Resume Crafting logo

Resume Crafting

Community
youngbeauty
resume-crafting

简历优化与包装。把平淡的经历描述改写成让面试官"被镇住"的高信号简历,方法论提炼自一份爆火的校招简历(多模态算法工程师,每个面试官都被镇住的那种)。当用户想优化简历、改简历、写简历、包装经历、准备校招/社招材料、把项目经历写得更有分量、或让你评估一份简历的强弱时,使用这个 skill。包括中英文简历。也适用于把一段口头描述的工作经历转成简历 bullet。

Overview

Publisheryoungbeauty
RepositoryGodSU
Skill nameresume-crafting
Stars
74
Forks
4
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by youngbeauty on GitHub. Read the source before you install it.

Installation

Install the Resume Crafting AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/youngbeauty/GodSU/tree/main/resume-crafting
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/youngbeauty/GodSU.git /tmp/GodSU
mkdir -p .claude/skills
cp -r /tmp/GodSU/resume-crafting .claude/skills/resume-crafting
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Resume Crafting in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Resume Crafting on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Resume Crafting is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

简历包装(Resume Crafting)

目标:把用户真实做过的事,用最高的信号密度呈现出来。只放大,不虚构——每一条写上去的内容都必须能在面试中守住 15 分钟的追问,守不住的包装是负资产。

方法论来自一份逐段拆解过的爆火校招简历:手法层拆解见 references/exemplar.md(做什么),句式层拆解见 references/phrasebook.md(具体怎么写,13 个句式模板)。开始改写前先读这两份,看看"满分卷"长什么样。

工作流程

第 1 步:挖料(先问,别急着写)

用户给的初始素材几乎总是不够的。简历写得弱,90% 是因为料没挖出来,不是文笔问题。对每段经历追问:

  • 你到底负责到什么程度? 是 owner、核心成员、还是参与者?从 0 到 1 还是接手维护?(决定能不能用 ownership 语言)
  • 有没有数字? 任何维度都行:性能提升、成本下降、耗时缩短、调用量、用户量、转化率、覆盖率、star 数、榜单名次。用户说"没有数字"时,帮他推算:上线前后对比?人工 vs 自动化耗时?服务了多少人/多少次调用?
  • 旧方案是什么,为什么不行,你改成了什么? 这是"技术判断力叙事"的原料,比"做了什么"值钱得多。
  • 有没有外部可验证的锚点? GitHub 链接、线上产品域名、开源社区身份、比赛名次、内部榜单/等级。
  • 有没有极值? 最年轻的、第一个、排名第一的、唯一的。哪怕限定词很多("公司内该方向排名第一")也有效。
  • 有什么反差或人味素材? 跨界背景、非典型起点、小众爱好里做出的东西。

如果用户丢来一份现成简历,先做逐条诊断(用下面的手法清单当检查表),标出每条缺什么,再挖料。

第 2 步:定信号排序(头部即胜负)

面试官平均 30 秒扫一份简历。前 5 行决定他用什么心态读剩下的部分。

  • 把最稀缺、最可验证的 2-4 个信号压进姓名下方的一行简介里(年龄/年级优势、开源身份、极值标签、代表作链接)。
  • 经历排序按信号强度,不必严格按时间。最硬的一段放最前。
  • 每个头部信号都配可点击/可搜索的锚点:少数几个真实可查的锚点会让其余内容集体沾光。

第 3 步:逐段改写(统一叙事骨架)

每段经历都套这个结构,读起来像 mini 技术方案而不是岗位描述:

项目名 | 一句话定位(借势:绑到大公司/大项目/热方向上)
背景与目标:旧方案的痛点是什么,要解决什么
我的职责:ownership 定位(owner / 核心作者 / 主导 X 到 Y 的升级)
技术链路:具体到架构决策和参数级细节(见"细节密度"手法)
指标:量化收益,用"约 / + / 区间"留余地

改写时对照 references/exemplar.md 里的手法清单逐条应用,核心的几条:

  • Ownership 语言:能说"主导/owner/从 0 到 1"就不说"参与/协助"——但必须与第 1 步确认的真实角色一致。
  • 演进叙事:优先写"1.0 有什么问题 → 我改成 2.0 → 收益",而不是平铺功能列表。
  • 热词命名:把自己做的事映射到行业当前最热的术语上(做上下文裁剪 → Context Engineering;写打分脚本 → LLM-as-Judge / Rubric Eval)。前提:用户真的能讲清这个术语的内涵,否则是自爆按钮。
  • 细节密度:写到参数级(并发数、超时阈值、token 阈值、压缩策略)。具体数字=可信度,而且密度本身就是威慑。
  • 量化留余地:+25%+、约 30%、月均 600+ 次。区间和约数比精确数字更可信也更难被证伪。

第 4 步:防伪审计(最后一道,不可跳过)

逐条过一遍成稿,对每个 claim 问:

  1. 面试官追问 3 层,用户能守住吗?("这个 25% 怎么测的?baseline 是什么?")守不住 → 降级措辞或删掉。
  2. 数字的口径能说清吗? 每个数字用户要能一句话说出来源。
  3. 热词用户能定义吗? 让用户口头解释一遍他简历里的每个术语,卡壳的换成平实说法。
  4. ownership 会不会被背调/交叉面试戳穿? 团队项目里把队友的活写成自己的,是最常见的死法。

把审计中降级/删除的条目告诉用户并说明原因——这本身就是给用户的面试预演。

第 5 步:排版交付

文案定稿(或带待确认占位的准定稿)后,用 resume-typeset skill 排版导出一页 A4 PDF——那才是最终交付物,markdown 只是中间产物。待确认项在排版里会显示为黄色高亮,视觉上无处可藏。

输出格式

  • 交付改写后的简历正文(markdown),保持用户原有语言(中文简历就中文,术语可保留英文)。
  • 每段改写后附一个简短的「改动说明」:用了哪些手法、哪些数字需要用户确认口径。
  • 若用户只给了口头描述,先输出挖料问题清单,拿到回答再写。

边界

  • 不虚构经历、数字、头衔、身份。用户要求编造时,明确拒绝并解释:包装被戳穿的负收益远大于平淡的负收益。
  • 极值标签必须真实成立(可以加限定词收窄范围来让它成立)。
  • 这套手法为技术岗(尤其 AI/算法/工程)调校;非技术岗可复用骨架,但热词命名一节要换成对应行业的热词。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Resume Crafting AI skill do?

简历优化与包装。把平淡的经历描述改写成让面试官"被镇住"的高信号简历,方法论提炼自一份爆火的校招简历(多模态算法工程师,每个面试官都被镇住的那种)。当用户想优化简历、改简历、写简历、包装经历、准备校招/社招材料、把项目经历写得更有分量、或让你评估一份简历的强弱时,使用这个 skill。包括中英文简历。也适用于把一段口头描述的工作经历转成简历 bullet。

Why use Resume Crafting on TypingMind?

Because you install it once and use it with any model. Resume Crafting is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Resume Crafting in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/youngbeauty/GodSU/tree/main/resume-crafting. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Resume Crafting?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Resume Crafting?

As many as you like. As long as a model supports skills, you can use Resume Crafting with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Resume Crafting AI skill free?

It is published on GitHub by youngbeauty. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇