面试复盘 skill（求职者视角）。把一次已结束的面试，从「文字记录」沉淀成结构化复盘：逐题诊断 + 5 维评分 + 更优回答范本 + 下一场准备清单，最终产出一份飞书复盘文档。当用户说"面试复盘"、"复盘一下面试"、"刚面完 XX 帮我盘下"、"这场面试哪答崩了"、"面试问答记录帮我分析"时触发。
区别于 resume-optimizer / cv-expert（面试前优化简历），本 skill 处理「面完之后」。
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
把一次「面完就散」的面试，沉淀成可复用的资产。核心交付：一份飞书复盘文档，含逐题诊断、5 维评分、更优回答范本、下一场行动清单。
resume-optimizer / cv-expertlark-minutes（飞书妙记）转写，再回到本 skill| 素材 | 必需 | 说明 |
|---|---|---|
| 面试问答文字记录 | ✅ | 直接粘贴；或给飞书文档链接 → 用 lark-doc 读取 |
| 目标 JD | 强烈建议 | 判断「该考什么」+「你的卖点有没有打出来」 |
| 自己的简历 | 强烈建议 | 看回答和简历是否自洽、有没有挖出更强的故事 |
| 基本信息 | 引导补全 | 公司 / 岗位 / 轮次（HR/技术/总监/HR终面）/ 整体感觉 / 自评卡壳的题 |
记录越糙没关系（断断续续的回忆也行），但不要编造没发生的问答——记不清的题标「记不清」，复盘它「为什么记不清」本身也是信息。
lark-doc 读取正文。把记录拆成有序的「问题清单」。每题抽成四元组：
输出一张 timeline 表给用户确认，确认后再进入逐题复盘——避免在错误的还原上做一大堆分析。
对每一题给出：
references/rubric.md 的单题四档（优 / 良 / 中 / 差），一句话定级理由被追问崩了的题要单独标注追问链，复盘「第几个追问开始接不住」。
基于全场，给 5 维评分（量表见 references/rubric.md），每维一句话点评：
用 lark-doc skill 创建（docs +create --api-version v2，正文走 Markdown）。
面试复盘 · {公司}-{岗位}-{轮次} · {YYYY-MM-DD}（日期用今天）references/report-template.md写文档前，先把完整内容在对话里给用户过一遍，用户确认后再创建飞书文档（符合「先商量再动手」的习惯）。
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
AI 初学者导师。抓取 AI 大厂最新博客（Anthropic/OpenAI/Cursor），提炼成结构化深度精读笔记，直接存入 CherryStudio 笔记目录。笔记包含术语百科、核心原理解析（含关键图表）、学习重点、知识关联和行业简报。调用方式：/ai-tutor（默认 Anthropic），/ai-tutor openai，/ai-tutor cursor。
The English summary is being prepared. Showing the original description.
标书文档分析与评估。当用户上传招标文件（.pdf/.docx/.doc/.xlsx）或明确要求「分析标书」「评估投标」「检查合规性」「标书评分」「废标风险」「技术方案评估」时使用。支持解析、评分计算、合规检查、废标风险识别，自动生成 Markdown 报告。版本 3.0
The English summary is being prepared. Showing the original description.
投标书模板填充引擎。当用户明确要求「填模板」「写标书」「出标书」「生成投标文件」「标书填充」「套模板」「做标书」，或提供了脱敏 DOCX 模板需要填充时使用。扫描模板中的占位符和虚拟文本，提取招标信息、收集投标人数据、构建替换映射、执行填充，输出可直接提交的成品标书。覆盖商务标+技术标+报价书全部章节。
The English summary is being prepared. Showing the original description.
This skill should be used when the user asks to "优化简历", "resume optimization", "简历诊断", "tailor resume to JD", "改简历", "resume review", "简历优化助手", or when the user mentions "校招", "社招", "ATS", "JD匹配", "Word批注", shares a .docx resume path alongside a job description, or wants to match their resume to a specific job posting. Also triggers on "resume expert", "HR feedback", "interview prep with resume".
The English summary is being prepared. Showing the original description.
Full lifecycle expense reimbursement: single invoice intake and staging, batch aggregation to generate reimbursement drafts, approval workflow, ledger and dashboard. Trigger when user mentions reimbursement, expenses, invoices, travel reimbursement, approval workflow, or needs to organize / verify / approve expense records. Also applies when user needs to enter invoices, view reimbursement dashboards, ledgers, or compliance checks.
The English summary is being prepared. Showing the original description.
Discuss a community-edition product requirement with the user, draft a bilingual (Chinese + English) PRD for review, then — after explicit user approval — create the English-only issue on GitHub (<OWNER/REPO>). Use whenever the user wants to turn a requirement (from a Feishu doc, a meeting note, a customer ask, or a rough idea) into a GitHub issue. Triggers on phrases like "create requirement doc", "create a requirement", "put this requirement on GitHub", "create new feature issue", "draft an issue for...", or anytime the user describes a product feature/improvement they want tracked. The format is opinionated (Background / Goal / Spec / Verification / Related, NO implementation details, draft shown bilingually for human review, issue itself written in English only).
The English summary is being prepared. Showing the original description.