Score resume text for applicant tracking system (ATS) compatibility. Returns a 0-100 score, a recruiter take, prioritized issues with concrete fixes, and detected strengths. Use for "is my resume ATS friendly", "why am I not getting interviews", or before tailoring to a specific job.

Parse a job posting into structured data: title, company, seniority, industry, must-have keywords, nice-to-have keywords, and key responsibilities. Feed the result into optimize_resume to find keyword gaps.

Return prioritized, rewrite-level suggestions for a resume, optionally aimed at a specific role or job description. Each suggestion has a type, priority, tip, and an example rewrite. Pass missingMustHave / missingNiceToHave from analyze_job_description to close keyword gaps.

Run the MatchCV "resume roast": a brutally honest recruiter reaction plus an ATS score. Returns a public shareable report URL. Use when the user wants candid feedback rather than a polite checklist.

Read a local PDF/DOC/DOCX/TXT resume and return its plain text, optionally also parsing it into structured JSON (name, experience, education, skills). Text extraction is unlimited; set structured=true only when the structured form is needed, since that path uses a daily AI credit. Scanned/image-only PDFs will fail — ask the user to paste the text instead.

The full MatchCV pipeline: analyze the job description, structure the resume, then rewrite it for that role with must-have keywords worked in and bullets rewritten. Returns the tailored resume JSON, an ATS score, and a public preview link the user can open and download as PDF. This is the heaviest tool — it uses one generation credit plus the parse and JD-analysis credits, so run it once the user has settled on a target job.