agentleFS
sangowusangowu/job-matcher-skill/SKILL.md

job-matcher

Skill18 starsChanged 51 days agoMITView on GitHub

根据用户简历(CV)和求职意向,抽取CV结构化字段、实时检索匹配职位、生成可交互HTML报告。当用户提供简历文件(pdf/docx/txt/md)或粘贴简历文本,并希望找工作、匹配职位、获取职位推荐、做求职匹配时使用。

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. fred-brown-3/job-hunter-ai★ 0same name
    2. ShayanxBG/Job-Discovery-Engine★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

Files
SKILL.md

Job Matcher

把简历(CV) + 求职意向 变成一份匹配职位的可交互 HTML 报告。

执行方式:先读 WORKFLOW.md,按它的 0–7 步流程做。 WORKFLOW.md 是 agent-中立的单一事实源,包含:所需能力、如何映射到你当前运行时的工具、脚本调用契约、缺能力时的降级策略。本文件兼容 Claude Code 与 Codex 的 skill 机制(同样的 name/description + scripts/、references/、assets/ 结构)。

能力映射(本文件唯一的职责)

WORKFLOW.md 是 agent-中立的,它说「用你的 web 搜索工具」。下表把那些能力换成本运行时的具体工具;流程规则不在这里,全在 WORKFLOW.md,两处都写会漂。

能力必需性各 agent 对应缺失时
模型/Web 搜索可选发现路径Claude: WebSearch;Codex: 内置 web 搜索降级到已就绪的本机浏览器;两者都缺失则无法实时检索
子代理(并行+隔离)可选Claude: Task/Agent(单消息内并行 spawn);Codex: custom agents降级为串行
网页抓取可选Claude: WebFetch回退 scripts/fetch_rendered.py
本机浏览器发现可选发现路径当前运行时已连接、已授权且具备 tabs/navigate/read 的 BrowserOS Neo 或用户浏览器工具继续模型/Web 搜索;绝不读取 Cookie 文件

Claude Code 特有的两点:

  • 子代理并行:Task/Agent 支持在同一条消息里同时 spawn 多个 worker,WORKFLOW 的「批间重叠」和并行搜索/评估都靠这个;没有它就按 WORKFLOW 的降级列串行做。
  • 本机浏览器:只使用当前会话已暴露、已授权的浏览器工具(BrowserOS Neo 或用户浏览器),按 WORKFLOW 第 0 步用 scripts/local_browser_probe.py probe 确认状态。不扫描端口、浏览器配置、Cookie 或既有标签页;已安装不等于 ready。

其余

流程、脚本契约、容错阶梯、护栏、配置、降级 —— 全部见 WORKFLOW.md(规则的理由在 docs/rationale.md)。指令文档在 references/。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.