agentleFS
DeliciousBudingDeliciousBuding/xiaohongshu-skill/SKILL.md

xiaohongshu-skill

Skill43 starsChanged 3 months agoApache-2.0View on GitHub

小红书 / Xiaohongshu / RedNote AI Agent Skill。用 Python Playwright 搜索和读取内容、管理登录会话、发布图文/视频/长文、评论、点赞和收藏;默认输出 JSON,任何写操作都必须先获得用户确认。用户提到 xiaohongshu、小红书、rednote、小红书搜索、发到小红书、小红书笔记分析、小红书运营或小红书自动化时触发。

4 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 1

    1. chrisopal/skills★ 1163% same

    Wrote their own version · 3

    1. KimYx0207/Kim_Service★ 185same name
    2. Ancienttwo/xiaohongshu-skill★ 2same name
    3. Ancienttwo/growth-hacker★ 1same 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.

  • In this repository3 other files it gives its agents.

The file

Files
SKILL.md

小红书 Skill

通过 JSON CLI 操作小红书浏览器会话。执行入口统一为:

cd {baseDir}
uv run python -m scripts <command>

安全规则

发布、评论、回复、点赞、收藏、取消点赞和取消收藏会改变真实账号状态。执行前必须:

  1. 展示目标账号、内容、媒体和操作类型。
  2. 获得用户明确确认。
  3. 只执行用户确认的单次操作。

遇到验证码、登录页或安全验证页时停止。不要自动绕过验证,不要运行批量抓取或批量互动。

任务路由

用户目标命令或参考
首次登录或重新登录qrcode --headless=false
检查登录check-login
管理多个账号--profile <name>;详见 docs/INSTALL.md
搜索笔记search
读取笔记详情feed
读取用户主页user 或 me
获取推荐流explore
准备或发布图文publish
准备或发布视频publish-video
Markdown 转图片发布publish-md
准备或发布长文publish-longform
评论和回复comment、reply、reply-notification
点赞和收藏like、collect、unlike、uncollect
模板、策略和 SOPtemplate、strategy-*、sop
查看参数python -m scripts <command> --help

完整命令见 docs/API.md;安装和平台接入见 docs/INSTALL.md、docs/INTEGRATIONS.md。

初始化

cd {baseDir}
uv sync --frozen --no-dev
uv run playwright install chromium
uv run python -m scripts qrcode --headless=false

开发者使用:

uv sync --frozen --group dev
uv run python -m scripts.quality check

只读示例

uv run python -m scripts search "咖啡" --limit=5
uv run python -m scripts feed <feed_id> <xsec_token>
uv run python -m scripts explore --limit=10

feed_id、user_id 和 xsec_token 必须来自当前会话的结果,不要长期缓存。

发布语义

发布命令默认填写表单并返回 ready。用户确认后才能追加 --auto-publish。

自动提交可能返回:

  • confirmed:已观察到可信成功信号。
  • submitted_unconfirmed:已点击提交但未确认成功;必须人工复核,禁止自动重试。
  • failed:提交失败或出现登录、验证码、安全验证等失败信号。

输出和错误

标准输出是 JSON;诊断信息写入标准错误。Agent 应先读取 status,再依据 scripts/output_contracts.py 中的契约处理字段。

发生 captcha_required 或浏览器安全验证时,不要重试循环。切换到有头模式并由用户处理。

本地状态

每个 profile 独立保存浏览器状态、Cookie 备份和会话元数据。不要读取、展示、提交或外发这些文件。XHS_FP_SEED 只用于显式覆盖当前进程的稳定指纹 seed。

安全和隐私规则见 docs/SECURITY.md。架构说明见 docs/ARCHITECTURE.md。

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.