Should you build your own Saply?

Build me a local CV formatting pipeline to replace Saply for personal use. Requirements:

- A Node + Express app on localhost:4173 with one page to upload a PDF or DOCX,
  choose a file from templates/, add an optional job description, and run the job.
- Extract DOCX text with mammoth and PDF text with pdftotext. Detect image-only files
  and stop with a clear message instead of producing an empty CV.
- Send extracted text to an LLM API of your choice, key from .env, using a strict JSON
  schema for contact details, summary, skills, experience, education, and certificates.
- Never invent employers, dates, qualifications, or skills. Missing values stay null,
  and every tailored claim must be supported by the source CV.
- Render the JSON into the selected tagged Word template using docxtemplater and PizZip,
  preserving its fonts, colors, tables, headers, footers, and repeating experience rows.
- When a job description is present, show a 0-100 match score, strengths, gaps, and
  questions. Rewrite the summary and bullets only when a Tailor checkbox is enabled.
- Save job metadata and structured JSON in SQLite via better-sqlite3. Delete uploaded
  source files and generated documents after 24 hours.
- Bind to localhost only, with no accounts or telemetry. Data leaves the machine only
  for the documented LLM call.
- Out of scope: OCR for scanned CVs, Word or Google Docs add-ins, ATS/email integrations,
  bulk processing, collaboration, and enterprise compliance controls.
- Include a sample tagged template, two fixture CVs, extraction/render smoke tests, and
  a README covering setup, .env, template tags, retention, and the honest limitations.
- Be aware of the hard part: CVs vary wildly in structure (two-column layouts, tables,
  sidebars, mixed date formats), and a schema that runs fine on the fixtures will
  silently miss fields on real-world CVs. Test on messy inputs and document what gets
  dropped.