Modes

The 14 modes

career-ops ships 14 user-invocable modes. Each one is a plain-markdown skill the agent loads and runs inside whichever AI coding CLI you already use — Claude Code, Codex, OpenCode, Gemini CLI, Qwen, or GitHub Copilot. You invoke a mode as /career-ops <mode>, and each covers one stage of the job search: evaluating a listing against the six-dimension rubric, tailoring a CV, drafting an application, tracking outcomes, or preparing for interviews. Modes are System Layer per the Data Contract — they update with the tool and never modify your cv.md, profile, or reports.

Evaluate

The core scoring loop — read a job listing and score it against the six dimensions before you spend any effort on it.

• auto-pipeline — the default flow. Paste a JD URL or text; it runs the A–F evaluation, writes the report, exports a tailored PDF, and logs a tracker entry with no manual steps in between.
• pipeline — runs auto-pipeline against every URL queued in data/pipeline.md, so a day's worth of listings crunch in one session.
• oferta — the A–F evaluation against a single listing when you only need the scoring decision, not the full pipeline.
• ofertas — ranks two or more competing offers across comp, fit, growth, and red flags into one decision matrix.
• deep — a deep company-research document (funding, leadership, press, comp signals, red flags) before you apply to a company you don't know well.

Tailor & apply

Turn a high-scoring match into a submitted application.

• pdf — renders a tailored, ATS-clean PDF résumé against a specific JD via Playwright.
• apply — reads an open application form's open-ended questions and drafts answers grounded in your CV and the JD.
• contacto — surfaces likely-warm LinkedIn contacts and drafts a short, role-specific outreach message.
• followup — flags applications and interviews overdue for follow-up and drafts the messages.

Track & grow

Keep the search organised and calibrate it over time.

• tracker — a chat-side status summary of every application grouped by stage.
• patterns — reads your rejected and discarded applications to surface targeting patterns and blind spots.
• interview-prep — round-specific prep docs (recruiter, hiring manager, peer technical, panel) with likely questions and STAR stories.
• training — scores a course or certification against your stated career direction and its opportunity cost.
• project — scores a portfolio-project idea against your target roles and the time it would take to build.

Portals

The three zero-token portal scanners — Greenhouse, Ashby, and Lever — have their own portals reference.