见失败模式

If the outputs feel generic:
  • widen the partitions
  • add a stronger far-analogy pass
  • write sharper contradictions
  • regenerate only missing mechanism families
If the outputs feel clever but unusable:
  • reduce ambition by one step
  • sharpen the first user and first context
  • attach a cheaper test and a narrower wedge
If the outputs all sound similar:
  • stop scoring
  • restart with blind pools from new viewpoints
  • avoid celebrity personas and vague mission statements
若输出内容同质化：
  • 拓宽划分维度
  • 强化跨领域类比环节
  • 写出更尖锐的矛盾点
  • 仅补充缺失的机制类别创意
若输出内容看似巧妙但无法落地：
  • 降低一级目标野心
  • 明确首批用户及初始场景
  • 搭配更低成本的测试和更精准的切入点
若输出内容听起来都相似：
  • 停止打分
  • 从新视角重新构建盲创意池
  • 避免使用知名角色和模糊的使命陈述

Examples

示例

Example 1

示例1

User says: I need fresh B2B SaaS ideas for compliance teams.
Actions:
  1. Build an opportunity model around buyers, blockers, trust, procurement, and audit.
  2. Partition by operator, approver, audit trail, and partner channel.
  3. Generate blind pools, then run analogy and contradiction passes.
  4. Return a portfolio with wedge, differentiator, bold bet, and tests.
用户需求：我需要针对合规团队的全新B2B SaaS创意。
行动：
  1. 围绕采购方、障碍、信任、采购流程及审计构建机会模型。
  2. 按操作人员、审批者、审计追踪、合作伙伴渠道划分创意池。
  3. 生成盲创意池，然后执行类比和矛盾解决环节。
  4. 返回包含切入点、差异化方案、大胆赌注及测试方法的创意组合。

Example 2

示例2

User says: This startup idea feels generic. Make it genuinely better.
Actions:
  1. Extract the underlying job from the current idea.
  2. Generate at least two alternative mechanisms before improving the original.
  3. Keep only ideas with sharper wedges and clearer tests.
用户需求：这个初创企业创意太同质化了，让它真正变得更好。
行动：
  1. 从现有创意中提炼核心需求。
  2. 在优化原创意前，生成至少两种替代机制。
  3. 仅保留切入点更清晰、验证方法更明确的创意。

Example 3

示例3

User says: Help me come up with novel research directions in battery diagnostics.
Actions:
  1. Build tensions, constraints, missing capabilities, and evidence limits.
  2. Use scientific mode from 
    references/MODES.md
    .
  3. Add structured contradiction solving and feasibility pressure-testing.
For trigger tests and maintenance checks, use 
references/VALIDATION.md
.
用户需求：帮我想出电池诊断领域的全新研究方向。
行动：
  1. 梳理矛盾点、约束条件、缺失能力及证据局限。
  2. 使用
    references/MODES.md
    中的科学模式。
  3. 加入结构化矛盾解决和可行性验证环节。
如需触发测试和维护检查，请使用
references/VALIDATION.md
。