agentleFS
chang-zychang-zy/xiaohongshu-skill/CLAUDE.md

xiaohongshu-skill

CLAUDE.md2 starsChanged 58 days agoMITView on GitHub

小红书自动化 Claude Code Skills,使用用户的真实浏览器和账号信息操作小红书。 双层结构:scripts/ 是 Python 自动化引擎,skills/ 是 Claude Code Skills 定义(SKILL.md 格式)。 CLI 会自动检测环境,若浏览器未打开也会自动启动 Chrome。

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. autoclaw-cc/xiaohongshu-skills★ 1.9k100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    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.

  • In this repository6 other files it gives its agents.

The file

Files
CLAUDE.md

xiaohongshu-skills

小红书自动化 Claude Code Skills,使用用户的真实浏览器和账号信息操作小红书。

Git 工作流

  • 所有代码修改必须在分支上进行,禁止直接推送 main 分支
  • 分支开发完成后通过 PR 合入 main

开发命令

uv sync                    # 安装依赖
uv run ruff check .        # Lint 检查
uv run ruff format .       # 代码格式化
uv run pytest              # 运行测试

架构

双层结构:scripts/ 是 Python 自动化引擎,skills/ 是 Claude Code Skills 定义(SKILL.md 格式)。

  • scripts/xhs/ — 核心自动化库(模块化,每个功能一个文件)
  • scripts/cli.py — 统一 CLI 入口,JSON 结构化输出,自动启动 bridge server 和浏览器
  • scripts/bridge_server.py — 本地通信服务(连接 CLI 与浏览器扩展)
  • extension/ — Chrome 扩展,在用户的真实浏览器中执行操作
  • skills/*/SKILL.md — 指导 Claude 如何调用 scripts/

调用方式

python scripts/cli.py check-login
python scripts/cli.py search-feeds --keyword "关键词"
python scripts/cli.py publish --title-file t.txt --content-file c.txt --images pic.jpg

CLI 会自动检测环境,若浏览器未打开也会自动启动 Chrome。

代码规范

  • 行长度上限 100 字符
  • 完整 type hints,使用 from __future__ import annotations
  • 异常继承 XHSError(xhs/errors.py)
  • CLI exit code:0=成功,1=未登录,2=错误
  • 用户可见错误信息使用中文
  • JSON 输出 ensure_ascii=False

安全约束

  • 发布类操作必须有用户确认机制
  • 文件路径必须使用绝对路径
  • 敏感内容通过文件传递,不内联到命令行参数

CLI 子命令对照表

CLI 子命令对应 MCP 工具分类
check-logincheck_login_status认证
loginget_login_qrcode认证
phone-login—认证
delete-cookiesdelete_cookies认证
list-feedslist_feeds浏览
search-feedssearch_feeds浏览
get-feed-detailget_feed_detail浏览
user-profileuser_profile浏览
post-commentpost_comment_to_feed互动
reply-commentreply_comment_in_feed互动
like-feedlike_feed互动
favorite-feedfavorite_feed互动
publishpublish_content发布
publish-videopublish_with_video发布
fill-publish—分步发布(图文填写)
fill-publish-video—分步发布(视频填写)
click-publish—分步发布(点击发布)
long-article—长文发布(填写+排版)
select-template—长文发布(选择模板)
next-step—长文发布(下一步+描述)
get-netlog—风控数据
risk-report—风控数据

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.