santifer / career-ops

查看原文 / View Original 编辑 / Edit

santifer / career-ops

I spent months applying to jobs the hard way. So I engineered the system I wish I had. Companies use AI to filter candidates. I just gave candidates AI to choose companies. Now it’s open source. 我曾花费数月时间，以最笨拙的方式投递简历。因此，我设计了这套我梦寐以求的系统。企业利用 AI 来筛选候选人，而我则为候选人提供了利用 AI 来筛选企业的工具。现在，它已开源。

亮点数据

740+ job listings evaluated · 100+ personalized CVs · 1 dream role landed 评估了 740+ 个职位列表 · 生成了 100+ 份个性化简历 · 成功斩获 1 个理想职位

Built with

构建技术

What Is This Career-Ops (career-ops.org, also known as careerops) turns any AI coding CLI into a full job search command center. Instead of manually tracking applications in a spreadsheet, you get an AI-powered pipeline that: 什么是 Career-Ops？ Career-Ops (career-ops.org，也称为 careerops) 能将任何 AI 编程命令行界面 (CLI) 转化为全功能的求职指挥中心。你无需再在电子表格中手动追踪申请进度，而是获得了一个由 AI 驱动的流程，它可以：

  • Evaluates offers with a structured A-F scoring system (10 weighted dimensions) 通过结构化的 A-F 评分系统（10 个加权维度）评估职位。
  • Generates tailored PDFs — ATS-optimized CVs customized per job description 生成定制化 PDF —— 根据职位描述优化的 ATS（申请人追踪系统）友好型简历。
  • Scans portals automatically (Greenhouse, Ashby, Lever, company pages) 自动扫描招聘门户网站（Greenhouse、Ashby、Lever 及公司官网）。
  • Processes in batch — evaluate 10+ offers in parallel with sub-agents 批量处理 —— 利用子代理并行评估 10+ 个职位。
  • Tracks everything in a single source of truth with integrity checks 通过单一事实来源追踪所有进度，并进行完整性检查。

Important: This is NOT a spray-and-pray tool. Career-ops is a filter — it helps you find the few offers worth your time out of hundreds. The system strongly recommends against applying to anything scoring below 4.0/5. Your time is valuable, and so is the recruiter’s. Always review before submitting. 重要提示：这不是一款“广撒网”工具。Career-ops 是一个过滤器，旨在帮助你从数百个职位中筛选出真正值得投入时间的少数几个。系统强烈建议不要申请评分低于 4.0/5 的职位。你的时间很宝贵，招聘人员的时间也是。提交前请务必进行审核。

Career-ops is agentic: Claude Code navigates career pages with Playwright, evaluates fit by reasoning about your CV vs the job description (not keyword matching), and adapts your resume per listing. Career-ops 具有代理特性：Claude Code 使用 Playwright 浏览招聘页面，通过分析你的简历与职位描述的匹配度（而非简单的关键词匹配）来评估契合度，并针对每个职位调整你的简历。

Heads up: the first evaluations won’t be great. The system doesn’t know you yet. Feed it context — your CV, your career story, your proof points, your preferences, what you’re good at, what you want to avoid. The more you nurture it, the better it gets. Think of it as onboarding a new recruiter: the first week they need to learn about you, then they become invaluable. 注意：初期的评估效果可能不会太理想，因为系统还不了解你。请为其提供背景信息——包括你的简历、职业经历、证明材料、偏好、擅长领域以及想要规避的内容。你对它投入的调教越多，它的表现就越好。可以把它想象成入职一名新招聘专员：第一周他们需要了解你，之后他们将变得不可或缺。

Built by someone who used it to evaluate 740+ job offers, generate 100+ tailored CVs, and land a Head of Applied AI role. Read the full case study. 该工具由一位成功人士开发，他利用该系统评估了 740+ 个职位，生成了 100+ 份定制简历，并最终成功入职“应用 AI 主管”岗位。阅读完整案例研究。

Features

功能特性

FeatureDescription
Auto-PipelinePaste a URL, get a full evaluation + PDF + tracker entry
自动流程粘贴 URL，即可获得完整评估 + PDF + 追踪记录
6-Block EvaluationRole summary, CV match, level strategy, comp research, personalization, interview prep (STAR+R)
六大模块评估职位摘要、简历匹配度、职级策略、薪酬调研、个性化定制、面试准备 (STAR+R)
Interview Story BankAccumulates STAR+Reflection stories across evaluations — 5-10 master stories that answer any behavioral question
面试故事库在评估过程中积累 STAR+反思故事 —— 5-10 个核心故事，足以应对任何行为面试题
Negotiation ScriptsSalary negotiation frameworks, geographic discount pushback, competing offer leverage
谈判脚本薪资谈判框架、应对地理位置薪资折扣、利用竞品 Offer 增加筹码
ATS PDF GenerationKeyword-injected CVs with Space Grotesk + DM Sans design
ATS PDF 生成注入关键词的简历，采用 Space Grotesk + DM Sans 设计
Portal Scanner45+ companies pre-configured (Anthropic, OpenAI, ElevenLabs, Retool, n8n…) + custom queries across Ashby, Greenhouse, Lever, Wellfound
门户扫描器预配置 45+ 家公司 (Anthropic, OpenAI, ElevenLabs, Retool, n8n…) + 支持 Ashby, Greenhouse, Lever, Wellfound 的自定义查询
Batch ProcessingParallel evaluation with claude -p workers
批量处理使用 claude -p 工作进程进行并行评估
Dashboard TUITerminal UI to browse, filter, and sort your pipeline
仪表盘 TUI用于浏览、筛选和排序申请流程的终端界面
Human-in-the-LoopAI evaluates and recommends, you decide and act. The system never submits an application — you always have the final call
人机协作AI 负责评估和推荐，你负责决策和行动。系统绝不会自动提交申请 —— 最终决定权永远在你手中
Pipeline IntegrityAutomated merge, dedup, status normalization, health checks
流程完整性自动合并、去重、状态标准化及健康检查

Quick Start

快速开始

  1. Clone and install 克隆并安装

    git clone https://github.com/santifer/career-ops.git
cd career-ops && npm install
npx playwright install chromium # Required for PDF generation

  2. Check setup 检查设置

    npm run doctor # Validates all prerequisites

  3. Configure 配置

    cp config/profile.example.yml config/profile.yml # Edit with your details
cp templates/portals.example.yml portals.yml # Customize companies

  4. Add your CV 添加简历 Create cv.md in the project root with your CV in markdown. 在项目根目录下创建一个包含你 Markdown 格式简历的 cv.md 文件。

  5. Personalize with Claude 使用 Claude 个性化定制

    claude # Open Claude Code in this directory

    Then ask Claude to adapt the system to you: 然后让 Claude 根据你的需求调整系统：

    • “Change the archetypes to backend engineering roles” “将原型修改为后端工程岗位”
    • “Translate the modes to English” “将模式翻译为英语”
    • “Add these 5 companies to portals.yml” “将这 5 家公司添加到 portals.yml”
    • “Update my profile with this CV I’m pasting” “用我粘贴的这份简历更新我的个人资料”

  6. Start using 开始使用 Paste a job URL or run /career-ops 粘贴职位 URL 或运行 /career-ops

The system is designed to be customized by Claude itself. Modes, archetypes, scoring weights, negotiation scripts — just ask Claude to change them. It reads the same files it uses, so it knows exactly what to edit. See docs/SETUP.md for the full setup guide. 该系统旨在由 Claude 自行定制。无论是模式、原型、评分权重还是谈判脚本，只需让 Claude 修改即可。它读取的是自身使用的文件，因此非常清楚该修改哪里。查看 docs/SETUP.md 获取完整设置指南。

Gemini CLI Integration

Gemini CLI 集成

Career-ops supports Gemini CLI natively, the same way it supports Claude Code and OpenCode. All 15 slash commands are available, using the same modes/*.md evaluation logic. Career-ops 原生支持 Gemini CLI，方式与支持 Claude Code 和 OpenCode 相同。所有 15 个斜杠命令均可用，并使用相同的 modes/*.md 评估逻辑。

Option A: Native Gemini CLI (Recommended) 选项 A：原生 Gemini CLI（推荐）

# 1. Install Gemini CLI
npm install -g @google/gemini-cli
# 2. Authenticate (free, uses your Google account)
gemini auth
# 3. Run in the career-ops directory
cd career-ops
gemini
# 4. Use slash commands just like Claude Code
/career-ops "Senior AI Engineer at Anthropic..."
/career-ops-evaluate --file ./jds/openai.txt
/career-ops-scan
/career-ops-pdf
/career-ops-tracker

The GEMINI.md file is auto-loaded as context. All 15 commands are defined in .gemini/commands/*.toml. GEMINI.md 文件会自动作为上下文加载。所有 15 个命令均定义在 .gemini/commands/*.toml 中。

Option B: Standalone API Script (No CLI install needed) 选项 B：独立 API 脚本（无需安装 CLI）

# 1. Get a free API key at https://aistudio.google.com/apikey
cp .env.example .env # Edit .env, set GEMINI_API_KEY=your_key_here
# 2. Install dependencies
npm install
# 3. Evaluate a job description
node gemini-eval.mjs "We are looking for a Senior AI Engineer..."
node gemini-eval.mjs --file ./jds/my-job.txt
npm run gemini:eval -- "JD text here"

Free tier: Both options work without billing. Native CLI uses Google OAuth; the API script uses gemini-2.5-flash (15 RPM, 1M tokens/day free). 免费层级：两种选项均无需付费即可使用。原生 CLI 使用 Google OAuth；API 脚本使用 gemini-2.5-flash（15 RPM，每天 100 万 Token 免费额度）。

Usage

使用方法

Career-ops is a single slash command with multiple modes: Career-ops 是一个包含多种模式的单一斜杠命令：

  • /career-ops → Show all available commands (显示所有可用命令)
  • /career-ops {paste a JD} → Full auto-pipeline (evaluate + PDF + tracker) (完整自动流程：评估 + PDF + 追踪)
  • /career-ops scan → Scan portals for new offers (扫描门户网站获取新职位)
  • /career-ops pdf → Generate ATS-optimized CV (生成 ATS 优化简历)
  • /career-ops batch → Batch evaluate multiple offers (批量评估多个职位)
  • /career-ops tracker → View application status (查看申请状态)
  • /career-ops apply → Fill application forms with AI (使用 AI 填写申请表)
  • /career-ops pipeline → Process pending URLs (处理待处理的 URL)
  • /career-ops contacto → LinkedIn outreach message (LinkedIn 联络消息)
  • /career-ops deep → Deep company research (深度公司调研)
  • /career-ops training → Evaluate (评估)
← 返回新闻列表 / Back to news list