Agent skill

Han Jr System

by LeoYeAI in LeoYeAI/openclaw-master-skills

小翰系统:1688平台自动化供应商联系系统。使用场景:用户需要联系1688供应商、发送询价消息、收集报价时。触发于如联系1688铅笔供应商、搜索dgx spark供应商等任务。严格遵守逐家联系、验证优先、准确性优先原则。

MITAuto-check passed

Install Han Jr System

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill han-jr-system -a claude-code

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

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills han-jr-system --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/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/han-jr-system .claude/skills/han-jr-system && 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
han-jr-system
GitHub stars
2.2k
Token cost
~2.8k tokens
SKILL.md length
432 words
Files
108 (incl. scripts, references)
Skills in repo
1,235
Repo updated
First seen
Licence
MIT

At a glance

小翰系统:1688平台自动化供应商联系系统。使用场景:用户需要联系1688供应商、发送询价消息、收集报价时。触发于如联系1688铅笔供应商、搜索dgx spark供应商等任务。严格遵守逐家联系、验证优先、准确性优先原则。

  • Works in 6 steps: 启动Chrome → 搜索供应商(搜索框输入方式) → 处理反爬虫/滑块验证码 → …
  • SKILL.md covers Overview, ⚠️ 重要:反爬虫解决办法, 依赖安装 and Workflow, plus 6 more sections
  • Runs Python scripts from its folder; calls python, pip and playwright; reaches air.1688.com and detail.1688.com

What it does

Han Jr System is an agent skill from LeoYeAI/openclaw-master-skills. 小翰系统:1688平台自动化供应商联系系统。使用场景:用户需要联系1688供应商、发送询价消息、收集报价时。触发于如联系1688铅笔供应商、搜索dgx spark供应商等任务。严格遵守逐家联系、验证优先、准确性优先原则。

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 109 other files, including scripts and reference files (for example `RESOLVED_ISSUES.md`, `STATUS_REPORT.md` and `TODAY_UPDATE.md`).

It works with 1688 and Python. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

Example prompts

  • “/han-jr-system”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. 启动Chrome
  2. 搜索供应商(搜索框输入方式)
  3. 处理反爬虫/滑块验证码
  4. 联系供应商(逐家)
  5. 验证步骤
  6. 完整工作流

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. 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 9 files in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python
    • pip
    • playwright

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • air.1688.com
    • detail.1688.com

    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

Han Jr System loads about 2.8k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 31 tokens; SKILL.md has 432 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.3k

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 LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 432 words, ~2,818 tokens.

Download SKILL.mdSave it as .claude/skills/han-jr-system/SKILL.md (or your agent's skills folder). This skill also uses 107 other files; get the full folder from GitHub.
name
han-jr-system
description
小翰系统:1688平台自动化供应商联系系统。使用场景:用户需要联系1688供应商、发送询价消息、收集报价时。触发于如联系1688铅笔供应商、搜索dgx spark供应商等任务。严格遵守逐家联系、验证优先、准确性优先原则。
version
1.0.0

Han Jr System - 1688 供应商联系系统

Overview

小翰系统提供完整的1688供应商联系自动化工作流,强调:

  • 逐家联系:一次只联系一家供应商,等待回复后再联系下一家
  • 严格验证:每个步骤后10秒First Check,失败则20秒Double Check
  • 准确性优先:宁可慢,不要错,所有操作必须验证后才报告成功
  • 真实执行:使用实际脚本(playwright + Chrome CDP),非模拟

⚠️ 重要:反爬虫解决办法

问题现象

当搜索频繁或触发安全机制时,页面会跳转到包含 _____tmd_____ 的URL,并显示滑块验证码。

解决方法

使用 slider_captcha.py 脚本自动解决滑块验证码:

bash
python slider_captcha.py --selector "#nc_1_n1z" --distance 260 --duration 1.5

参数说明:

  • --selector: 滑块元素的CSS选择器(默认: #nc_1_n1z)
  • --distance: 拖动距离(像素,默认: 260)
  • --duration: 拖动持续时间(秒,默认: 1.5)

滑块元素常见选择器:

#nc_1_n1z
.nc_iconfont.btn_slide
span[aria-label="滑块"]
[data-spm-anchor-id*="slide"]
工作流程(含反爬虫处理)
bash
# 1. 启动Chrome
python chrome_launch.py

# 2. 搜索供应商
python search_box_v2.py --keyword "铅笔" --num 5 --output suppliers.json

# 3. 如果遇到滑块验证码,自动解决
python slider_captcha.py --selector "#nc_1_n1z" --distance 260

# 4. 继续搜索或联系供应商
python search_box_v2.py --keyword "钢笔" --num 5 --output suppliers2.json
注意事项
  1. 真正的反爬虫标志:页面上出现 "Sorry, we have detected unusual traffic from your network."
  2. URL包含 _____tmd_____ 不一定是反爬虫,可能是其他错误
  3. 解决验证码后,页面会恢复正常,可以继续操作
  4. 建议搜索间隔:每个关键词之间等待 3-5 秒,避免频繁触发

依赖安装

首次使用前安装依赖:

bash
pip install playwright requests beautifulsoup4 easyocr pillow numpy
playwright install chromium

Workflow

Step 1: 启动Chrome
bash
python chrome_launch.py
  • 启动Chrome with remote debugging (port 9222)
  • 10秒First Check:验证CDP连接
  • 失败则20秒Double Check
Step 2: 搜索供应商(搜索框输入方式)
bash
python search_box_v2.py --keyword "铅笔" --num 5 --output suppliers.json
  • 必须通过搜索框输入关键词,不要通过URL参数搜索
  • 在1688真实搜索(非百度)
  • 提取供应商名称、链接、价格、地区
  • 10秒First Check:验证结果包含关键词
  • 保存到JSON文件(UTF-8编码,避免乱码)

重要: 搜索框输入方式更稳定,不易触发反爬虫机制

Step 3: 处理反爬虫/滑块验证码
bash
python slider_captcha.py --selector "#nc_1_n1z" --distance 260
  • 当页面出现滑块验证码时执行
  • 模拟人类拖动行为(带随机抖动和缓动函数)
  • 验证成功后继续操作
Step 4: 联系供应商(逐家)
bash
python 1688_send_message.py --offer <供应商链接> "需要铅笔,请报价"
  • 打开供应商页面
  • 点击"客服"按钮
  • 发送询价消息
  • 10秒First Check:截图验证消息已发送
Step 5: 验证步骤
bash
python verify_step.py --step "step_name" --text "期望文本" --double
  • 截图当前页面
  • OCR识别内容
  • 检查是否包含期望文本
  • 失败时自动Double Check
Step 6: 完整工作流
bash
python pencil_workflow.py
  • 执行完整流程(启动→搜索→联系→验证)
  • 自动处理所有步骤
  • 记录到文件

脚本说明

scripts/
脚本功能用法
chrome_launch.py启动Chrome并验证python chrome_launch.py
search_box_v2.py1688搜索(搜索框输入)python search_box_v2.py --keyword "铅笔" --num 5
slider_captcha.py解决滑块验证码python slider_captcha.py --selector "#nc_1_n1z"
batch_contact_final.py批量联系供应商(推荐)python batch_contact_final.py --keyword "棒球帽" --message "询价" --num 20
wangwang_chat_manager.py旺旺聊天管理器python wangwang_chat_manager.py --list
search_contact_fixed.py搜索旺旺联系人(重要)python search_contact_fixed.py --name "供应商"
supplier_manager.py供应商管理系统python supplier_manager.py list
1688_send_message.py发送询价消息python 1688_send_message.py --offer "链接" "消息"
verify_step.py截图OCR验证python verify_step.py --step "name" --text "期望"
batch_search.py批量搜索多个关键词python batch_search.py
pencil_workflow.py完整工作流python pencil_workflow.py
references/
  • soul_rules.md - SOUL.md核心规则摘要
  • popup_handling.md - 1688弹窗处理指南
  • inquiry_template.md - 询价消息模板
  • antibot_handling.md - 反爬虫处理指南(重要)

关键规则

  1. 逐家联系:一次只联系一家,等待回复后再下一家
  2. 硬性验证:每个步骤后必须10秒First Check,失败则20秒Double Check
  3. 验证后才报告:绝不报告"应该成功了",只报告"已验证成功"
  4. 准确性>速度:宁可慢,不要错
  5. Chrome启动:必须使用指定命令,失败告知用户
  6. 搜索方式:必须通过搜索框输入,不要通过URL参数搜索
  7. 编码:所有输出和文件必须使用UTF-8编码,避免乱码
  8. 反爬虫处理:遇到滑块验证码使用 slider_captcha.py 解决
  9. 聊天页面管理:每次只能有一个旺旺聊天页面打开,发送完消息后必须关闭,再回到搜索结果页联系下一家

🔍 旺旺图标定位规则(重要)

搜索结果页旺旺图标

在搜索结果页,每张产品卡片右下角有旺旺图标:

HTML特征:

html
<span class="J_WangWang ww-light ww-static" data-nick="供应商名称">
  <a href="https://air.1688.com/app/ocms-fusion-components-1688/def_cbu_web_im/..." 
     target="_blank" class="ww-link ww-inline ww-online">
    <span>旺旺在线</span>
  </a>
</span>

选择器优先级(按可靠性排序):

  1. .J_WangWang - 主要class名
  2. .ww-light 或 .ww-link - 旺旺链接
  3. a[href*="air.1688.com"][href*="im"] - 聊天页面链接
  4. a:has-text("旺旺在线") - 包含"旺旺在线"文本
  5. [data-spm-anchor-id*="offerlist"] - 商品列表中的旺旺

使用方法:

bash
# 从搜索结果页直接联系供应商
python search_and_contact.py --keyword "棒球帽" --message "询价内容" --num 10
店铺页旺旺图标

在供应商店铺页,旺旺图标通常在:

  • 页面顶部/侧边栏
  • 产品详情页右下角
  • 特征:img[src*="O1CN01is8OHl"] 或 img[src*="wangwang"]

使用方法:

bash
# 进入店铺页联系
python contact_supplier_wangwang.py --link "店铺链接" --message "询价内容"

📋 旺旺聊天页面 iframe 处理方法(重要)

问题

旺旺聊天页面使用 iframe 架构,消息输入框不在主页面,而是在特定的 frame 中。

解决方案
Show full SKILL.md (174 more words)Show less
Frame 结构

旺旺聊天页面通常包含 4 个 frames:

  • Frame 0: 主聊天框架(联系人列表)
  • Frame 1: 消息输入区域 ← 在这里发送消息
  • Frame 2: 分析/统计
  • Frame 3: 空白
正确的发送消息代码
python
# 遍历所有 frames 找到输入框
for frame in chat_page.frames:
    try:
        # 在 frame 中查找输入框
        inp = frame.locator("pre[contenteditable='true']").first
        if inp.is_visible():
            inp.click()
            inp.fill(message)
            
            # 点击发送按钮
            btn = frame.locator("button:has-text('发送')").first
            if btn.is_visible():
                btn.click()
                print("✓ 消息已发送")
                break
    except:
        continue
关键要点
  1. ✅ 使用 page.frames 遍历所有 frames
  2. ✅ 消息输入框通常在 Frame 1
  3. ✅ 使用 frame.locator() 在特定 frame 中查找元素
  4. ✅ 不需要点击联系人,直接发送消息即可
完整示例
python
from playwright.sync_api import sync_playwright

with sync_playwright() as p:
    browser = p.chromium.connect_over_cdp("http://localhost:9222")
    
    # 打开聊天页面
    chat_page = browser.contexts[0].new_page()
    chat_page.goto("旺旺链接", wait_until="domcontentloaded")
    time.sleep(4)
    
    # 发送消息
    message = "我要定制..."
    for frame in chat_page.frames:
        try:
            inp = frame.locator("pre[contenteditable='true']").first
            if inp.is_visible():
                inp.click()
                inp.fill(message)
                btn = frame.locator("button:has-text('发送')").first
                btn.click()
                print("✓ 消息已发送")
                break
        except:
            continue
    
    chat_page.close()
    browser.close()
注意事项
  • 聊天页面加载需要 4-5 秒等待时间
  • 发送完消息后等待 1-2 秒再关闭页面
  • 每次只打开一个聊天页面,发送完必须关闭

示例:完整工作流程(含反爬虫处理)

场景1:批量联系供应商
bash
# 1. 启动Chrome
python chrome_launch.py

# 2. 批量联系供应商(推荐)
python batch_contact_final.py --keyword "棒球帽" --message "我要定制1000顶,多少钱?" --num 20

# 3. 查看旺旺聊天页面列表
python wangwang_chat_manager.py --list

# 4. 打开第一个旺旺聊天页查看回复
python wangwang_chat_manager.py --open 0 --history

# 5. 回复消息
python wangwang_chat_manager.py --reply "好的,请发样品"
场景2:传统流程
bash
# 1. 启动Chrome
python chrome_launch.py

# 2. 搜索第一个关键词
python search_box_v2.py --keyword "帽子" --num 5 --output hat_suppliers.json

# 3. 如果遇到滑块验证码,解决它
# (页面URL包含 _____tmd_____ 且显示滑块)
python slider_captcha.py --selector "#nc_1_n1z" --distance 260

# 4. 继续搜索其他关键词
python search_box_v2.py --keyword "外套" --num 5 --output coat_suppliers.json

# 5. 查看结果
cat hat_suppliers.json
cat coat_suppliers.json

# 6. 联系第一家供应商
python 1688_send_message.py --offer "https://detail.1688.com/offer/xxx.html" "需要帽子,请报价"

# 7. 验证发送成功
python verify_step.py --step "message_sent" --text "报价" --double

🆕 新功能1:旺旺聊天管理器

功能说明

wangwang_chat_manager.py 是一个全新的工具,用于管理旺旺聊天页面:

  1. 列出所有旺旺聊天页 - 查看当前打开的所有旺旺聊天页面
  2. 打开指定聊天页 - 切换到指定的旺旺聊天页面
  3. 搜索联系人 - 在联系人列表中搜索特定供应商
  4. 查看聊天记录 - 获取并显示聊天记录
  5. 回复消息 - 在指定聊天页面发送回复
  6. 打开最后访问的页面 - 快速回到上次访问的旺旺页
使用方法
bash
# 列出所有旺旺聊天页
python wangwang_chat_manager.py --list

# 打开第1个旺旺聊天页
python wangwang_chat_manager.py --open 0

# 搜索联系人
python wangwang_chat_manager.py --open 0 --search "供应商名称"

# 查看聊天记录
python wangwang_chat_manager.py --open 0 --history

# 回复消息
python wangwang_chat_manager.py --open 0 --reply "好的,请报价"

# 打开最后访问的旺旺页
python wangwang_chat_manager.py --last

# 打开最后访问的页并回复
python wangwang_chat_manager.py --last --reply "收到"
工作流程示例
bash
# 1. 先联系一批供应商
python batch_contact_final.py --keyword "帽子" --message "询价" --num 10

# 2. 等待一段时间后,查看有哪些供应商回复了
python wangwang_chat_manager.py --list

# 3. 打开第一个聊天页查看回复
python wangwang_chat_manager.py --open 0 --history

# 4. 如果有回复,继续沟通
python wangwang_chat_manager.py --reply "请问最低价格是多少?"

# 5. 查看其他供应商的回复
python wangwang_chat_manager.py --open 1 --history

🆕 新功能2:搜索旺旺联系人(重要)

功能说明

search_contact_fixed.py 用于搜索特定供应商并获取最新对话记录:

  1. 在搜索框输入供应商名称
  2. 按 Enter 触发搜索
  3. 点击第一个联系人
  4. 等待聊天内容加载(5秒)
  5. 获取完整对话记录
  6. 同步到本地数据库
重要步骤(已验证)
bash
# 搜索供应商并获取最新对话
python search_contact_fixed.py --name "东莞宝瑞森"

关键要点:

  • 搜索框选择器:input.ant-input (placeholder="搜索联系人")
  • 输入后按 Enter 触发搜索
  • 等待 4秒 让搜索结果加载
  • 点击联系人后等待 5秒 让聊天内容加载
  • 使用 bring_to_front() 确保页面激活
  • 截图验证每一步
工作流程
bash
# 1. 搜索并获取供应商最新回复
python search_contact_fixed.py --name "供应商名称"

# 2. 查看生成的截图验证
# step2_search_results.png - 搜索结果
# step4_chat_loaded.png - 聊天内容

# 3. 查看数据库中的记录
python supplier_manager.py get --id 27

🆕 新功能3:供应商管理系统

功能说明

supplier_manager.py 是一个本地供应商管理系统,可以:

  1. 记录供应商信息 - 名称、产品、价格、链接、联系方式等
  2. 管理沟通历史 - 记录所有发出的消息和收到的回复
  3. 标记供应商状态 - 待联系、已联系、已回复、已成交等
  4. 搜索和筛选 - 按状态、产品类型筛选供应商
  5. 导入导出 - 从搜索结果导入,导出供应商列表
数据文件

所有数据保存在 suppliers_database.json 文件中

使用方法
bash
# 从搜索结果导入供应商
python supplier_manager.py import

# 列出所有供应商
python supplier_manager.py list

# 列出已回复的供应商
python supplier_manager.py list --status 已回复

# 查看供应商详情
python supplier_manager.py get --id 1

# 添加沟通记录(发出消息)
python supplier_manager.py communicate --id 1 --message "询价内容" --direction out

# 添加沟通记录(收到回复)
python supplier_manager.py communicate --id 1 --message "供应商回复内容" --direction in

# 更新供应商状态
python supplier_manager.py update --id 1 --status 已回复

# 显示统计信息
python supplier_manager.py stats

# 导出供应商列表
python supplier_manager.py export --file my_suppliers.json
工作流程示例
bash
# 1. 搜索并联系供应商
python batch_contact_final.py --keyword "棒球帽" --message "询价" --num 20

# 2. 导入到供应商管理系统
python supplier_manager.py import

# 3. 查看所有供应商
python supplier_manager.py list

# 4. 记录沟通历史
python supplier_manager.py communicate --id 1 --message "已发送询价" --direction out

# 5. 收到回复后更新
python supplier_manager.py communicate --id 1 --message "价格5元,可以接单" --direction in
python supplier_manager.py update --id 1 --status 已回复

# 6. 查看详情
python supplier_manager.py get --id 1

# 7. 查看统计
python supplier_manager.py stats

故障排除

问题解决
Chrome启动失败检查路径是否正确,是否有其他Chrome占用9222端口
搜索无结果检查网络连接,1688是否可访问
消息发送失败检查Chrome是否已登录1688
OCR识别失败安装easyocr: pip install easyocr
滑块验证码使用 slider_captcha.py 脚本解决
页面乱码确保使用UTF-8编码输出和保存文件
搜索被拦截使用搜索框输入方式,避免URL参数搜索

注意:所有脚本使用真实浏览器操作,非模拟。执行前确保已安装依赖。

重要提醒:

  • 搜索必须通过搜索框输入
  • 输出必须使用UTF-8编码
  • 遇到滑块验证码使用 slider_captcha.py 解决
  • 真正的反爬虫页面会显示 "Sorry, we have detected unusual traffic from your network."

© LeoYeAI, 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 107 other files (scripts, references) in skills/han-jr-system of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • RESOLVED_ISSUES.md
  • STATUS_REPORT.md
  • TODAY_UPDATE.md
  • _meta.json
  • references/antibot_handling.md
  • references/api_reference.md
  • references/inquiry_template.md
  • references/popup_handling.md
  • references/soul_rules.md
  • scripts/1688_inspect.py
  • scripts/1688_send_message.py
  • scripts/1688_switch_tab.py
  • scripts/batch_contact.py
  • scripts/batch_contact_final.py
  • scripts/batch_inquire.py
  • scripts/batch_search.py
  • scripts/check_current_status.py
  • scripts/check_full_scroll.py
  • … and 89 more

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Han Jr System 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.

Han Jr System compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Han Jr System this skillLeoYeAI/openclaw-master-skills2.2k—~2.8kAutomated safety check: PassMIT
1688 Common HTML Report Generatornext-1688/1688-common-html-report-generator298—~1.2kAutomated safety check: PassNone
1688 Product Findnext-1688/1688-product-find177—~2kAutomated safety check: NotesNone
1688 Distributionnext-1688/1688-distribution101—~1.8kAutomated safety check: PassNone
1688 Product Detail Extractorbrowser-act/skills6.1k—~3.3kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0

Similar skills

  • 1688 Common HTML Report Generator

    next-1688/1688-common-html-report-generator

    将文本数据报告快速转换为交互式可视化HTML网页。使用 Python 代码驱动预置模板,只需编写数据配置即可自动生成专业数据看板。适用于市场分析报告、运营数据复盘、行业调研报告、销售数据汇总等场景。触发词:生成HTML报告、生成网页报告、转成可视化网页、做成数据看板、数据可视化、生成HTML看板。

    298 GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed
  • 1688 Product Find

    next-1688/1688-product-find

    1688智能选品找货能力。通过文字、图片或链接搜商品、找同款、找相似款,支持批量采购比价、热销选品、跨境找货、场景化选品及多条件筛选(价格/销量/材质/属性排除等)。

    177 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check: notes
  • 1688 Distribution

    next-1688/1688-distribution

    1688 分销唯一主入口。选品铺货、订单管理、知识库查询、店铺绑定,涵盖分销全链路。当用户提到铺货、选品、分销、上架、查订单、催发、旺旺、发货流程、绑店时触发。不要在用户仅询问非1688业务(如闲聊、天气、翻译等无关话题)时触发。

    101 GitHub stars~1.8k tokensUpdated 5 mo ago
    Auto-check passed
  • Extracts wholesale product data from 1688.com offer pages, including tiered prices, SKU variants, seller info, promotions and review stats, with bundled Python scripts.

    6.1k GitHub stars~3.3k tokensUpdated 1 mo ago
    Data & AnalyticsAuto-check passed
  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • PDF Processing

    anthropics/skills

    Official

    Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.

    180k GitHub starsUsed in 47 repos~2k tokens
    Documents & OfficeAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,200 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Works with

Questions about Han Jr System

What does Han Jr System do?

小翰系统:1688平台自动化供应商联系系统。使用场景:用户需要联系1688供应商、发送询价消息、收集报价时。触发于如联系1688铅笔供应商、搜索dgx spark供应商等任务。严格遵守逐家联系、验证优先、准确性优先原则。. Han Jr System is an agent skill from LeoYeAI/openclaw-master-skills.

How do I install Han Jr System in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill han-jr-system -a claude-code`. Or copy the skill folder (skills/han-jr-system in LeoYeAI/openclaw-master-skills) into .claude/skills/han-jr-system in your project. Claude Code loads it when a task matches its description.

How do I install Han Jr System in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill han-jr-system -a codex`. Or copy the skill folder (skills/han-jr-system in LeoYeAI/openclaw-master-skills) into .agents/skills/han-jr-system in your project. Codex loads it when a task matches its description.

Can I use Han Jr System 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 LeoYeAI/openclaw-master-skills --skill han-jr-system -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/han-jr-system, .gemini/skills/han-jr-system, .github/skills/han-jr-system and .opencode/skills/han-jr-system in your project.

What does Han Jr System need to run?

Going by SKILL.md and its folder, Han Jr System needs Python for the scripts in its folder and the command-line tools its instructions call (python, pip and playwright). Our summary lists: Python 3.

Does Han Jr System access the network?

SKILL.md names 2 domains. In commands or code: air.1688.com and detail.1688.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Han Jr System 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 Han Jr System use?

Han Jr System 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 Han Jr System use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.

What are the alternatives to Han Jr System?

Skills that share tags, products or a category with Han Jr System: 1688 Common HTML Report Generator (next-1688/1688-common-html-report-generator, 298 stars), 1688 Product Find (next-1688/1688-product-find, 177 stars), 1688 Distribution (next-1688/1688-distribution, 101 stars) and 1688 Product Detail Extractor (browser-act/skills, 6.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Han Jr System?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.