Title Writing logo

Title Writing

Community
vivy-yi
title-writing

Use when writing Xiaohongshu post titles, creating headlines for content, improving click-through rates, or optimizing titles for search and discovery

Overview

Publishervivy-yi
Repositoryxiaohongshu-skills
Skill nametitle-writing
Stars
502
Forks
76
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by vivy-yi on GitHub. Read the source before you install it.

Installation

Install the Title Writing AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/vivy-yi/xiaohongshu-skills/tree/main/skills/01-内容创作/title-writing
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Use it in TypingMind

Enable Title Writing in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Title Writing on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Title Writing is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Title Writing (标题撰写)

Overview

Title writing is crafting compelling headlines that grab attention, spark curiosity, accurately represent content, and entice users to click - the critical first impression for content discovery on Xiaohongshu.

When to Use

Use when:

  • Writing titles for new posts
  • Optimizing low-performing content
  • A/B testing headline variants
  • Improving click-through rates
  • Making content more discoverable

Do NOT use when:

  • Writing full content body (use copywriting-skills)
  • Creating cover text (use cover-design)

Core Pattern

Before (boring titles):

❌ "我的护肤routine"
❌ "好用的产品推荐"
❌ "今天分享穿搭"
❌ "关于xx的一些想法"

After (compelling titles):

✅ "学生党必看: 5个平价好物让你告别选择困难"
✅ "坚持这套护肤30天,变化惊呆了所有人"
✅ "没想到这个每天的习惯竟然毁了皮肤"
✅ "普通女孩如何逆袭? 我做对了这3件事"

4 Title Frameworks:

  1. Number + Promise - "5 ways to..."
  2. Curiosity Gap - "The secret nobody tells you..."
  3. Problem-Solution - "Struggling with X? Here's the fix"
  4. Transformation - "How I went from X to Y"

Quick Reference

FrameworkTemplateExampleUse For
Number"N个...""5个平价好物"Lists, collections
Promise"让你...""让你皮肤发光"Benefit-driven
Curiosity"没想到...""没想到这个...有用"Surprising tips
Negative"别再...""别再犯这个错误"Problem-solving
Before-After"如何...""如何从0到1万粉"Transformation

Implementation

Step 1: Identify Core Value

Ask: What's the ONE thing audience gets?

Examples:

  • Tutorial → "学会..."
  • Product → "发现..."
  • Tips → "知道..."
  • Story → "了解..."

Step 2: Choose Title Framework

Match content to framework:

  • Educational → Number or Promise
  • Surprising → Curiosity
  • Problem-solving → Negative or Problem-Solution
  • Personal story → Before-After or Transformation

Step 3: Draft 5-10 Variants

Brainstorm multiple angles:

Content: 平价防晒霜推荐

Variants:
1. "学生党平价防晒霜推荐" (basic)
2. "5个防晒霜误区,你中了几个?" (curiosity)
3. "这些百元防晒霜竟然比千元还好用" (surprising)
4. "别再花冤枉钱了,平价防晒霜才是真香" (negative)
5. "从过敏到最爱: 我和防晒霜的爱恨情仇" (story)

Step 4: Optimize with Power Words

Add emotional/trigger words:

  • Urgency: "必看", "立即", "现在"
  • Exclusivity: "秘密", "没人告诉你", "终于"
  • Numbers: "5个", "3步", "7天"
  • Results: "惊呆", "逆袭", "变化"

Step 5: Keep Under 20 Characters

Xiaohongshu title limit: ~20 Chinese characters

Techniques:

  • Remove filler words
  • Use concise phrasing
  • Front-load important words
  • Use symbols sparingly (emoji takes space)

Step 6: Test and Iterate

A/B test approach:

  1. Post with title variant A
  2. Measure CTR (click-through rate)
  3. Test variant B next time
  4. Keep what works

Common Mistakes

MistakeFix
Too longKeep under 20 characters
Clickbait without substanceDeliver on title's promise
VagueBe specific about value
No hookStart with number or curiosity
MisleadingTitle must match content

Real-World Impact

Great titles: 2-3x more clicks Poor titles: Great content gets <100 views

Key metric: Title is 50% of content success.


Related Skills:

  • REQUIRED: cover-design (cover text = title)
  • REQUIRED: content-planning (title matches content type)
  • copywriting-skills (write compelling body)
  • hashtag-optimization (add tags for discovery)

Frequently asked questions

What does the Title Writing AI skill do?

Use when writing Xiaohongshu post titles, creating headlines for content, improving click-through rates, or optimizing titles for search and discovery

Why use Title Writing on TypingMind?

Because you install it once and use it with any model. Title Writing is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Title Writing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vivy-yi/xiaohongshu-skills/tree/main/skills/01-内容创作/title-writing. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Title Writing?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Title Writing?

As many as you like. As long as a model supports skills, you can use Title Writing with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Title Writing AI skill free?

It is published on GitHub by vivy-yi. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇