npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@cjsqbn/resume-screening-mcp

v0.3.5

Published

Evidence-verified deterministic resume screening, hard-gate evaluation, timeline calculation, scoring, ranking and audit MCP server.

Downloads

1,400

Readme

Resume Screening MCP 0.3.5

这是 RTS 简历初筛项目的轻量规则引擎。大模型负责理解 JD 和简历并提交结构化事实;MCP 负责验证原文证据、计算不重复工作年限、执行硬性门槛、确定性评分、候选人分层排序和审计记录。

0.3.5 将嵌套证据字段改为可选但不使用 JSON Schema default。缺少 quote 时不再拒绝整批请求,而是由规则引擎将相关证据降为未验证,并记录 warnings/audit。保留平台兼容的简单 schema 和评分上限修复。

为什么使用 MCP

  • 同一输入得到同一分数和排名。
  • 模型提交的 E1-E3 证据必须能在简历原文中找到,否则自动降为 E0。
  • 重叠经历不会重复累计工作年限。
  • 年限、学历、地点、必备技能和证书按统一规则执行。
  • 每次加减分都保留规则和原因,便于复核。

MCP 不负责解析 PDF/Word,也不调用外部大模型,不需要 API Key。

工具

| 工具 | 用途 | |---|---| | health_check | 检查版本、传输方式和服务状态 | | screen_resumes | 单次处理一份或多份简历,完成证据校验、时间线、门槛、评分、分层、排序和审计 |

评分口径

  • 匹配度基础权重:硬门槛 25、核心技能 35、职责/项目 25、行业/优先项 10、表达与证据清晰度 5。
  • JD 未提供的分项不计分,其余有效分项自动重新归一化。
  • E3=100,E2=70,E1=30,E0=0。
  • 综合分:匹配度 70% + 证据完整度 30%。
  • 硬性门槛失败或证据完整度低于 60 的候选人不进入推荐榜。

npm 配置

{
  "mcpServers": {
    "resume-screening-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@cjsqbn/[email protected]"
      ],
      "env": {}
    }
  }
}

不要在包名中的 @ 前添加反斜杠。

本地验证

npm.cmd install --cache "D:\npm-cache"
npm.cmd run test:smoke
npm.cmd pack --dry-run --cache "D:\npm-cache"

性能设计

  • 正式分析只调用一次 screen_resumes。
  • 不生成重复 Markdown 报告。
  • 不返回完整简历原文。
  • 不访问外部 API。
  • 支持单次批量排序。