creativity

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Creativity

创意生成

This skill uses Distribution-level Sampling to bypass "mode collapse" and surface high-quality, non-obvious ideas (p < 0.10).

State the goal for using this skill, and align the outcome to it.

本Skill采用分布级采样（Distribution-level Sampling）来规避「模式坍缩（mode collapse）」，挖掘高质量、非显而易见的创意想法（概率p < 0.10）。

请说明使用本Skill的目标，并确保产出与目标对齐。

Creative Workflow

创意工作流

Follow these phases thoroughly. Show your reasoning to the user.

请严格遵循以下阶段执行，并向用户展示你的推理过程。

Phase 1: Explore semantic space

阶段1：探索语义空间

Conduct a reasoning-first exploration of the semantic space. Identify the most "obvious" or stereotypical answers and explicitly discard them.

Announce a list of discarded ideas with a super-short rationale.

以推理为核心探索语义空间。识别出最“显而易见”或刻板的答案，并明确将其排除。

列出被排除的想法及简短理由。

Phase 2: Generate

阶段2：生成创意

Produce a set of diverse responses:

$k$ (default 5) from the tail of the distribution (p < 0.15)
$k$ (default 5) from the head of the distribution (p > 0.85)

Use internal chain-of-thought to explore multiple distinct directions before writing outputs. Assign an estimated probability to each.

产出一组多样化的响应：

从分布尾部选取$k$个（默认5个，概率p < 0.15）
从分布头部选取$k$个（默认5个，概率p > 0.85）

在输出前，通过内部思维链（chain-of-thought）探索多个不同方向。为每个想法分配预估概率。

Phase 3: Review

阶段3：审核

Review the generated set against the broader task user is working on.
Eliminate any ideas that are irrelevant, or lack impact.

对照用户正在处理的更广泛任务，审核生成的创意集合。
剔除任何无关或缺乏影响力的想法。

Phase 4: Iteration

阶段4：迭代

Decide whether the current set is sufficient:

Loop: If ideas lack impact or relevance, re-run Phase 1.
Finalize: If the set is strong, follow the output format.

判断当前创意集合是否足够：

循环：若想法缺乏影响力或相关性，重新执行阶段1。
定稿：若集合质量达标，遵循输出格式呈现结果。

Output Format

输出格式

Present the final set of ideas using Markdown tables. Each idea must have its own table with the following structure:

Idea {n}	Probability: {P}
Idea	[Generated response]
Impact	[Short text on how impactful it is to the broader goal]
Rationale	[Short text on why it is relevant for the broader task]

使用Markdown表格展示最终的创意集合。每个想法需单独使用如下结构的表格：

创意{n}	概率: {P}
创意内容	[生成的响应内容]
影响力	[简短说明该创意对整体目标的影响程度]
合理性	[简短说明该创意与整体任务的相关性]

Example Output

示例输出

Idea 1	Probability: 0.04
Idea	Silent Onboarding: Replace tutorial pop-ups with environmental cues embedded in the UI itself.
Impact	High. Standard onboardings are often skipped. This reframe lets users "learn by doing."
Rationale	Most onboarding assumes explicit instruction. This challenges the pattern by treating the interface as a "learning landscape" rather than a "lesson plan."

创意1	概率: 0.04
创意内容	静默式引导：将教程弹窗替换为嵌入UI中的环境提示。
影响力	高。常规引导常被用户跳过，这种重构让用户“在实践中学习”。
合理性	大多数引导方式依赖明确指令，而该创意打破此模式，将界面视为“学习场景”而非“教案”。

Creative Operators

创意操作符

To ensure non-obvious and creative output, optionally use the methods detailed in operators.md.

为确保产出非显而易见的创意内容，可选择性使用operators.md中详细介绍的方法。