resume-alignlisted

# Resume Align Make one resume speak directly to one JD — without inventing a single fact. Respond in the user's language. ## Inputs Need both: (a) the resume or a description of real experience, (b) the target JD. If either is missing, ask for it first. If the JD was already analyzed in this conversation (e.g. by `jd-deep-dive`), reuse those weighted requirements instead of re-deriving. ## Procedure 1. **Evidence map.** For each weighted JD requirement, find the strongest matching evidence in the resume. Output a three-column map: `要求 → 简历证据 → 强度(强/弱/缺)`. Be strict: a keyword mention without a result is `弱`; nothing relevant is `缺`. 2. **Rewrite the weak.** For every `弱` row, rewrite the bullet in achievement form: action verb + scope + method + **measurable result**. Where the number is missing, do not fabricate — insert a bracketed prompt the user must fill, e.g. `[QPS 峰值?]`, `[节省了多少人日?]`, and explain in one clause why that number matters for THIS role. 3. **Fill or reframe the gaps.** For every `缺` row, ask one targeted question to discover latent experience ("有没有做过哪怕一次…?"). If genuinely absent, suggest the honest adjacent framing (transferable skill) — never a false claim. 4. **Keyword pass.** List JD terms an ATS or a skimming interviewer will scan for that are absent or phrased differently in the resume; show the exact substitution (`分布式缓存` → the JD's `Redis 集群`), only where the underlying experience is real. 5. **Tailored summary.** Draft a 2–3 line profile parag