Back to Details

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.
本技能采用Distribution-level Sampling（分布级采样）来规避“模式坍缩（mode collapse）”，挖掘高质量、非显而易见的创意（概率p < 0.10）。
请明确使用本技能的目标，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操作，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，探索相关语义空间。识别出最“显而易见”或刻板的答案，并明确将其排除。
列出被排除的创意列表，并附上简短的理由。

Phase 2: Generate

阶段2：生成创意

Produce a set of diverse responses:
  1. $k$ (default 5) from the tail of the distribution (p < 0.15)
  2. $k$ (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：
  1. $k$个（默认5个）来自分布尾部（概率p < 0.15）
  2. $k$个（默认5个）来自分布头部（概率p > 0.85）
在撰写输出前，通过内部思维链（chain-of-thought）探索多个不同方向。为每个创意分配一个预估概率。

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创意。

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：如果创意缺乏影响力或相关性，重新执行阶段1。
  • 定稿：如果创意集合质量达标，请遵循输出格式呈现。

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表格呈现最终的创意集合。每个创意需单独使用一个表格，结构如下：
创意{n}概率: {P}
创意内容[生成的响应内容]
影响力[关于该创意对整体目标影响力的简短说明]
理由[关于该创意与整体任务相关性的简短说明]

Example Output

示例输出

Idea 1Probability: 0.04
IdeaSilent Onboarding: Replace tutorial pop-ups with environmental cues embedded in the UI itself.
ImpactHigh. Standard onboardings are often skipped. This reframe lets users "learn by doing."
RationaleMost 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。标准引导流程常被用户跳过，这种重构让用户“在实践中学习”。
理由大多数引导流程依赖明确指令，而该创意打破这一模式，将界面视为“学习场景”而非“教学计划”。

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中详述的方法。