Why this matters Most automated resume tools stop at text generation; this workflow treats the PDF as the product. It automates job matching, drafts tailored LaTeX CVs and one-page cover letters, runs a separate reviewer agent, compiles and inspects PDFs, and verifies the CV text layer for ATS compatibility—reducing the common gap between “looks right” and “parses right.”
What Sets It Apart
- Drafter–reviewer pipeline: one agent drafts tailored documents and a fresh reviewer agent researches the company and critiques framing and keywords, so drafts are iteratively improved rather than accepted in a single pass.
- PDF-first verification: the system compiles CVs/letters and programmatically fixes layout issues (orphans, font fallbacks) until page limits and visual constraints are met, so the delivered PDFs match recruiter expectations.
- ATS text-layer checks: extracts the PDF text layer to confirm contact info and keyword visibility from an ATS perspective, preventing subtle LaTeX extraction failures that break automated parsers.
- Extensible search skills and templates: ships CLI skills for Danish portals and a country-agnostic LinkedIn skill; supports adding portal scrapers and user LaTeX templates via built-in commands.
Who It's For and Trade-offs
Great fit if you maintain a detailed documents/LinkedIn/CV corpus and want high-assurance, tailored applications at scale—especially users who need both human-readable PDFs and machine-parseable output. Not ideal if you lack any source documents, cannot run Claude Code or LaTeX locally, or need a simple web UI; the workflow assumes command-line use, Claude Code access, and a LaTeX toolchain (lualatex/xelatex).
