agentleFS
Sign inStart free
mindfold-aimindfold-ai/xhs-content/SKILL.md

xhs-content

Skill17 starsChanged 8 months agoMITView on GitHub

XiaoHongShu (小红书) content creation tool. Collects trending XHS notes by keyword, generates a topic research report, then produces XHS-style note drafts. Use when the user wants to: (1) research what's trending on XiaoHongShu/小红书 for a topic, (2) generate XHS note drafts, (3) find XHS content inspiration, or mentions "小红书", "XHS", "xiaohongshu", "xhs content", "xhs note".

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. guzhezao/ai-content-skills★ 2same name
    2. guzhezao/xhs-content-skill★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When this skill is triggered:

    line 48
  2. Distinctive:

    Ask user for keyword (if not provided)

    line 50
  3. Very specific:

    Run xhs-search.py to collect posts → save JSONL

    line 51
  4. Distinctive:

    Read JSONL, generate report markdown

    line 52
  5. Very specific:

    Read report + references/prompt.md, generate note drafts

    line 53
  6. Very specific:

    All outputs go to .claude/skills/xhs-content/data/<date>-<keyword>/:

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

XHS Content — 小红书选题采集 + 内容生成

从小红书采集热门笔记 → 汇总选题报告 → 生成笔记草稿。

Prerequisites

  • Python 3 — 运行采集脚本
  • xhs-cli — 小红书 CLI 工具 (pipx install xhs-cli 或 uv tool install xhs-cli)
  • 已登录 (xhs login — 支持 QR 码 / cookie / Chrome 自动提取)

Usage

给定一个关键词，执行三步流程：

Step 1: 采集

python3 scripts/xhs-search.py --keyword "<关键词>" --limit 30

采集结果自动保存到 data/<date>-<keyword>/sources.jsonl。

Step 2: 汇总报告

读取 sources.jsonl，生成选题报告 data/<date>-<keyword>/report.md，包含：

  • 话题热度概览（总笔记数、平均互动）
  • 热门角度分类（按标题/内容聚类）
  • Top 笔记摘要（标题、互动数据、核心观点）
  • 选题建议（基于数据的差异化切入点）
  • 全部采集笔记表格（标题、作者、赞/藏/评、链接，按互动量降序）

Step 3: 生成笔记

基于报告 + 固定 prompt，生成 1-3 篇小红书笔记草稿，保存到 data/<date>-<keyword>/drafts.md。

Workflow (for Claude)

When this skill is triggered:

  1. Ask user for keyword (if not provided)
  2. Run xhs-search.py to collect posts → save JSONL
  3. Read JSONL, generate report markdown
  4. Read report + references/prompt.md, generate note drafts
  5. Present drafts to user for review

Data Directory

All outputs go to .claude/skills/xhs-content/data/<date>-<keyword>/:

  • sources.jsonl — raw collected posts
  • report.md — topic research report
  • drafts.md — generated note drafts

References

  • references/prompt.md — Fixed generation prompt with XHS style rules

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free