Agent skill

Resume Builder

by StoneLL1 in 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。

MITAuto-check passedBusiness, Finance & HR

Install Resume Builder

skills CLI
$ npx skills add StoneLL1/resume-builder --skill resume-builder -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install StoneLL1/resume-builder resume-builder --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
resume-builder
GitHub stars
109
Token cost
~862 tokens
SKILL.md length
173 words
Files
370 (incl. scripts, references, assets)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

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。

  • Works in 4 steps: 内容稿覆盖全部拟保留板块与条目,无占位空壳; → claim-map 中 ⛔ 缺失阻塞清零(已确认,或经用户同意记 ➖); → 关键 ❓ 已确认过一轮(影响定稿的都问过); → …
  • Tasks that involve Resume and CV writing
  • SKILL.md covers 适用场景, 能力边界(不做什么), 项目归档(每个用途一个独立目录) and 核心原则, plus 4 more sections
  • Tasks that involve PDF

What it does

Resume Builder is an agent skill from 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。

Its SKILL.md is about 860 tokens, which your agent loads only when the skill is triggered. The skill folder holds 373 other files, including scripts, reference files and assets (for example `INSTALL.md`, `README.en.md` and `README.md`).

It sits in Business, Finance & HR, covering Resume and CV writing and PDF. The repository describes itself as: 简历制作 Agent Skill | 写作方法论蒸馏自近百篇小红书高赞经验帖. The licence is MIT.

When your agent uses it

  • Tasks that involve Resume and CV writing
  • Tasks that involve PDF

Example prompts

  • “/resume-builder”

Workflow steps

4 steps, taken from the first numbered list in SKILL.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。

What it can do on your machine

Read from SKILL.md and the folder at commit be31ae8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Resume Builder loads about 862 tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 36 tokens; SKILL.md has 173 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~862
With references · SKILL.md plus every file in references/, read only if the agent opens them
~14k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from StoneLL1/resume-builder at commit be31ae8, republished under its MIT licence (© StoneLL1). 173 words, ~862 tokens.

Download SKILL.mdSave it as .claude/skills/resume-builder/SKILL.md (or your agent's skills folder). This skill also uses 369 other files; get the full folder from GitHub.
name
resume-builder
description
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。

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。

© StoneLL1, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 369 other files (scripts, references, assets) in the repository root of StoneLL1/resume-builder.

  • SKILL.md
  • .gitattributes
  • .gitignore
  • INSTALL.md
  • LICENSE
  • README.en.md
  • README.md
  • assets/runtime-NOTICES.md
  • assets/runtime-manifest.json
  • assets/screenshots/README.md
  • assets/screenshots/editor.png
  • assets/screenshots/facts.png
  • assets/screenshots/gallery-en.png
  • assets/screenshots/gallery-zh.png
  • assets/screenshots/inline-edit.png
  • assets/templates/.shared/bindings.typ
  • assets/templates/.shared/english-bindings.typ
  • … and 353 more

Open the folder on GitHubat commit be31ae8

Compare with similar skills

Resume Builder next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Resume Builder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Resume Builder this skillStoneLL1/resume-builder109—~862Automated safety check: PassMIT
Application OptimiserZal4DW/career-helper110—~2.8kAutomated safety check: PassCustom licence
Tailor Resumeandrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-501—~1.2kAutomated safety check: PassMIT
Resume Skillyanliudesign/offer-toolkit-skill520—~1.1kAutomated safety check: PassMIT
Resume Optimizersundial-org/awesome-openclaw-skills663—~1.2kAutomated safety check: PassNone
Ectheory Submissionfranklee16/academic-research-skills2231 repos~1.2kAutomated safety check: PassNone

Similar skills

  • Application Optimiser

    Zal4DW/career-helper

    A skill your agent uses when the user is applying for a specific role and wants help with the application itself, such as tailoring or fixing a CV for ATS, researching the company and role, planning…

    110 GitHub stars~2.8k tokensUpdated 9 days ago
    Business, Finance & HRAuto-check passed
  • Tailor Resume

    andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-

    Generate an ATS-optimized resume tailored to a specific job posting.

    501 GitHub stars~1.2k tokensUpdated 2 mo ago
    Business, Finance & HRAuto-check passed
  • Resume Skill

    yanliudesign/offer-toolkit-skill

    简历生成与美化。两种入口:把已有简历(PDF/Word/文本)解析、诊断、套用模板美化;或者还没有简历时,通过 LinkedIn 导入或一问一答的对话帮你从零建出一份。输出单页打印优化的 HTML(浏览器里 Cmd+P 直接存成 PDF),提供 12 套模板,覆盖 ATS 友好、侧栏、衬线、编辑、时间轴与头像版式。关键词:resume, CV, 简历, 美化简历, 做简历, 简历模板…

    520 GitHub stars~1.1k tokensUpdated 9 days ago
    Business, Finance & HRAuto-check passed
  • Resume Optimizer

    sundial-org/awesome-openclaw-skills

    Professional resume builder with PDF export, ATS optimization, and analysis capabilities.

    663 GitHub stars~1.2k tokensUpdated 7 mo ago
    Business, Finance & HRAuto-check passed
  • Ectheory Submission

    franklee16/academic-research-skills

    A skill your agent uses when running the final pre-submission preflight for Econometric Theory (ET) via ScholarOne / Manuscript Central — single embedded-font PDF, single-anonymous (no double-blind…

    223 GitHub starsUsed in 1 repo~1.2k tokens
    Research & ScienceAuto-check passed
  • Cover Letter

    bahayonghang/academic-writing-skills

    Submission cover-letter assistant for existing LaTeX manuscripts.

    497 GitHub stars~2.8k tokensUpdated 11 days ago
    Business, Finance & HRAuto-check passed

Questions about Resume Builder

What does Resume Builder 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。. Resume Builder is an agent skill from StoneLL1/resume-builder.

When should I use Resume Builder?

Resume Builder fits situations like: tasks that involve Resume and CV writing; tasks that involve PDF.

How do I install Resume Builder in Claude Code?

Run `npx skills add StoneLL1/resume-builder --skill resume-builder -a claude-code`. Or copy the skill folder (the StoneLL1/resume-builder repository) into .claude/skills/resume-builder in your project. Claude Code loads it when a task matches its description.

How do I install Resume Builder in Codex?

Run `npx skills add StoneLL1/resume-builder --skill resume-builder -a codex`. Or copy the skill folder (the StoneLL1/resume-builder repository) into .agents/skills/resume-builder in your project. Codex loads it when a task matches its description.

Can I use Resume Builder in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add StoneLL1/resume-builder --skill resume-builder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/resume-builder, .gemini/skills/resume-builder, .github/skills/resume-builder and .opencode/skills/resume-builder in your project.

What does Resume Builder need to run?

SKILL.md names no scripts, command-line tools or credentials: Resume Builder is instructions for the agent only.

Does Resume Builder access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Resume Builder safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Resume Builder use?

Resume Builder is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Resume Builder use?

About 862 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 13k tokens, read only when the agent opens those files.

What are the alternatives to Resume Builder?

Skills that share tags, products or a category with Resume Builder: Application Optimiser (Zal4DW/career-helper, 110 stars), Tailor Resume (andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-, 501 stars), Resume Skill (yanliudesign/offer-toolkit-skill, 520 stars) and Resume Optimizer (sundial-org/awesome-openclaw-skills, 663 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Resume Builder?

StoneLL1 (a GitHub user) maintains it in StoneLL1/resume-builder, which has 109 GitHub stars. The repository was last updated on September 17, 2026.

Source: StoneLL1/resume-builder on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.