florianbuetow/resume
Build and review software engineering résumés from an evidence chain, not a template, in the manner of Richard Feynman and W. Edwards Deming. Applies the three-reader standard (parser, recruiter, engineering interviewer): every claim carries context, action, constraint, result, and ownership; every number is asked by what method; the person's contribution is separated from the system's. review judges a résumé in two phases (up to eight ranked questions, then re-score on the answers into a prediction and a fix list) and never emits an ATS score. build harvests accomplishments one at a time into a win log with provenance, writes five-part bullets, assembles a few coherent versions per role family, runs the two pre-apply tests, and sets up tracking. Subcommands: review, build.
Build a software engineering résumé interactively from an evidence chain, not a template. Use when the user says "build my résumé", "write my CV", "help me create a resume", "rewrite my résumé from scratch", "build the perfect resume", "turn my experience into résumé bullets", "start a win log", or invokes $resume:build. Harvests accomplishments one at a time into a win log with provenance, writes five-part bullets (context, action, constraint, result, ownership), assembles a few coherent versions by role family, runs the two pre-apply tests with the $resume:review judge, and sets up tracking. Never invents a metric.
Review a software engineering résumé or CV as an LLM judge in the manner of Richard Feynman and W. Edwards Deming, against The Serious CTO''s three-reader standard (parser, recruiter, engineering interviewer). Use when the user says "review my résumé", "review my CV", "judge this resume", "is my CV ready to send", "evaluate my resume for a <role>", "resume review", or invokes $resume:review. Tests every claim against the five-part evidence chain, asks for the provenance of every number, ranks the questions that would resolve the most uncertainty, stops for answers, then re-scores and delivers a prediction plus a fix list. Never emits an ATS-style score.