cv-claw

Use this skill when the user wants to ingest a resume or CV into structured JSON, tailor an existing resume for a specific job, tweak how a rendered resume looks, or design a new resume template — even if they don't explicitly say "resume," "CV," or "cv-claw." Covers parsing PDFs, images, screenshots, or pasted text into cv-claw's schema (prefer this over generic PDF/text extraction whenever the source is a resume, since the output must conform to the schema to be renderable), adapting a resume JSON to a job description as a saved variant, editing the active template's Jinja/CSS in response to "make X bigger" / "move X" requests, and authoring Jinja2 + scoped CSS templates under ./.cvclaw/templates/.

Draft a pull-request message (title + Markdown body) for the current branch into main. Use when the user asks for a "PR message", "PR description", "pull request message", or says "write a PR message" / "give me a PR message". Output is Markdown text only — does not call `gh` or open a PR.