# Quick Start Source: https://career-ops.org/docs (canonical HTML, identical content) > Get started with career-ops in five minutes: install the open-source AI job-search system, open your AI CLI, and evaluate your first job listing. No coding required. This guide takes you from zero to your first evaluated job in about five minutes. You will set up the workspace, open your AI coding assistant, let it onboard you conversationally, and then paste a job posting — career-ops gives you back a full report, a score, and a tailored PDF resume. ## What you need [#what-you-need] You do not need to know how to code. You only need to be comfortable opening a terminal and running a command. > **New to the terminal?** If you have never used a command line before, that is completely fine — but this guide is not the place to learn it. To get up to speed quickly, read the [Command Line for Beginners](https://www.freecodecamp.org/news/command-line-for-beginners/) handbook by freeCodeCamp. It covers everything you need to follow along here. Once you are comfortable opening a terminal and running a command, come back and continue from Step 1. ### AI coding assistant [#ai-coding-assistant] Install **[Claude Code](https://claude.ai/code)**, **[Codex](https://developers.openai.com/codex/cli)**, **[OpenCode](https://opencode.ai/)**, **[Qwen Code](https://qwen.ai/qwencode)**, or **[GitHub Copilot CLI](https://docs.github.com/en/copilot/github-copilot-in-the-cli)** — the AI coding assistant that runs this system. career-ops works with [eight CLIs first-class](https://career-ops.org/docs/supported-clis.md); install any one and log in before continuing. ### Node.js 18+ (22.5+ recommended) [#nodejs-18-225-recommended] Install **[Node.js](https://nodejs.org)** — minimum **18** (it works, with a warning), **22.5+ recommended** (it enables the SQLite tracker index). It runs the helper scripts and generates PDFs. Check your version with `node --version`. ### Git [#git] Install **[Git](https://git-scm.com/)** — used internally by the scaffolder. Most computers already have it. To check, open a terminal and run `git --version`. ## Step 1: Set up the workspace [#step-1-set-up-the-workspace] Open a terminal in the folder where you want career-ops to live. The recommended path uses one command; an advanced path with `git clone` is below it. If Node (18+) or Git are missing, `npx` will refuse to run — install both first (see prerequisites above). ### Recommended — one command [#recommended--one-command] ```bash title="Terminal" npx @santifer/career-ops init ``` This clones the latest release into `./career-ops`, installs dependencies, and scaffolds the workspace structure. It also detects which AI coding CLI you have installed and tells you the right command to start with. The command is idempotent — running it again never overwrites files you already have. Move into the workspace when it finishes: ```bash title="Terminal" cd career-ops ``` **Advanced — clone the repository yourself** Use this path if you want to track a specific branch, contribute back, or audit the code before installing dependencies. ```bash title="Terminal" git clone https://github.com/santifer/career-ops.git cd career-ops npm install ``` ### Headless browser (one-time) [#headless-browser-one-time] career-ops uses a headless Chromium for several jobs: rendering PDFs, checking whether listings are still live, and running full ATS scans. The installer sets it up automatically after dependencies; if that step failed on your machine, install it manually: ```bash title="Terminal" npx playwright install chromium ``` ## Step 2: Open your AI assistant [#step-2-open-your-ai-assistant] From inside the `career-ops` folder, launch the AI coding CLI you installed. **Claude Code** ```bash title="Terminal" claude ``` **Codex** ```bash title="Terminal" codex ``` **OpenCode** ```bash title="Terminal" opencode ``` **Qwen Code** ```bash title="Terminal" qwen ``` **GitHub Copilot CLI** ```bash title="Terminal" copilot ``` **Gemini CLI** ```bash title="Terminal" gemini ``` > **The agent will introduce itself** The first time you launch your CLI inside the workspace, the career-ops agent runs a short onboarding conversation. It asks for your CV, the kinds of roles you are targeting, your compensation range, and your location preference. Nothing is edited by hand — you reply in plain language and the agent writes the config files for you. The session takes about two to three minutes. > **One unrelated prompt you may see** Some CLIs (Claude Code, for example) ask whether you trust the files in a new folder the first time you open it. That prompt comes from the CLI itself, not from career-ops — say yes to continue. The career-ops onboarding starts right after. ## Step 3: Run your first evaluation [#step-3-run-your-first-evaluation] Once the agent has onboarded you, you are ready to evaluate a real job posting. Copy the URL of any job ad and paste it into the chat. With Claude Code, prefix it with the explicit command; with the other CLIs, paste the URL and ask the agent to run the auto-pipeline: **Claude Code** ```bash /career-ops auto-pipeline https://jobs.example.com/senior-engineer-ai ``` **Codex** ```bash Run the auto-pipeline command with the job URL: https://jobs.example.com/senior-engineer-ai ``` **OpenCode** ```bash Run the auto-pipeline command with the job URL: https://jobs.example.com/senior-engineer-ai ``` **Qwen Code** ```bash Run the auto-pipeline command with the job URL: https://jobs.example.com/senior-engineer-ai ``` **GitHub Copilot CLI** ```bash Run the auto-pipeline command with the job URL: https://jobs.example.com/senior-engineer-ai ``` **Gemini CLI** ```bash Run the auto-pipeline command with the job URL: https://jobs.example.com/senior-engineer-ai ``` If you do not have a URL, paste the full job description text into the chat instead. The agent detects either input as a job posting and runs the full pipeline automatically — this is the **auto-pipeline**. ### What happens next [#what-happens-next] After you paste the job, career-ops does the following on its own: ### Reads the job description [#reads-the-job-description] Understands the role, requirements, and compensation. ### Reads your CV [#reads-your-cv] Pulls from `cv.md` to find matches and gaps against the role. ### Scores the job [#scores-the-job] Rates the role from 0 to 5 across multiple dimensions, like role fit, compensation, and remote policy. ### Writes a report [#writes-a-report] Saves a detailed breakdown to the `reports/` folder. ### Generates a tailored PDF resume [#generates-a-tailored-pdf-resume] Outputs a version of your CV customized for this specific job to the `output/` folder. ### Adds a row to your tracker [#adds-a-row-to-your-tracker] Logs the application in `data/applications.md`. The whole process takes about one to two minutes. When it finishes, career-ops shows you the score and a summary of the report. ## Reading your results [#reading-your-results] Open the report file in `reports/`. The filename follows the pattern `{number}-{company}-{date}.md`. Inside, you will find: * **Score** — a number from 0.0 to 5.0. Anything below 4.0 means the job is probably not a strong fit. * **Block A** — a plain-English summary of the role. * **Block B** — a table showing how your CV matches each job requirement, plus any gaps. * **Block C** — a strategy recommendation for how to position yourself for this role. * **Block D** — compensation research comparing the offer to market rates. * **Block E** — personalization notes for your application. * **Block F** — interview preparation with STAR stories tailored to this job. * **Block G** — posting legitimacy: a check that the listing is real and not a scam or ghost job. Your tailored PDF resume is in the `output/` folder. Review it before sending it anywhere — career-ops never submits anything without your approval. ## What to do next [#what-to-do-next] Now that your first evaluation is done, here are a few things you can explore: * **Refine your profile.** Tell the agent something new about yourself — *"Here is more context: I just shipped X."* It updates the profile and future evaluations get more accurate. * **Evaluate more jobs.** Paste more URLs or descriptions. Each one adds to your tracker. * **Scan job boards.** Type `/career-ops scan` to search dozens of pre-configured company career pages at once. * **Compare offers.** If you have several reports, type `/career-ops ofertas` to get a ranked comparison. ## Troubleshooting [#troubleshooting] #### The agent did not run the onboarding Make sure you launched your CLI from inside the `career-ops` folder (run `pwd` to check). Re-launch the CLI from the right path and tell the agent: *"please run the first-run onboarding."* It will start the conversation from scratch. #### The report did not generate Make sure `cv.md` exists in the root folder and has content in it. If the onboarding finished but `cv.md` is empty, ask the agent: *"my cv.md looks empty, can you help me fill it in?"* #### The PDF did not generate Run `npx playwright install chromium` again. If that does not fix it, check that Node.js is version 18 or higher (22.5+ recommended) by running `node --version`. #### The score seems off The first few evaluations are rough — the system does not know you well yet. After each evaluation, tell your AI assistant what it got wrong. For example: *"That score is too high — I have no experience with Kubernetes."* It will learn and adjust. #### Something else is broken Ask your AI assistant directly: *"What is wrong with my setup?"* If it cannot diagnose it, run `npm run doctor` for a full health check. ## Found a bug or have a question? [#found-a-bug-or-have-a-question] If something is not working the way this guide says it should, please report it. Bug reports help everyone who comes after you. * **Report a bug:** Open an issue on the [GitHub repository](https://github.com/santifer/career-ops/issues). Describe what you expected to happen, what actually happened, and paste any error message you saw. * **Ask a question:** Join the [Discord community](https://discord.gg/8pRpHETxa4). It is the fastest way to get help from other users and the author. * **Contribute a fix:** If you know how to fix the issue yourself, read [CONTRIBUTING.md](https://github.com/santifer/career-ops/blob/main/CONTRIBUTING.md) before opening a pull request. The short version: open an issue first to discuss the change, then submit your PR.