Agent skill

Xhs Auto Publisher

by DjangoPeng in DjangoPeng/agentic-ai

面向云服务器的小红书图文自动发布 Skill。适用于需要在 Linux 云服务器上,通过 Playwright/CDP、二维码人工接管、登录缓存、龙虾代发飞书群图片消息、截图留痕与审计日志来完成小红书草稿或发布流程的场景。

MITAuto-check passedTesting & QA

Install Xhs Auto Publisher

skills CLI
$ npx skills add DjangoPeng/agentic-ai --skill xhs-auto-publisher -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install DjangoPeng/agentic-ai xhs-auto-publisher --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/DjangoPeng/agentic-ai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/xhs-auto-publisher .claude/skills/xhs-auto-publisher && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
xhs-auto-publisher
GitHub stars
152
Token cost
~570 tokens
SKILL.md length
135 words
Files
32 (incl. scripts)
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

面向云服务器的小红书图文自动发布 Skill。适用于需要在 Linux 云服务器上,通过 Playwright/CDP、二维码人工接管、登录缓存、龙虾代发飞书群图片消息、截图留痕与审计日志来完成小红书草稿或发布流程的场景。

  • Works in 7 steps: Agent 打开小红书登录页 → Agent 截出二维码图片 → 项目生成 login_qr.payload.json → …
  • Tasks that involve Browser testing
  • SKILL.md covers 默认链路, 适用场景, 项目结构 and 部署分层, plus 8 more sections
  • Runs Shell scripts from its folder; calls bash

What it does

Xhs Auto Publisher is an agent skill from DjangoPeng/agentic-ai. 面向云服务器的小红书图文自动发布 Skill。适用于需要在 Linux 云服务器上,通过 Playwright/CDP、二维码人工接管、登录缓存、龙虾代发飞书群图片消息、截图留痕与审计日志来完成小红书草稿或发布流程的场景。

Its SKILL.md is about 570 tokens, which your agent loads only when the skill is triggered. The skill folder holds 37 other files, including scripts (for example `README.md`, `config/app.json` and `config/selectors.json`).

It sits in Testing & QA, covering Browser testing. It works with Xiaohongshu, Linux, Playwright and Python. The repository describes itself as: 一套经过生产验证的 OpenClaw + Claude Code 实战知识库:涵盖生产部署、IM 接入、模型配置、安全加固,以及一系列可落地的 AI Agent 业务流项目(小红书发布 / 财务票据 / 智能早报 / CRM / 量化投研 / 密钥巡检自愈)。 The licence is MIT.

When your agent uses it

  • Tasks that involve Browser testing

Example prompts

  • “/xhs-auto-publisher”

Requirements

  • Python 3
  • A Bash shell

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Agent 打开小红书登录页
  2. Agent 截出二维码图片
  3. 项目生成 login_qr.payload.json
  4. 龙虾读取 payload
  5. 龙虾把二维码图片直接发到飞书群
  6. 用户扫码
  7. Agent 继续执行

What it can do on your machine

Read from SKILL.md and the folder at commit c8bc8f1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • bash

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Xhs Auto Publisher loads about 570 tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 135 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~570

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from DjangoPeng/agentic-ai at commit c8bc8f1, republished under its MIT licence (© DjangoPeng). 135 words, ~570 tokens.

Download SKILL.mdSave it as .claude/skills/xhs-auto-publisher/SKILL.md (or your agent's skills folder). This skill also uses 31 other files; get the full folder from GitHub.
name
xhs-auto-publisher
description
面向云服务器的小红书图文自动发布 Skill。适用于需要在 Linux 云服务器上,通过 Playwright/CDP、二维码人工接管、登录缓存、龙虾代发飞书群图片消息、截图留痕与审计日志来完成小红书草稿或发布流程的场景。

XHS Auto Publisher Cloud

这个 Skill 是云端执行版,不是本机版替代品。

它主要解决四件事:

  • 在 Linux 云服务器上跑浏览器自动化
  • 把登录二维码交给人扫码
  • 把登录状态缓存起来
  • 把执行结果留痕

默认链路

当前项目只保留一条默认链路:

  1. Agent 打开小红书登录页
  2. Agent 截出二维码图片
  3. 项目生成 login_qr.payload.json
  4. 龙虾读取 payload
  5. 龙虾把二维码图片直接发到飞书群
  6. 用户扫码
  7. Agent 继续执行

不依赖公网二维码链接,不依赖 XHS_PUBLIC_RUNTIME_BASE_URL。

适用场景

适合:

  • 在云服务器上跑小红书图文草稿/发布
  • 需要人工扫码接管登录
  • 需要持久化浏览器 profile
  • 需要截图、日志、DOM 快照
  • 需要把标准化部署交给龙虾执行

不适合:

  • 绕过验证码、滑块、人机验证
  • 批量互动、批量点赞、批量评论
  • 操作未授权账号

项目结构

  • config/:平台配置与选择器
  • src/:发布逻辑、登录检测、通知模块
  • scripts/:CLI 入口
  • deploy/:部署脚本与 systemd 示例
  • docs/:部署说明和龙虾执行文档
  • runtime/:浏览器 profile、截图、运行结果

部署分层

系统级

这部分影响整台机器:

  • python3
  • python3-venv
  • python3-pip
  • xvfb
  • 浏览器运行依赖
项目级

这部分只属于当前目录:

  • .venv
  • Python 依赖
  • Playwright Chromium
  • runtime/

推荐目录

text
~/projects/xhs-auto-publisher
~/projects/xhs-auto-publisher/runtime
~/projects/xhs-auto-publisher/runtime/browser-profile
~/projects/xhs-auto-publisher/runtime/runs
~/projects/xhs-auto-publisher/runtime/lobster-notify

输入格式

发布内容使用 JSON 文件,例如:

json
{
  "title": "OpenClaw 能帮业务团队做什么?",
  "body": "很多团队不是缺 AI 聊天工具,而是缺一个能把业务流程真正跑起来的数字员工。",
  "topics": ["OpenClaw", "AI工具", "浏览器自动化"],
  "images": ["assets/cover.jpg"],
  "mode": "publish"
}

环境变量

当前只保留最常用的两个:

env
MODE=publish
LOGIN_TIMEOUT=300

运行方式

手动运行:

bash
cd ~/projects/xhs-auto-publisher
bash deploy/run_with_xvfb.sh

执行流程

  1. 校验内容和图片
  2. 检查重复发布保护
  3. 启动持久化 Chromium profile
  4. 读取登录缓存,默认 12 小时
  5. 检查是否已登录
  6. 如未登录,生成二维码截图并写出龙虾通知 payload
  7. 龙虾把二维码图片发到飞书群
  8. 用户扫码后继续
  9. 上传图片、填写内容、触发发布
  10. 保存截图、日志、DOM 快照和结果 JSON

运行产物

每次执行都会写入:

text
runtime/runs/<timestamp>/

包含:

  • actions.jsonl
  • result.json
  • content.normalized.json
  • screenshots/*.png
  • dom/*.html

通知文件会写入:

text
runtime/lobster-notify/<run_id>/login_qr.payload.json

文档入口

当前定位

这不是并发平台,而是一套稳妥的单机顺序执行方案:

  • 单机
  • 单浏览器
  • 单任务
  • 人工扫码接管
  • 有留痕
  • 可复跑

© DjangoPeng, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 31 other files (scripts) in xhs-auto-publisher of DjangoPeng/agentic-ai.

  • SKILL.md
  • .gitignore
  • README.md
  • config/app.json
  • config/selectors.json
  • deploy/bootstrap_project.sh
  • deploy/env.example
  • deploy/install_system_ubuntu.sh
  • deploy/run_with_xvfb.sh
  • deploy/setup.sh
  • deploy/systemd/xhs-auto-publisher-cloud.service
  • docs/DEPLOY_TODO.md
  • docs/LOBSTER_NOTIFY_PROTOCOL.md
  • docs/cloud_deploy.md
  • examples/assets/Openclaw商业应用场景.jpg
  • … and 17 more

Open the folder on GitHubat commit c8bc8f1

Compare with similar skills

Xhs Auto Publisher next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Xhs Auto Publisher compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Xhs Auto Publisher this skillDjangoPeng/agentic-ai152—~570Automated safety check: PassMIT
Web Application Testinganthropics/skills180k51 repos~966Automated safety check: PassApache-2.0
RStudio Selenium to Playwright Migrationrstudio/rstudio5.1k—~3.6kAutomated safety check: PassCustom licence
Brightdata Proxybrightdata/skills264—~5.1kAutomated safety check: PassMIT
JS-in-HTML Testingliaohch3/claude-tap3.3k—~924Automated safety check: PassMIT
Playwright Screen Recordingliaohch3/claude-tap3.3k—~714Automated safety check: PassMIT

Similar skills

  • Web Application Testing

    anthropics/skills

    Official

    Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.

    180k GitHub starsUsed in 51 repos~966 tokens
    Testing & QAAuto-check passed
  • Converts RStudio Python Selenium electron tests into TypeScript Playwright tests, checking each against a live RStudio before counting it as migrated.

    5.1k GitHub stars~3.6k tokensUpdated today
    Testing & QAAuto-check passed
  • Brightdata Proxy

    brightdata/skills

    Generate working code that routes HTTP requests through Bright Data proxy networks (Datacenter, ISP, Residential, Mobile) and help users decide which network and IP pool type to use (shared pool…

    264 GitHub stars~5.1k tokensUpdated 4 days ago
    Testing & QAAuto-check passed
  • JS-in-HTML Testing

    liaohch3/claude-tap

    Tests JavaScript embedded in an HTML file in two layers: pytest checks of the logic ported to Python, and Playwright runs in a real browser for the DOM.

    3.3k GitHub stars~924 tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Playwright Screen Recording

    liaohch3/claude-tap

    Records headless Playwright sessions as .webm videos to show a bug fix working or to give pull request reviewers visual evidence.

    3.3k GitHub stars~714 tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Playwright Trace

    mellowagain/gitarena

    Inspect Playwright trace files from the command line — list actions, view requests, console, errors, snapshots and screenshots.

    115 GitHub starsUsed in 1 repo~1.2k tokens
    Testing & QAAuto-check passed

More from DjangoPeng/agentic-ai

  • 当用户希望生成 AI 早报、运行晨报链路、查看今日资讯摘要,或消息中包含”早报””晨报””今日资讯””新闻摘要”等关键词时触发。

    152 GitHub stars~974 tokensUpdated 3 mo ago
    Auto-check: notes
  • CRM Assistant

    DjangoPeng/agentic-ai

    将销售会议 transcript、飞书会议原始 JSON、飞书云文档正文或 Word/DOCX 会议纪要,转换成 CRM 结构化结果,并按客户信息表 + 商机推进快照表两表模型生成/同步飞书多维表格记录时使用。适用于多轮客户推进、客户画像增量更新、商机阶段判断、Lead Score 计算,以及“弱值不覆盖旧值、沟通风格/风险顾虑合并”的客户字段更新规则。

    152 GitHub stars~681 tokensUpdated 3 mo ago
    Auto-check passed
  • Financial Expense Automation

    DjangoPeng/agentic-ai

    当用户上传 PDF、JPG、JPEG、PNG 附件,或消息中包含"报销""发票""票据""录入""火车票""机票"等关键词时触发。对附件内容进行识别,若确认为报销票据则提取结构化字段并写入飞书多维表格;若识别后内容不是报销票据,告知用户并终止流程。

    152 GitHub stars~816 tokensUpdated 3 mo ago
    Auto-check passed
  • GitHub Secret Auditor

    DjangoPeng/agentic-ai

    当用户希望让 OpenClaw 通过 ACP 调度 Claude Code,对 GitHub 仓库进行 API Key、Token、密码、私钥、Webhook URL 等敏感信息泄露巡检、自动修复、验收、推送修复 commit,并通过飞书发送巡检报告时使用。

    152 GitHub stars~2.8k tokensUpdated 3 mo ago
    Auto-check: notes

Categories

Questions about Xhs Auto Publisher

What does Xhs Auto Publisher do?

面向云服务器的小红书图文自动发布 Skill。适用于需要在 Linux 云服务器上,通过 Playwright/CDP、二维码人工接管、登录缓存、龙虾代发飞书群图片消息、截图留痕与审计日志来完成小红书草稿或发布流程的场景。. Xhs Auto Publisher is an agent skill from DjangoPeng/agentic-ai.

When should I use Xhs Auto Publisher?

Xhs Auto Publisher fits situations like: tasks that involve Browser testing.

How do I install Xhs Auto Publisher in Claude Code?

Run `npx skills add DjangoPeng/agentic-ai --skill xhs-auto-publisher -a claude-code`. Or copy the skill folder (xhs-auto-publisher in DjangoPeng/agentic-ai) into .claude/skills/xhs-auto-publisher in your project. Claude Code loads it when a task matches its description.

How do I install Xhs Auto Publisher in Codex?

Run `npx skills add DjangoPeng/agentic-ai --skill xhs-auto-publisher -a codex`. Or copy the skill folder (xhs-auto-publisher in DjangoPeng/agentic-ai) into .agents/skills/xhs-auto-publisher in your project. Codex loads it when a task matches its description.

Can I use Xhs Auto Publisher in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add DjangoPeng/agentic-ai --skill xhs-auto-publisher -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xhs-auto-publisher, .gemini/skills/xhs-auto-publisher, .github/skills/xhs-auto-publisher and .opencode/skills/xhs-auto-publisher in your project.

What does Xhs Auto Publisher need to run?

Going by SKILL.md and its folder, Xhs Auto Publisher needs a shell for the scripts in its folder and the command-line tools its instructions call (bash). Our summary lists: Python 3; A Bash shell.

Does Xhs Auto Publisher access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Xhs Auto Publisher safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Xhs Auto Publisher use?

Xhs Auto Publisher is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Xhs Auto Publisher use?

About 570 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Xhs Auto Publisher?

Skills that share tags, products or a category with Xhs Auto Publisher: Web Application Testing (anthropics/skills, 180k stars), RStudio Selenium to Playwright Migration (rstudio/rstudio, 5.1k stars), Brightdata Proxy (brightdata/skills, 264 stars) and JS-in-HTML Testing (liaohch3/claude-tap, 3.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Xhs Auto Publisher?

DjangoPeng (a GitHub user) maintains it in DjangoPeng/agentic-ai, which has 152 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on July 8, 2026.

Source: DjangoPeng/agentic-ai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.