write-xiaohongshu

Write Xiaohongshu (小红书: research first, then write, then post)

Quick Start (shortest usage)

When the user gives you a topic, directly run the full process according to "Steps 0→6"; in the end output only:

Title (≤20 characters)
Body (≤1000 characters)
Tags (#xxx #yyy…)
Images (if the user provides images, use the provided images; if not, choose 1~2 yourself, 9:16 preferred)
Publish after user review
Publish result (if Xiaohongshu MCP is available)

Hard limits (must be followed)

Title:≤ 20 characters
Body:≤ 1000 characters

Counting basis: count by "characters" (including spaces, punctuation, line breaks, #topics, etc.). To be safe: keep the title as close to ≤18 as possible, and the body as close to ≤950 as possible, leaving margin for tags/formatting.

Output (must include these blocks)

The output of this skill is divided into three parts:

Analysis summary report(must be given first after completing the analysis in steps 1+2; for the structure, see the template below)
Final publishable draft(title + body + tags + images)
Publish result after review

标题：<不超过20字符>
正文：
<不超过1000字符>
标签：#标签1 #标签2 #标签3 ...
配图：<1~2张，9:16优先；给出图片URL或本地路径>

If the publishing interface supports a "separate tags field", then do not pile #tags into the body; put the tags into the publishing parameters; in the end it is still necessary to ensure the body itself is ≤1000.

Overall process (must be done in order)

flowchart TD
  A[检查登录状态] --> B[小红书找Top10图文]
  B --> C[拆标题&正文规律 + 点赞高原因]
  C --> D[抓评论并分析情绪共鸣点]
  D --> E[Firecrawl补背景&事实校验]
  E --> F[写标题/正文/标签 + 字数自检]
  F --> G{用户是否提供图片?}
  G -- 是 --> H[用用户图片]
  G -- 否 --> I[网上找1~2张高清9:16图]
  H --> J[用小红书MCP发布]
  I --> J

Step 0: First check login status

First call Xiaohongshu MCP to check the login status; if not logged in, obtain a QR code for the user to log in.

Step 1: Find related "Top 10 by likes" image-text posts on Xiaohongshu, and summarize the patterns

Goal: first find "the most popular way of writing within similar content", then start writing.

Hard threshold (must be executed)

Must successfully obtain at least 10 image-text posts with "complete and usable post details", only then can you proceed to steps 2/3/4/5/6.

Requirements:

Only selectimage-text posts(exclude videos/livestream clips)
Relevance first, then high like count; filter by "most liked"
Filter time to "within half a year"
Only use Xiaohongshu MCP's get_specified_post tool to obtain posts; filter posts that are "image-text" and "within half a year", obtain 20 posts' data (the actual result may be fewer than 20, tolerate 10), do not call other MCP tools; the content returned by this tool contains all the needed information.

For each Top post, record these fields (for later analysis):

Title (original text)
Likes/favorites/comments (if available)
Body structure (summarize in 1 line: e.g. "conclusion→checklist→steps→feedback→interaction")
Key hook (the "attraction point" of the first sentence at the beginning)
Evidence type (experience, comparison, data, screenshots, before-and-after changes…)
Interaction design (questions, polls, comment keywords, giveaways, collection guidance…)

Output a "pattern summary" (directly reusable for writing):

Title patterns (length, sentence structure, keywords, symbols/numbers, emotional words, benefit points)
Body patterns (paragraph rhythm, lists/steps, transitions, pitfalls to avoid, closing CTA, tone style)
Reasons for high likes (at least 3, grounded in "writing style/information density/resonance points/actionability/tone style" as much as possible)

Step 2: Based on the comments in the Step 1 data, analyze the reasons for "emotional resonance"

Goal: Find out why viewers "want to comment/want to share/want to save", summarize 3-6 resonance point conclusions, and 1 interaction design suggestion.

Method:

Categorize the "resonance triggers" in the comments, for example:
- Shared pain points (me too...)
- Identity recognition (office worker/student/mom...)
- Anxiety and solutions (finally there's a way/saved)
- Values (self-discipline, relaxed vibe, cost-effectiveness, minimalism...)
- Contrast/surprise (so this works too)
- Replicability (I can do it too)
- Desire to share (I want to try it too)
- Curiosity (what is this?)
- Resonance point (I'm like this too)

Output:

3-6 "resonance point conclusions" (each conclusion paired with 1-2 original quote fragments/summaries)

Analysis summary report (must be output, then automatically continue with the subsequent process)

After you complete Steps 1+2 (and meet "usable samples >= 10"),you must first output a summary report according to the structure below(refer to the user's example for content style/level of detail), and then in the same round of outputautomatically continue with Steps 3->6。

If the sample threshold is not met: according to the hard threshold requirement in Step 1,stop directly, do not enter Steps 2/3/4/5/6, and do not fabricate a report.

Report template:

【分析总结报告】
评论数/互动量排名（从高到低）
1. <标题> - <评论数>（<图文/视频>）
2. ...
...
10. ...
11. ...

标题规律分析
- <规律1>
- <规律2>
- <规律3>
...

内容规律分析
- <规律1>
- <规律2>
...

封面规律分析
- <规律1>
- <规律2>
...

总结
爆款三要素：
1. <要素1>
2. <要素2>
3. <要素3>

互动催化剂：
- <催化剂1>
- <催化剂2>
...

Step 3: Use Firecrawl MCP to supplement background knowledge (and perform fact-checking)

Goal: Avoid empty content, avoid errors/exaggeration, and fill in "credible information."

Method:

Use topic keywords to expand retrieval: concept explanations, common misconceptions, authoritative recommendations, data (from credible sources as much as possible)
Distill into "5-10 citable background points" (short sentences are fine)
Downgrade claims that are easily questioned (efficacy, returns, comparative conclusions):
- Change to "my personal experience/only suitable for some people/may be effective"
- Or add conditions (applicable population, prerequisites)

Output a "background knowledge card":

Key conclusions (5-10 items)
Risks/precautions (2-4 items)

Step 4: Based on the above analysis, write the title + body + tags (and enforce word count self-check)

Writing requirements (leaning toward Xiaohongshu/RED, but don't be fake):

Colloquial, short sentences, line break every 1-3 sentences
High information density: less empty talk, more "steps/checklists you can follow"
Emoji can be used appropriately (to improve rhythm/emotion), but do not pile them on
The ending should be natural, like something a real user wrote, not a "marketing account tone"

De-AI-flavor prompt (must be executed)

Write more "I/at the time I/I found/I've stepped in this pit", and use less "everyone/users/audience/suggestions are as follows"
Give 2–3 specific details: time points, scenes, before-and-after comparisons, one specific line of dialogue / one shot / one small action
Allow imperfection: use "I feel / I guess / maybe / not sure but…" (don't pretend to be authoritative)
Fewer template phrases: avoid "in conclusion / in summary / therefore / firstly secondly finally / not to be missed / hurry"
Like chatting with a friend: short sentences, line breaks, occasional colloquial words (but don't pile them up)

Word count gate (must be done last)：

Title character count > 20: delete redundant words, remove subtitles, shorten sentences, remove unnecessary symbols
Body character count > 1000: first delete repetitions and catchphrases, then merge sentences, then compress steps/reduce examples
Finally output only the compliant version

Step 5: If the user didn't provide images, find 1–2 high-definition images online yourself (9:16 preferred)

Requirements:

1–2 images is enough, high-definition, clean, strongly related to the topic
Aspect ratio preferably 9:16 (vertical image)
Only choosecommercially usable/no copyright risksources preferred (e.g., Pexels / Unsplash, etc.)
When outputting, provide: image URL (and optionally: local download path)

Step 6: Publish using Xiaohongshu MCP

When publishing (adapt to MCP capabilities, do as much as possible):

Upload 1–2 images (vertical images preferred)
Set title, body, tags
If supported: first create a draft → echo draft information → then publish

After successful publishing, output:

Published link/ID (if available)
Publishing parameter summary (title/tags/number of images)

Fallback strategy (when tools are unavailable)

If the current environment does not have Firecrawl MCP or Xiaohongshu MCP:

Still complete "analysis → writing → image links" according to the process, but do not auto-publish
List the information the user needs to supplement as the shortest checklist (for example: provide 3~5 benchmark post links, or authorization/API configuration)

Examples

Example 1: The user only gives a topic

User input:

Write a Xiaohongshu image-and-text post: the topic is "quick dinner for office workers", suitable for one person, budget within 20 yuan.

You need to do:

Use topic keywords to find "image-and-text posts" on Xiaohongshu, summarize title/body patterns
Capture the comments on these posts, extract resonance points and interactive questions
Use Firecrawl to supplement "health/meal prep/safety"-related background
Output title + body + tags, and do a word count self-check
If there are no images, find 1~2 high-definition 9:16 vertical images
Publish using Xiaohongshu MCP (if available)

Example 2: The user provides images