¿Puedo vibecodear CVMatchScore?

Build me a local resume match scorer to replace CVMatchScore. Requirements:

- A Node 22 CLI: `match score resume.pdf job.txt` prints a score table and writes
  a Markdown report to reports/YYYY-MM-DD-<company>.md.
- Extract resume text with pdf-parse; accept .txt and .md for the job posting.
- Keep the rubric in rubric.json: 10 criteria (skills overlap, seniority fit,
  domain experience, quantified achievements, education, keyword coverage,
  employment gaps, clarity, length, ATS-safety), each with a 0-10 definition
  and a weight.
- One Anthropic structured-outputs call scores all criteria at once and must
  quote the resume line that justifies each score, no unquoted claims.
- A second cheap pass lists the 10 most important posting keywords missing from
  the resume and where each could honestly fit.
- Weighted total out of 100, computed in code from rubric.json, not by the model.
- Store every run in SQLite via better-sqlite3: date, company, total, and the
  per-criterion JSON, so `match history` shows my scores over time.
- API key from .env. No accounts, no telemetry, the resume never leaves my
  machine except the API call.
- Out of scope: cover letter generation, DOC/DOCX parsing, multi-language
  support, and recruiter-style bulk ranking.
- README: setup, cost per run, and a warning that scores are only comparable
  within one rubric version, so bump a version field in rubric.json when I edit it.