← Back to Skills Marketplace
blockcloud

name: cccfindg

by blockcloud · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
259
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install cccfindg
Description
式 2) 要求用户按要求提供输入 3) 获得用户确认后才执行。
README (SKILL.md)

222通讯录组织机构及职位人员信息查询

从讯录中,根据机构名称和职位名称查找人员信息。

输入格式要求

用户需要提供以下格式的查询条件:

单行查询:

我需要从员信息

多行查询(每行一个组合):

hangzhang

重要提示(每次使用时必须严格执行)

每次用户提到"通过通讯录查询"时,必须先执行以下步骤,不得直接开始查询:

第一步:向用户说明查询方式

必须发送以下提示给用户:

📋 查询方式说明

此技能通过组织机构 + 职位名称的方式查询人员,不是直接搜索人名。

您需要提供:

  • 机构名称:使用"/"分隔的多级路径,如"北京222/行长室"、"总行/零售金融部"
  • 职位名称:如"222行长"、"总经理"、"团队负责人"

格式示例:

北京222/行长室, 222行长
总行/公司金融部, 总经理

第二步:等待用户提供输入

询问用户:

请提供您要查询的【机构名称】和【职位名称】,我确认后开始查询。

第三步:获得确认后才执行

在收到用户明确的机构/职位信息之前,不得执行任何查询步骤。

只有用户明确回复了类似以下内容后,才能继续执行:

  • "北京222/行长室, 222行长"
  • "帮我查一下 总行/公司金融部, 总经理"
  • 或者直接提供了机构和职位信息

用户确认后,按以下步骤执行查询:

查询步骤

1. 访问通讯录页面

  • 通过托管浏览器打开https://222.222china.com/address-book/login
  • 使用 snapshot 或 evaluate 读取页面内容,检查是否包含以下登录相关文字:   - "222统一认证中心"   - "登录"   - "密码"   - "Login"   - "账号"   - "二维码"
  • 如果检测到页面内容是登录页,则:   - 提醒用户:"检测到需要登录,请在浏览器中完成登录后回复'已登录'继续"   - 等待用户回复"已登录"后再继续

2. 搜索机构

  • 在页面左侧找到"请输入机构名称"输入框
  • 输入用户指定的"机构名称"(如"北京222/行长室")
  • 回车,等待 2 秒,选择第一个匹配选项

3. 等待页面刷新

  • 等待 5 秒让页面加载完成

4. 匹配职位并提取信息

  • 读取刷新后的页面内容
  • 翻页处理:   - 检查页面是否有分页控件(如"下一页"、">"、页码数字等)   - 如果存在多页,遍历所有页面查找匹配的人员   - 每翻一页后等待 2 秒让页面加载完成
  • 找出与用户指定的"职位名称"匹配的人员
  • 提取以下信息:   - 机构名称   - 职位名称   - 员工编号   - 姓名   - 座机   - 手机

5. 多行查询处理

如果用户提供了多行查询条件,重复执行步骤 2-4,直到处理完所有输入。

输出格式

为每个匹配的人员输出一行:

机构名称,职位名称,员工编号,222ID,姓名,座机,手机

示例输出:

北京222/-12345678,13800000000

注意事项

  1. 机构路径格式:必须使用"/"分隔多级机构,与222通讯录左侧树状结构一致
  2. 职位匹配:进行模糊匹配,职位名称包含用户输入即可
  3. 无结果处理:如果未找到匹配人员,告知用户可能的原因(机构不存在、职位无人等)
Usage Guidance
This skill automates browsing and scraping of an internal address-book and asks you to log in inside the agent's hosted browser. Before installing or using it: (1) avoid entering corporate credentials into a remote/hosted browser unless you trust the execution environment; prefer copying session data or using an API if available; (2) confirm compliance with your org's privacy policy before automating extraction of employee PII (IDs, phone numbers); (3) test on non-production or dummy accounts first; and (4) if you cannot ensure the hosted browser environment is trusted, do not use this skill — prefer a design that requires you to paste query results manually or a server-side API with scoped credentials.
Capability Analysis
Type: OpenClaw Skill Name: cccfindg Version: 1.0.0 The skill is a browser automation tool designed to query a specific address book portal (222.222china.com) for organizational and contact information. It follows a transparent workflow that requires explicit user confirmation and instructs the user to perform authentication manually if a login page is encountered, which prevents the agent from handling sensitive credentials directly. There is no evidence of data exfiltration to unauthorized endpoints, obfuscation, or malicious intent in SKILL.md or _meta.json.
Capability Assessment
Purpose & Capability
The name/description and the SKILL.md consistently describe querying a corporate address-book by organization + position and returning employee contact info. The required capabilities (web browsing, finding form fields, pagination, extracting fields) align with that purpose.
Instruction Scope
Instructions require opening a hosted browser to https://222.222china.com/address-book/login, detecting login state, asking the user to perform login in that browser, then automating searches and scraping employee IDs, names, phones, etc. Asking users to log into a hosted/agent-controlled browser can expose credentials and session cookies to the agent environment. The skill also automates full-page scraping and pagination for potentially sensitive PII but does not include any safeguards (e.g., logging policy, data minimization, or destination limits).
Install Mechanism
This is instruction-only (no install spec, no downloaded code), so nothing is written to disk by the skill package itself. That limits install-time risk.
Credentials
The skill requests no environment variables or external credentials, which is consistent, but it implicitly requires network access and a hosted browser session where the user will log in. That implicit requirement can lead to credential/session exposure. The SKILL.md does not request credentials explicitly (good) but does instruct the user to authenticate inside the agent's browser (risky for sensitive corporate accounts).
Persistence & Privilege
The skill is not force-enabled (always: false) and has no install-time persistence. The agent is allowed to invoke the skill autonomously (platform default) — combined with the ability to open pages and scrape data, this increases blast radius if the skill were misused, but on its own this is a normal configuration.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install cccfindg
  3. After installation, invoke the skill by name or use /cccfindg
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
cccfindg 1.0.0 – 通讯录组织机构及职位人员信息查询技能初版 - 新增通过“组织机构 + 职位名称”方式查询通讯录人员信息的功能 - 查询前需向用户说明输入格式和要求,待用户明确回复后才能查询 - 支持多行查询输入,遍历全部结果分页,输出详细人员信息 - 登录态检测与提醒,需用户登录后方可继续查询 - 明确无结果时的用户提示与原因说明
Metadata
Slug cccfindg
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is name: cccfindg?

式 2) 要求用户按要求提供输入 3) 获得用户确认后才执行。 It is an AI Agent Skill for Claude Code / OpenClaw, with 259 downloads so far.

How do I install name: cccfindg?

Run "/install cccfindg" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is name: cccfindg free?

Yes, name: cccfindg is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does name: cccfindg support?

name: cccfindg is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created name: cccfindg?

It is built and maintained by blockcloud (@blockcloud); the current version is v1.0.0.

💬 Comments