← Back to Skills Marketplace
xllinbupt

Liepin Jobs

by xllinbupt · GitHub ↗ · v0.2.0 · MIT-0
cross-platform ⚠ suspicious
296
Downloads
1
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install liepin-jobs
Description
猎聘求职工具 — 在猎聘上搜索职位、投递简历、查看/编辑简历。 触发词: 找工作, 搜职位, 投简历, 猎聘, liepin, 求职, 招聘, 简历
README (SKILL.md)

猎聘求职工具 (liepin-jobs)

在猎聘平台上搜索职位、投递简历、查看和编辑简历。基于猎聘官方 MCP Server,零外部依赖。

脚本位置: 本 skill 目录下的 liepin_mcp.py


!! 首次使用必读:获取凭证

使用此工具前,用户必须先获取猎聘的用户凭证。没有凭证无法使用任何功能。

获取步骤

  1. 打开猎聘 MCP 配置页: 引导用户在浏览器访问 https://www.liepin.com/mcp/server
  2. 登录猎聘账号: 用户需要有猎聘账号并登录
  3. 获取 User Token:
    • User Token: 格式为 liepin_user_token_xxxx(页面上的 x-user-token 值)
  4. 配置 Token: 运行 setup 命令保存 token
python3 "\x3Cskill_dir>/liepin_mcp.py" setup
# 按提示输入 user token

或通过环境变量配置

export LIEPIN_USER_TOKEN="liepin_user_token_xxxx"

Token 过期

  • 凭证有效期 90 天
  • 过期后会收到认证错误,需引导用户重新访问上述页面获取新 Token
  • 重新生成 Token 会立即使旧 Token 失效

如果用户还没有配置 Token,必须先引导他们完成上述步骤,再执行任何操作。


命令速查

SCRIPT="\x3Cskill_dir>/liepin_mcp.py"

# 搜索职位
python3 "$SCRIPT" search-job --jobName "AI产品经理" --address "上海"
python3 "$SCRIPT" search-job --jobName "前端开发" --address "北京" --salary "30-50k"
python3 "$SCRIPT" search-job --jobName "数据分析" --companyName "字节跳动" --json

# 投递职位(需要先搜索获取 jobId 和 jobKind)
python3 "$SCRIPT" apply-job --jobId "JOB_ID" --jobKind "JOB_KIND"

# 查看简历
python3 "$SCRIPT" my-resume
python3 "$SCRIPT" my-resume --json

# 更新简历
python3 "$SCRIPT" update-resume --module basic --data '{"name": "张三", "phone": "138xxx"}'
python3 "$SCRIPT" update-resume --module experience --data '{"company": "xxx", "title": "产品经理"}'
python3 "$SCRIPT" update-resume --module expectations --data '{"salary": "30-50k", "city": "上海"}'
python3 "$SCRIPT" update-resume --module self-assessment --data '{"content": "5年产品经验..."}'

# 列出所有可用工具(查看猎聘最新 API 能力)
python3 "$SCRIPT" list-tools
python3 "$SCRIPT" list-tools --json

# 通用调用(适用于猎聘新增的工具)
python3 "$SCRIPT" call \x3Ctool-name> -a '{"key": "value"}' --json

典型求职流程

当用户说"帮我找工作"、"搜一下猎聘上的XX职位"时,按以下流程执行:

  1. 检查 Token → 如果未配置,先引导用户获取(见上方"首次使用必读")
  2. 查看简历 (my-resume) → 确认简历信息完整,提醒用户补充缺失项
  3. 搜索职位 (search-job) → 根据用户意向搜索,用表格展示结果
  4. 分析匹配度 → 结合简历和职位要求,帮用户筛选最合适的
  5. 投递职位 (apply-job) → 必须先向用户展示职位详情并获得明确确认后再投递

搜索参数

参数 说明 示例
--jobName 职位名称关键词 "AI产品经理"、"前端开发"、"数据分析师"
--address 工作地点 "上海"、"北京"、"深圳"、"杭州"
--salary 薪资范围 "20-30k"、"30-50k"
--education 学历要求 本科、硕士
--experience 工作经验 "3-5年"、"5-10年"
--companyType 公司类型 外企、国企、民企
--companyName 公司名称 "字节跳动"、"阿里巴巴"、"腾讯"

简历模块

模块 说明
basic 基本信息(姓名、手机、邮箱等)
experience 工作/项目经历
expectations 求职期望(期望薪资、城市、岗位等)
self-assessment 自我评价

输出格式

  • 默认输出人类可读格式
  • --json 输出原始 JSON,方便程序化处理
  • 搜索结果建议以表格形式展示给用户,包含:职位名、公司、薪资、地点、经验要求

注意事项

  • 投递不可撤回: 执行 apply-job 前必须获得用户明确确认
  • 频率限制: 所有操作共享 60 次/分钟,避免短时间批量调用
  • Token 安全: 不要在日志或对话中暴露完整的 Token 内容
  • 数据来源: 所有数据来自猎聘平台,实时获取

错误处理

错误 原因 解决方案
"未配置 LIEPIN_USER_TOKEN" 没有运行 setup 引导用户获取 Token 并运行 setup
HTTP 401 Token 过期或无效 引导用户重新访问配置页获取新 Token
HTTP 429 频率限制 等待 1 分钟后重试
网络超时 网络问题 重试一次
Usage Guidance
This skill appears to be what it says: a CLI wrapper that calls Liepin's MCP server. However, the registry metadata does not declare the required LIEPIN_USER_TOKEN even though both SKILL.md and the script require it. Before installing: (1) confirm you trust the skill's source (check the GitHub repo and commit history); (2) understand the token is an account credential that will be stored under ~/.config/liepin-mcp/config.json and will be sent to the configured MCP URL (default: https://open-agent.liepin.com/mcp/user); (3) prefer setting LIEPIN_USER_TOKEN as an environment variable if you don't want it saved to disk, or rotate the token after use; (4) verify the MCP endpoint URL if you are concerned about a redirected/malicious server; and (5) if you need higher assurance, review the liepin_mcp.py source line-by-line or run it in an isolated environment before providing your real token.
Capability Analysis
Type: OpenClaw Skill Name: liepin-jobs Version: 0.2.0 This skill is a legitimate integration for the Liepin job recruitment platform, implementing a Model Context Protocol (MCP) client in `liepin_mcp.py`. It allows searching jobs, viewing/updating resumes, and applying for positions via the endpoint `open-agent.liepin.com`. The `SKILL.md` includes proactive safety instructions for the AI agent, such as requiring explicit user confirmation before job applications and maintaining token privacy. No malicious logic, unauthorized data exfiltration, or obfuscation was detected.
Capability Assessment
Purpose & Capability
Name/description (search, resume, apply on Liepin) matches the included code: a Python CLI that talks to an MCP endpoint and implements search/apply/resume actions. However, the registry metadata declares no required environment variables or primary credential while both SKILL.md and the code require a LIEPIN_USER_TOKEN to function.
Instruction Scope
Runtime instructions focus on obtaining a Liepin user token, running the provided Python script, and following a workflow that checks resume, searches jobs, and requires explicit confirmation before apply. The instructions do not ask the agent to read unrelated system files or exfiltrate data beyond sending the token to the configured MCP URL. The skill will read/write a config file under the user's home (~/.config/liepin-mcp/config.json) to store the token.
Install Mechanism
No install spec — instruction-only with a single Python script. Required binary is python3 only (declared). No downloads from arbitrary URLs or archive extraction are performed by the skill itself.
Credentials
The tool requires a LIEPIN_USER_TOKEN (described in SKILL.md and used by the code) but registry metadata lists no required env vars or primary credential. This mismatch is a notable omission: the skill needs a secret (user token) which will be sent to the configured MCP endpoint. Users should expect that this token gives account-level access on Liepin and will be stored on-disk in the user's config directory.
Persistence & Privilege
The skill does persist user configuration to ~/.config/liepin-mcp/config.json (its own config path) but does not request 'always' inclusion or modify other skills or system-wide agent settings. Autonomous invocation is allowed (platform default) which increases blast radius only if combined with other red flags; here the main persistence is the local config file.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install liepin-jobs
  3. After installation, invoke the skill by name or use /liepin-jobs
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.2.0
Update for the new Liepin MCP endpoint and single-token auth.
v1.0.0
liepin-jobs 1.0.0 - Initial release of 猎聘求职工具. - Enables searching for jobs, submitting resumes, and viewing/editing resumes on 猎聘. - Trigger words include: 找工作, 搜职位, 投简历, 猎聘, liepin, 求职, 招聘, 简历.
Metadata
Slug liepin-jobs
Version 0.2.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is Liepin Jobs?

猎聘求职工具 — 在猎聘上搜索职位、投递简历、查看/编辑简历。 触发词: 找工作, 搜职位, 投简历, 猎聘, liepin, 求职, 招聘, 简历. It is an AI Agent Skill for Claude Code / OpenClaw, with 296 downloads so far.

How do I install Liepin Jobs?

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

Is Liepin Jobs free?

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

Which platforms does Liepin Jobs support?

Liepin Jobs is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Liepin Jobs?

It is built and maintained by xllinbupt (@xllinbupt); the current version is v0.2.0.

💬 Comments