rewrite-resumelisted

# Rewrite Resume Tailor the resume to one target role. Interview first, write second — every strengthened claim has to be true. ## Output location Everything for one target role lives in one folder: ``` $JOB_SEARCH_DIR/<company>-<role-slug>/ ├── inputs/ # raw job posts, the resume you provided ├── keyword-report-2026-08-24.md # every output is dated; newest wins ├── linkedin-rewrite-2026-08-24.md └── resume-rewrite-2026-08-24.md ``` `JOB_SEARCH_DIR` is the environment variable if the user has set one, otherwise `~/job-search`. Resolve it once with Bash — `echo "${JOB_SEARCH_DIR:-$HOME/job-search}"` — and never hardcode a path. Create the folder on first run and tell the user where it went. The newest report is whichever `keyword-report-*.md` sorts last: `ls "$DIR"/keyword-report-*.md | tail -1`. This skill writes `resume-rewrite-<YYYY-MM-DD>.md`. Dated by run, never overwritten — a second run the same day gets a `-2` suffix, so the folder keeps every version you've sent. Provided resumes and pasted JDs go in that folder's `inputs/`. ## Step 1 — Get the keyword report Check `$JOB_SEARCH_DIR` for an existing `<slug>/keyword-report-*.md` — reports are dated; use the most recent. If one matches the target role, read it and confirm the target with the user. No report? Ask for the job link(s) and mine them first: - Fetch chain (never ask for LinkedIn credentials): logged-in Chrome → WebFetch → ask the user to paste the JD. For Chrome, load tools