title

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Title Generation

标题生成

Overview

概述

This skill generates high-performing titles and headlines optimized for engagement across any content type. Titles are designed to spark curiosity, complement visual assets where applicable, and compel the audience to click, open, or engage.

Core Principle: Every title must prompt a specific question in the audience's mind. Description alone is insufficient — curiosity is non-negotiable.

该Skill可为任意类型内容生成能提升用户参与度的高表现标题与副标题。生成的标题旨在激发受众好奇心、匹配相关视觉素材，并促使受众点击、打开或参与内容互动。

核心原则：每一个标题都必须能在受众心中引发一个具体的问题。仅对内容进行描述是远远不够的——激发好奇心是必不可少的要求。

When to Use

使用场景

Use this skill when:

The user asks to create a title, headline, or subject line
The user requests title ideas or brainstorming for content
The user wants to improve or optimize an existing title
Working on content creation and a title is needed
The user asks for multiple title variations to test

以下场景可使用该Skill：

用户需要创建标题、副标题或邮件主题行
用户请求为内容提供标题创意或进行头脑风暴
用户希望改进或优化现有标题
进行内容创作时需要生成标题
用户需要多个标题变体用于测试

Content Type Resolution

内容类型适配

Before generating titles, determine the content type and load the appropriate platform-specific reference file:

Content Type	Reference File	Key Focus
YouTube video	`references/youtube-title-formulas.md`	CTR, curiosity, thumbnail complementarity
Newsletter / email	`references/newsletter-subject-lines.md`	Open rate, preview text, inbox competition
Social media post	`references/social-headlines.md`	Scroll-stopping, platform-specific hooks

MANDATORY: Read the relevant reference file before generating titles. These references contain platform-specific patterns, forbidden patterns, and quality standards that are non-negotiable.

If the content type does not match any reference file, apply the universal principles below and adapt to the format.

在生成标题前，需先确定内容类型，并加载对应的平台专属参考文件：

内容类型	参考文件	核心关注点
YouTube 视频	`references/youtube-title-formulas.md`	点击率（CTR）、好奇心、缩略图匹配度
新闻通讯/邮件	`references/newsletter-subject-lines.md`	打开率、预览文本、收件箱竞争力
社交媒体帖子	`references/social-headlines.md`	吸引停留、平台专属钩子设计

强制要求：生成标题前必须阅读对应的参考文件。这些参考文件包含平台专属的标题范式、禁用范式以及不可妥协的质量标准。

如果内容类型与现有参考文件不匹配，请应用以下通用原则并适配对应格式。

Prerequisites

前置条件

Gather Context

收集上下文信息

Before generating titles, gather the following information from conversation context, the user's filesystem, or by asking the user directly.

Required Information:

Content topic: What is the content about?
Target audience: Who is this for?
Key message: What is the main takeaway or hook?

Highly Recommended Information:

Visual asset description: What does the thumbnail, header image, or preview show?
Target emotion: What emotion should the title evoke? (curiosity, shock, excitement, urgency)
Content type: Video, newsletter, social post, blog article, etc.

在生成标题前，需从对话上下文、用户文件系统中收集以下信息，或直接向用户询问。

必填信息：

内容主题：内容的核心主题是什么？
目标受众：内容面向的受众群体是谁？
核心信息：内容的主要要点或钩子是什么？

强烈建议收集的信息：

视觉素材描述：缩略图、标题图或预览图展示了什么内容？
目标情绪：标题需要唤起受众的哪种情绪？（好奇心、震惊、兴奋、紧迫感）
内容类型：视频、新闻通讯、社交媒体帖子、博客文章等。

Title Generation Workflow

标题生成工作流

Step 1: Gather Context

步骤1：收集上下文信息

Collect required information if not already provided. Ask the user for anything missing:

To create an optimized title, I need to understand:
1. What is the content about? (topic)
2. Who is your target audience?
3. What is the main hook or takeaway?
4. Do you have a visual asset (thumbnail, header image)? If so, what does it show?
5. What emotion should the title evoke?

如果未收集到必填信息，请向用户询问缺失的内容：

为了生成优化的标题，我需要了解以下信息：
1. 内容的核心主题是什么？（主题）
2. 你的目标受众是谁？
3. 内容的主要钩子或核心要点是什么？
4. 你是否有相关视觉素材（缩略图、标题图）？如果有，素材展示了什么内容？
5. 标题需要唤起受众的哪种情绪？

Step 2: Load Platform Reference

步骤2：加载平台参考文件

MANDATORY ACTION: Read the appropriate platform-specific reference file based on the content type identified in Step 1.

强制操作：根据步骤1确定的内容类型，阅读对应的平台专属参考文件。

Step 3: Identify the Question

步骤3：确定要引发的问题

Before writing any title, identify the specific question you want in the audience's mind:

What question will make them curious enough to engage?
Does this question align with the content?
Is the curiosity gap strong enough to drive action?

Examples of effective questions to prompt:

"What mistakes am I making?" (mistake framing)
"What happened?" (outcome uncertainty)
"Why would someone do that?" (extreme behavior)
"How is that possible?" (surprising claim)

在撰写任何标题前，先确定你希望在受众心中引发的具体问题：

什么样的问题能让他们足够好奇并参与内容？
这个问题是否与内容主题一致？
好奇心缺口是否足够大，能驱动用户采取行动？

能有效引发好奇心的问题示例：

"What mistakes am I making?"（错误框架）
"What happened?"（结果不确定性）
"Why would someone do that?"（极端行为）
"How is that possible?"（惊人断言）

Step 4: Generate Title Options

步骤4：生成标题选项

Generate 3-5 title variations that:

Prompt the identified question
Complement (not duplicate) any visual assets
Align with the target emotion
Follow platform-specific best practices from the reference file

生成3-5个标题变体，需满足以下条件：

能引发步骤3确定的问题
匹配（而非重复）视觉素材的内容
与目标情绪一致
遵循参考文件中的平台专属最佳实践

Step 5: Verify Against Checklist

步骤5：对照检查清单验证

Step 6: Present and Refine

步骤6：展示并优化

Present title options to the user with:

The title itself
The question it prompts in the audience's mind
How it complements the visual asset (if applicable)
Why it should drive engagement

Example presentation:

Here are 3 optimized title options:

1. "The AI Agent Mistake That Cost Me 10 Hours"
   - Prompts: "What mistake? How can I avoid it?"
   - Complements thumbnail showing frustrated face + error message
   - Creates urgency through time cost

2. "I Built This AI Agent Wrong (Here's What I Learned)"
   - Prompts: "What did they do wrong? What's the lesson?"
   - Personal experience framing creates relatability

3. "Why Your AI Agents Keep Breaking (And Mine Don't)"
   - Prompts: "Why do mine break? What's their secret?"
   - Creates contrast and curiosity

向用户展示标题选项时，需包含以下信息：

标题本身
该标题在受众心中引发的问题
该标题如何匹配视觉素材（如有）
该标题为何能提升用户参与度

展示示例：

以下是3个经过优化的标题选项：

1. "The AI Agent Mistake That Cost Me 10 Hours"
   - 引发的问题：“是什么错误？我该如何避免？”
   - 匹配展示沮丧表情 + 错误提示的缩略图
   - 通过时间成本营造紧迫感

2. "I Built This AI Agent Wrong (Here's What I Learned)"
   - 引发的问题：“他们哪里做错了？学到了什么教训？”
   - 个人经历框架增强共鸣感

3. "Why Your AI Agents Keep Breaking (And Mine Don't)"
   - 引发的问题：“为什么我的AI Agent总是崩溃？他们有什么秘诀？”
   - 通过对比激发好奇心

Step 7: Iterate Based on Feedback

步骤7：根据反馈迭代

If the user requests changes:

Understand what aspect needs adjustment (curiosity, tone, length, etc.)
Regenerate while maintaining checklist compliance
Re-verify against the checklist

如果用户要求修改：

明确需要调整的方面（好奇心、语气、长度等）
在符合检查清单要求的前提下重新生成标题
再次对照检查清单进行验证

Voice Application

语气适配

Before finalizing any written output, invoke the

writing:voice

skill to apply voice rules. Titles should sound authentic to the user's voice, not generic.

在最终确定任何书面输出前，调用

writing:voice

Skill来应用语气规则。标题应贴合用户的独特语气，而非千篇一律。

Brand Compliance

品牌合规性

When creating assets for The AI Launchpad, invoke

branding-kit:brand-guidelines

to resolve the correct design system and check anti-patterns.

为The AI Launchpad创建内容资产时，需调用

branding-kit:brand-guidelines

来获取正确的设计体系并检查禁用范式。

Quality Assurance

质量保证

Priority Order

优先级排序

Spark curiosity (highest priority)
Complement visual asset
Raise audience question
Create click/open compulsion

激发好奇心（最高优先级）
匹配视觉素材
引发受众疑问
营造点击/打开驱动力

Rejection Criteria

拒绝标准

REJECT and regenerate if the title:

Merely describes the content without sparking curiosity
Duplicates text that appears on the visual asset
Answers the question instead of raising it
Uses generic patterns without intrigue
Fails the "What question does this raise?" test

若标题符合以下任一情况，需拒绝并重新生成：

仅描述内容而未激发好奇心
重复视觉素材上的文字内容
直接回答问题而非引发问题
使用无吸引力的通用范式
未通过“该标题引发了什么问题？”的测试

Success Criteria

成功标准

A successful title:

Prompts a specific, compelling question in the audience's mind
Works synergistically with any visual asset
Creates a curiosity gap strong enough to drive engagement
Aligns with the target audience and content type
Passes all 5 universal checklist items

成功的标题需满足以下条件：

在受众心中引发具体且有吸引力的问题
与视觉素材协同作用
营造足够大的好奇心缺口以提升用户参与度
匹配目标受众与内容类型
通过全部5项通用检查清单测试

Common Pitfalls

常见误区

Generic Description: "AI Agents Tutorial" describes but does not intrigue. Add curiosity.
Answering the Question: "How to Fix AI Agent Memory in 3 Steps" gives away too much. Tease, do not tell.
Ignoring Platform: A YouTube title and a newsletter subject line have different constraints. Load the right reference.
Thumbnail/Asset Duplication: If the thumbnail says "BROKEN", the title should not also say "broken." Complement, do not repeat.
Single Option: Always provide 3-5 variations for the user to choose from.

通用描述误区：“AI Agents Tutorial”仅描述内容但无吸引力，需加入好奇心元素。
直接回答问题误区：“How to Fix AI Agent Memory in 3 Steps”透露过多信息，应点到为止，而非全盘托出。
忽略平台差异误区：YouTube标题与邮件主题行有不同的限制，需加载对应的参考文件。
素材重复误区：如果缩略图显示“BROKEN”，标题不应也使用“broken”，应匹配而非重复。
单一选项误区：始终提供3-5个标题变体供用户选择。