Resume Builder logo

Resume Builder

Community
StoneLL1
resume-builder

简历制作流水线:为求职 / 比赛 / 升学新建、完善或重组简历(中文 / 英文,1–2 页),覆盖对话收集→事实核对→撰写→画廊选模板→Typst 排版→浏览器可视化精修→导出 PDF,强调事实可溯源、不编造。触发词:简历、resume、CV、投简历、改简历。

Overview

PublisherStoneLL1
Repositoryresume-builder
Skill nameresume-builder
Stars
123
Forks
4
Bundled files
258
LicenseMIT
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.

  • 258 bundled files

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

  • Open source

    Published by StoneLL1 on GitHub. Read the source before you install it.

Installation

Install the Resume Builder 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/StoneLL1/resume-builder/tree/main
  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/StoneLL1/resume-builder.git \
  .claude/skills/resume-builder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Resume Builder 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 Builder 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 Builder 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.

Resume Builder — 简历制作流水线

适用场景

用户要为某个具体目标(求职岗位 / 比赛 / 升学)制作中文或英文简历,或要把不同用途的简历分目录管理。

能力边界(不做什么)

  • 只做 1–2 页求职 / 比赛 / 升学简历。
  • 不做:三页及以上简历、多页学术 CV、求职信 / 推荐信、作品集 / 个人主页、手机和平板编辑。
  • 素材只通过对话提供(粘贴文字、口述、让 Agent 读本地 PDF);网页端不上传旧简历、PDF 或 JD。
  • 编辑器不内置 AI 对话、不做跨板块拖拽、不做快照回滚;所有数据只在本机,不调用云端接口。

超出范围就明示用户,另寻工具。

项目归档(每个用途一个独立目录)

text
<用途>/
├── resume.json      ← 唯一内容数据源,Agent 与网页编辑器共同读写
├── resume.pdf       ← 导出的正式交付物(姓名-目标岗位-电话.pdf)
└── work/
    ├── 信息整理.md   ← 素材库
    ├── claim-map.md  ← 事实追溯表
    ├── session.json  ← 阶段状态机(Agent 与本地服务协作)
    ├── events.jsonl  ← 事件日志
    └── build/        ← 渲染中间产物,不作为交付物

用途目录之间互不联动。新建简历先建目录,再开始收集。

核心原则

  • 撰写前必读:在撰写、改写、审计简历或针对 JD 定制之前,必须完整阅读 Resume-Writing-Guide-LLM.md,并按其方法进行内容取舍、证据表达与措辞调整。它是本 skill 写作方法论的唯一权威,也适用于模板适配时的压缩与润色;不能只读阶段说明就直接动笔。同一会话已完整读过后,后续按需回查,不必每轮重读。
  • 事实不可编造(最高优先级):决策链 真实性 > 岗位匹配 > 证据强度 > 个人贡献 > 结果影响 > 可扫描性 > 文辞漂亮。没有可靠数字时不估算、不补造、不美化,改用真实的上线、采用、验收、规模、交付物、决策影响或外部认可。
  • 强表述必须可举证:主导、Owner、独立负责、设计、优化 等说法要有事实支撑;团队结果不得自动写成个人结果。
  • 目标决定取舍:每份简历围绕一个明确的「背景 + 目的」,与目标无关的经历果断舍弃并说明理由。重包装 ≠ 编造。
  • 内容表达与排版质量:内容清楚、有重点,版面饱满、均衡、易扫读。两者冲突时保留核心证据与可读性;不为排满页面增加空话、重复或无关内容。
  • 两阶段撰写:先产出模板无关的完整内容稿;用户选定模板后,才做模板相关的压缩、排序、断行和页数控制。
  • 模板由用户选:画廊分中文与英文,各 9 套;中文使用指定的 9 个上游原版排版库,英文复用既有来源的原版模板,其中 Harvard 为原版纯黑白。Agent 不替用户最终决定,也不自行重写模板版式。中英文各用其原版字体与布局,不做跨语言或双语适配。
  • 提问驱动完善:缺口分优先级批量提问;用户说"跳过 / 没有"就接受,不反复追问。

事实与防幻觉(claim 追溯)

每份简历在 <用途>/work/claim-map.md 维护一张三列表,贯穿收集→撰写→导出全过程:

简历内容来源状态
某某大学 某专业本科原 PDF / 用户口述✅ 已确认
某项目 年化收益 X%(待用户给出)⛔ 缺失阻塞

四态:✅ 已确认(可写入)· ❓ 待确认(暂不写入,等确认)· ⛔ 缺失阻塞(高危且缺失,必须先问清才能动笔)· ➖ 已省略(经用户同意不写)。

高危类目(要么确认、要么经用户同意省略,绝不猜、不偷删):身份信息 · 学历 / 学校 · 雇主 / 公司 · 时间日期 · 论文 / 专利 · 量化数字 · 照片取舍。

claim-map 由 Agent 在对话中维护;网页端只读展示,不自动改状态。

阶段流程与阅读路由

text
A 对话收集与模板无关撰写 → B 模板选择(画廊)→ C 模板适配与正式排版
    → D 可视化精修(编辑器)→ F 正式导出
D 中用户换模板 → E 重新排版检查 → 回 D
阶段Agent 做什么进入时读取
A收集素材、确认目标、claim-map、缺口提问、模板无关内容稿references/writing-stage.md(首次调用即读)
B启动本地画廊,等用户选模板,自动获取结果references/template-selection.md
C按所选模板二轮精修,写入 resume.json,渲染并检查references/rendering-stage.md + references/data-contract.md
D与网页编辑器协作精修(双方改同一份 JSON)references/editor-stage.md
E针对新模板重新排版和检查references/rendering-stage.md 的换模板一节
F终检后引导导出规范命名 PDFreferences/editor-stage.md 的导出一节
  • 服务器、前端、模板语法、Typst 排错细节全部放在上表按需文件里,主入口不展开。阶段 A 不启动任何服务、不讨论模板与排版实现。
  • 运行与恢复:Windows 使用 scripts/run.ps1、macOS 使用 scripts/run.sh 调用服务和脚本,或使用 bootstrap 输出的解释器绝对路径。默认只装基础运行时,选模板后按需准备字体。首次渲染失败读取具体错误,不连续盲目重试;详见阶段 B/C。
  • 日常制作只检查当前简历:内容与版面检查按 references/rendering-stage.md §4 执行,已检查且未变化的部分不重复检查。发布版不附带开发测试流程。
  • 恢复旧项目:先看 work/session.json 的 stage 字段,按上表路由到对应阶段文件继续。模板退役或语言不匹配时回画廊让用户重选;不得静默换模板。

何时进入模板选择(Agent 自行判断,不问用户"该进下一步吗")

同时满足以下条件即告知用户"素材已充分,即将进入模板选择",然后读 references/template-selection.md:

  1. 内容稿覆盖全部拟保留板块与条目,无占位空壳;
  2. claim-map 中 ⛔ 缺失阻塞清零(已确认,或经用户同意记 ➖);
  3. 关键 ❓ 已确认过一轮(影响定稿的都问过);
  4. 用户暂无新增信息。

信息安全(硬性要求)

  • skill 文件、任何"模板 / 示例 / 流程"内容中不得出现真实姓名、电话、邮箱、学校、公司等个人数据,一律占位符脱敏。
  • 用户真实数据只存在于其自己的用途目录中,不回灌进 skill。
  • 第三方原始源码与许可证保留其上游署名;其中公开示例仅用于来源审计,不注入用户简历。画廊按用户要求使用上游公开预览原图;上游公开示例仅供展示,不注入用户数据。

Bundled files

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

and 140 more files.

Frequently asked questions

What does the Resume Builder AI skill do?

简历制作流水线:为求职 / 比赛 / 升学新建、完善或重组简历(中文 / 英文,1–2 页),覆盖对话收集→事实核对→撰写→画廊选模板→Typst 排版→浏览器可视化精修→导出 PDF,强调事实可溯源、不编造。触发词:简历、resume、CV、投简历、改简历。

Why use Resume Builder on TypingMind?

Because you install it once and use it with any model. Resume Builder 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 Builder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/StoneLL1/resume-builder/tree/main. 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 Builder?

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 Builder?

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

Is the Resume Builder AI skill free?

Yes. It is published on GitHub by StoneLL1 under the MIT license. 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 👇