agentleFS
KinomotoMioKinomotoMio/resumaker/skills/resume-tailor/SKILL.md

resume-tailor

Skill5 starsChanged 30 days agoMITView on GitHub

针对一份具体的 JD,从个人履历库里挑选最对口的成果、选对讲法,编译出定制简历(resume.yaml)和匹配报告(命中、缺口、投递策略),并做溯源检查确保每条内容都有出处。当用户贴出 JD / 招聘链接、说"帮我针对这个岗位改简历""这个岗位我适合吗""生成一份投 XX 的简历"时使用。

29 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use application-tracker, job-search and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • xiding-codeSkill

    application-tracker

    Automatically log and track all job applications submitted. Use this skill after every application submission to record the details in a tracking spreadsheet and save relevant documents. Also trigger when the user asks "application status", "what have I applied to", "tracking", or wants to review their application history. Maintains a single source of truth for all job search activity.

    Also in 3 projects that use this

  • proficientlyjobsSkill

    job-search

    Search for jobs matching my resume and preferences

    Also in 3 projects that use this

  • AnthropicSkill

    interview-prep

    Create structured interview plans with competency-based questions and scorecards. Trigger with "interview plan for", "interview questions for", "how should we interview", "scorecard for", or when the user is preparing to interview candidates.

    Also in 3 projects that use this

The file

Files
SKILL.md

Resume Tailor

简历是编译产物:履历库 + JD → 匹配报告 + 简历 + 深挖卡。

0. 准备

按约定定位履历库:RESUMAKER_VAULT → ~/.config/resumaker/config.json → ./career/。找不到就转 resumaker-init。 先读 <vault>/VAULT.md,然后读 profile.md。

1. 收下 JD

用户可能贴文本、给链接或给文件。链接打不开时请用户直接粘贴。 新建投递目录 applications/<YYYY-MM-DD>-<company>-<role>/(kebab-case,公司和岗位可以用拼音或英文), 把 JD 原文和来源链接写进 jd.md。

2. 拆解 JD

写进 match.md 的第一部分(模板见 references/match-template.md):

  • 硬性要求:年限、学历、必须会的技术。国内 JD 里通常在"任职要求"
  • 核心职责:真正要干的活。通常在"岗位职责",比要求更能说明岗位本质
  • 加分项
  • 隐含信号:职级、团队阶段(从 0 到 1 / 规模化 / 维护)、业务方向、JD 里反复出现的词
  • 关键词:ATS 和 HR 初筛会找的词,保留 JD 的原始写法(比如是"K8s"还是"Kubernetes")

3. 在库里找匹配

  1. 先按 skills、tags 在 achievements/ 的 frontmatter 里粗筛(grep 就够了),再细读候选文件。
  2. 对每条要求和职责,标出 强命中 / 部分命中 / 未命中,并写出对应的成果 id。
  3. 针对缺口主动提问,这是最有价值的一步。很多人做过但没记下来:

    JD 很看重"跨团队推动"。你在 Acme 推网关迁移时,是不是协调过其他组?大概几个组?

    用户的回答写回履历库:完整的成果直接存进 achievements/(status: confirmed,因为是用户亲口确认的);不确定的放进 inbox/。 这样每投一次,库就更厚一点。

  4. 在 match.md 里给出结论:匹配度(高/中/低)、值不值得投、主打什么叙事、缺口怎么应对。 匹配度低就直说,不要为了生成简历而硬凑。

4. 编译简历

按 resume-render 的 assets/example/resume.yaml 的结构写 resume.yaml。

选材

  • 按和 JD 的相关度排序,而不是按时间轴把所有事都塞进去
  • 每段经历 2~5 条 bullet;无关的经历可以压缩成一行,或者不写
  • 技能区只列和 JD 相关、并且在成果里有支撑的技能

选讲法

  • 每条成果的 ## 讲法 里可能有好几个角度,选和 JD 核心职责最贴近的那个
  • 没有合适的现成讲法,就基于成果原文重写,新讲法顺手补回成果文件

写 bullet

  • 结构:动词开头 + 做了什么 + 怎么做的 + 结果(数字),一条不超过两行
  • 用 JD 的词描述你确实做过的事(比如你做过 K8s 部署,JD 写的是"云原生",可以这样表述);不会的技能不写
  • 每条最多加粗 1~2 处,留给数字和关键结果
  • 每条都带上 from: <成果 id>
  • internal 级别的成果要脱敏:内部系统名换成通用描述,去掉客户名,未公开的数据用相对值
  • secret 级别的成果不出现

summary:两句话,第一句"我是谁 + 核心方向",第二句是最贴合这个 JD 的一项硬实力。

5. 溯源检查(必须做)

python3 scripts/trace.py <投递目录>
  • errors:引用了草稿、不存在的成果,或 secret 内容。必须修
  • warnings:数字找不到出处、用了未验证的数字、internal 内容需要确认脱敏。逐条处理:找到出处补进成果文件,或者改写 bullet
  • unsourced:没有 from 的 bullet。只允许出现在教育背景、技能这类来自 profile.md 的内容里

ok: true 之前不要进入下一步。

6. 排版和后续

  1. 转 resume-render 渲染并自检。
  2. 告诉用户:匹配结论、主打的叙事、主要缺口,以及 PDF 路径。
  3. 建议用 interview-grill 生成深挖卡,对着这份简历练一遍。
  4. 在 notes.md 里记一笔:投递日期、渠道、简历版本。以后有面试反馈或结果也记在这里,复盘时可以看出哪种讲法更有效。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.