agentleFS
shuheng-moshuheng-mo/career-ops-china/.claude/skills/career-ops/SKILL.md

career-ops

Skill114 starsChanged 21 days agoMITView on GitHub

中国大陆 AI 求职指挥中心 — 评估岗位、生成定制简历、扫描门户、追踪申请

15 other projects use a version of this, 6 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 1 is common, 0 are distinctive, and 0 are very specific to this project.

  • 1

    Common

    Most of the 14 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Common:

    After determining the mode, load the necessary files before executing:

    line 84

“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

career-ops — Router(中国大陆版)

Mode Routing

根据 {{mode}} 决定模式:

输入Mode
(空 / 无参数)discovery — 显示命令菜单
JD 截图(图片附件)auto-pipeline(推荐主路径,国内 Boss/Mokahr 等反爬平台必用)
JD 文本(粘贴)auto-pipeline
岗位 URL(无子命令)auto-pipeline — 但国内 URL 90% 抓不到 JD,会让用户截图
offeroffer(单岗位评估 A-F)
offersoffers(多 offer 对比)
contactcontact(脉脉/微信/LinkedIn 触达)
deepdeep(公司调研 prompt)
pdfpdf(生成定制 PDF)
trainingtraining(评估课程/证书)
projectproject(评估 portfolio 项目)
trackertracker(查看申请状态)
pipelinepipeline(处理待办 URL inbox)
applyapply(实时表单填写助手)
scanscan(线索发现,仅 URL+标题,不取 JD)
radarradar(管理远程"求职线索雷达"定期 routine — 创建/查看/立即跑/改节奏)
inboxinbox(处理 bookmarklet 捕获的 JD 文件,自动评估)
story-syncstory-sync(扫 reports/* 抽取 Block F,累积到 story-bank.md)
evolve / evolve init / evolve dig / evolve statusevolve(简历进化:深挖问卷 → 事实账本 → cv.md 版本 + 传导)
batchbatch(批量处理)

Auto-pipeline 检测: 如果 {{mode}} 不是已知子命令但包含:

  • JD 文本(出现关键词:"岗位职责"、"任职要求"、"工作描述"、"responsibilities"、"requirements"、公司名 + 岗位名)
  • 图片附件(截图)
  • 岗位 URL

→ 执行 auto-pipeline。

如果 {{mode}} 既不是子命令也不像 JD,显示 discovery。

🇨🇳 中国大陆使用规则:

如果用户给的是国内招聘门户 URL(zhipin.com / liepin.com / lagou.com / mokahr.com / feishu.cn 等),先尝试 WebFetch 一次,失败就立刻停止自动化尝试,让用户截图给你。不要在反爬上反复挣扎。

LinkedIn 例外: linkedin.com/jobs/view/… 链接不用截图,直接跑 npm run linkedin -- <链接>(走 LinkedIn 免登录接口,JD 存进 inbox/),再按 inbox 流程评估。搜索页链接(/jobs/search?…,常带 trk=missing_jd_redirect)说明原岗位已下线,没有 ID 可取。


Discovery Mode(无参数时)

输出下面这段紧凑 cheatsheet(不要展开成长版菜单;输入框上方已有 argument-hint,正文不需重复列子命令的全部说明):

career-ops — 中国大陆求职指挥中心

🎯 主路径:JD 截图 / 粘贴文本 / 公司+岗位 URL → 直接发给我 → 自动评估 + report + PDF + tracker

⚡ 子命令(/career-ops <name>):
  线索 & 批处理   scan       radar      inbox       pipeline    batch
  单岗位          offer      offers     pdf         contact     deep        apply
  追踪 & 沉淀     tracker    story-sync  evolve
  ROI 评估        training   project

🛰️ radar:每 2 天云端自动扫上海/杭州 AI应用·Agent 新岗,出线索清单(/career-ops radar 管理)

⚠️ 国内 URL(Boss/拉勾/猎聘/Mokahr/飞书)90% 抓不到 JD → 截图最快
🐧 腾讯招聘搜索页整页拉:npm run tencent -- "<search.html 链接>" --days 30 --fetch
🦘 美团招聘按关键词拉:npm run meituan -- agent --city 上海,深圳 --days 21 --fetch
🔗 LinkedIn 链接 / 搜岗:npm run linkedin -- <链接>  ·  npm run linkedin -- search "关键词" --city 上海 --days 7
🔖 bookmarklet:tools/README.md(一次安装,之后任意 JD 页一键 → inbox)

不确定哪个?直接发 JD 给我(auto-pipeline 默认),或问"<name> 怎么用"。

Context Loading by Mode

After determining the mode, load the necessary files before executing:

Modes that require _shared.md + their mode file:

Read modes/_shared.md + modes/{mode}.md

Applies to: auto-pipeline, offer, offers, pdf, contact, apply, pipeline, scan, inbox, batch

Standalone modes (only their mode file):

Read modes/{mode}.md

Applies to: tracker, deep, training, project, story-sync, radar, evolve

Modes delegated to subagent:

For scan, apply (with Playwright), and pipeline (3+ URLs): launch as Agent with the content of _shared.md + modes/{mode}.md injected into the subagent prompt.

Agent(
  subagent_type="general-purpose",
  prompt="[content of modes/_shared.md]\n\n[content of modes/{mode}.md]\n\n[invocation-specific data]",
  description="career-ops {mode}"
)

Execute the instructions from the loaded mode file.

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.