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
- career-ops-hq/career-opstheir own version, first seen Nov 10, 2026
- Leostruka/devin-bundletheir own version, first seen Nov 1, 2026
- limuchuan0619/ai-job-search-chinatheir own version, first seen Oct 20, 2026
- Shri-Phnx/claude-skillstheir own version, first seen Oct 13, 2026
- santifer/career-opstheir own version, first seen Oct 8, 2026
- okashiina/career-ops-idtheir own version, first seen Sep 28, 2026
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 6
- Youssifai/internship-finder★ 914% same
- skytiger6724/qwen-skills★ 226% same
- jpoindexter/theft-kit★ 123% same
- wranngle/career_architect★ 119% same
- gilliancai/career-explorer★ 021% same
- HarshaMogulla/career-ops★ 023% same
Wrote their own version · 9
- santifer/career-ops★ 83ksame name
- career-ops-hq/career-ops★ 83ksame name
- karthikrshet/Career-Agents★ 67same name
- poferraz/career-ops★ 7same name
- Shri-Phnx/claude-skills★ 2same name
- limuchuan0619/ai-job-search-china★ 1same name
- ankit-songara/career-autopilot★ 0same name
- Leostruka/devin-bundle★ 0same name
- okashiina/career-ops-id★ 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.
In this repositoryOne other file it gives its agents.
- CLAUDE.mdCLAUDE.md
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
- Common: line 84
After determining the mode, load the necessary files before executing:
“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.
Files
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 |
offer | offer(单岗位评估 A-F) |
offers | offers(多 offer 对比) |
contact | contact(脉脉/微信/LinkedIn 触达) |
deep | deep(公司调研 prompt) |
pdf | pdf(生成定制 PDF) |
training | training(评估课程/证书) |
project | project(评估 portfolio 项目) |
tracker | tracker(查看申请状态) |
pipeline | pipeline(处理待办 URL inbox) |
apply | apply(实时表单填写助手) |
scan | scan(线索发现,仅 URL+标题,不取 JD) |
radar | radar(管理远程"求职线索雷达"定期 routine — 创建/查看/立即跑/改节奏) |
inbox | inbox(处理 bookmarklet 捕获的 JD 文件,自动评估) |
story-sync | story-sync(扫 reports/* 抽取 Block F,累积到 story-bank.md) |
evolve / evolve init / evolve dig / evolve status | evolve(简历进化:深挖问卷 → 事实账本 → cv.md 版本 + 传导) |
batch | batch(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.
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
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.

