Skip to content
Back to search

yotta-resume

SkillWorks with Claude CodeGitHub

"元简 — 本地求职者简历诊断、分析、修改与成品导出技能:分析简历结构、经历证据、量化指标、岗位匹配和风险,向用户追问缺失事实,给出逐条合理化修改建议,并把确认后的内容导出为 DOCX/PDF。触发:简历诊断、简历分析、改简历、简历追问、JD匹配、导出Word/PDF。边界:不编造经历,不承诺ATS、面试或Offer结果;不自动投递;不处理复杂设计作品集排版;默认本地处理且不联网。"

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/yottameta--yotta-resume/badge.svg)](/listings/yottameta--yotta-resume)

HTML

<a href="/listings/yottameta--yotta-resume"><img src="/api/listings/yottameta--yotta-resume/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Choose one of the methods below. Skill files are distributed through **npm**; GitHub hosts source code and issues.

Method 1: npm one-liner (recommended)

npx -y @yottameta/yotta-resume --agent <agent-name>
npx -y @yottameta/yotta-resume --dir <agent-skills-dir>

- `--agent <name>` installs to that agent's default user-level skills directory. - `--dir <path>` installs to a specified skills directory. - `--list` shows supported agent defaults. - If a China mirror has not synced the package, append `--registry=https://registry.npmjs.org/`.

Method 2: git clone

git clone https://github.com/YottaMeta/yotta-resume.git <agent-skills-dir>/yotta-resume

Method 3: Download ZIP

Download the ZIP from `YottaMeta/yotta-resume`, then move the `yotta-resume` folder into your agent skills directory.

Method 4: install.sh

bash install.sh --agent <agent-name>
bash install.sh --dir <skills-dir>
bash install.sh --list

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

SKILL.md · Manifest · 116 lines
  1. ---
  2. name: yotta-resume
  3. description: "元简 — 本地求职者简历诊断、分析、修改与成品导出技能:分析简历结构、经历证据、量化指标、岗位匹配和风险,向用户追问缺失事实,给出逐条合理化修改建议,并把确认后的内容导出为 DOCX/PDF。触发:简历诊断、简历分析、改简历、简历追问、JD匹配、导出Word/PDF。边界:不编造经历,不承诺ATS、面试或Offer结果;不自动投递;不处理复杂设计作品集排版;默认本地处理且不联网。"
  4. version: 0.1.3
  5. license: MIT
  6. metadata:
  7. zh_name: "元简"
  8. ---
  9. # 元简(yotta-resume)
  10. 元简先根据简历内容自动识别行业,再分析结构、经历证据和 JD 关键词覆盖,
  11. 提出可回答的高价值问题,并按用户确认的事实导出 DOCX、HTML 或 PDF。
  12. ## 触发与边界
  13. - Triggers:用户要求诊断简历、改简历、补强经历证据、做 JD 匹配,或把已确认的简历导出为 Word/PDF。
  14. - Do NOT trigger:用户要求代投简历、编造经历或数字、预测面试结果、评估受保护个人属性,或制作复杂设计作品集排版。
  15. 常见自然语言说法:
  16. - “帮我看下这份安全运营简历哪里写虚了。”
  17. - “照这个 JD 看我还缺哪些关键词和证据。”
  18. - “先别改,告诉我还需要问我什么。”
  19. - “把确认后的内容导成 Word 和 PDF。”
  20. - “这段经历我只能确认范围,不能确认具体数字,应该怎么写?”
  21. 相近但不适用:“帮我海投”“把结果写成 90 分”“编一段大厂经历”“替我预测 Offer”。
  22. ## 核心流程
  23. 1. 首次安装或排查环境时先运行:
  24. ```bash
  25. python scripts/yotta_resume.py doctor
  26. ```
  27. `doctor` 会检查随包文件、数据契约、PyMuPDF、PDF 浏览器、临时目录和 Python 版本。
  28. PDF 依赖是可选项:缺少时仍可使用 Markdown / DOCX 输入和 DOCX / HTML 输出。
  29. 2. 读取简历文件。支持 UTF-8 Markdown、UTF-8 文本、DOCX 和文字层 PDF。
  30. PDF 解析优先使用本地 PyMuPDF;缺少依赖、加密、损坏或扫描件时明确失败或降级,
  31. 不生成伪完整报告。
  32. 3. 运行分析,优先让用户提供目标岗位 JD:
  33. ```bash
  34. python scripts/yotta_resume.py audit --resume resume.md --jd jd.txt --format json
  35. ```
  36. 4. 阅读 `source_manifest`、`parse_warnings`、`issues`、`unknowns` 和 `questions`。
  37. 先确认输入解析质量、规模、个人边界、结果、日期和 JD 缺口,再修改简历。
  38. 用户没有确认的事实不要写进简历。
  39. 5. 按用户确认的信息修改 Markdown,再导出成品:
  40. ```bash
  41. python scripts/yotta_resume.py export --input revised.md --docx revised.docx --html revised.html --pdf revised.pdf
  42. ```
  43. 6. 核对输出文件存在且可打开。多格式导出会先写入临时区,全部成功后一次性提交;
  44. 任一格式失败时不会留下本次部分成品,也不会覆盖原有同名文件。
  45. PDF 依赖本机 Chromium、Chrome 或 Edge;未找到浏览器时命令会明确失败,不会生成伪 PDF。
  46. 7. 需要单独校验随包岗位族、证据账本、题库、来源和双角色权限契约时运行:
  47. ```bash
  48. python scripts/yotta_resume.py contracts --format json
  49. ```
  50. ## 输出契约
  51. - `audit`:JSON 或 Markdown,包含文件来源清单、解析提示、行业识别、章节识别、
  52. 要点统计、工具发现、未知项、追问、修改建议、JD 匹配、结构准备度和边界声明。
  53. - `export`:DOCX / HTML / PDF。三者来自同一份 Markdown 内容模型,联系方式保留在成品简历中。
  54. - `contracts`:离线校验 `data/` 下的 6 个实际契约与 6 个 JSON Schema,
  55. 失败返回退出码 `6`,不写文件、不联网。
  56. - `doctor`:返回 `PASS / WARN / FAIL`,核心文件或契约失败返回退出码 `6`;
  57. PyMuPDF 或浏览器缺失只记为 `WARN`,不阻断 DOCX / HTML 路径。
  58. - 分析报告:手机号和邮箱会被打码;不承诺 ATS、面试或 Offer 结果。
  59. ## 评分与数字护栏
  60. - `readiness.score` 的展示名称固定为“结构准备度(规则分)”,
  61. `score_type` 为 `structure_rule_score`,只反映章节、量化证据、文本清洁度和
  62. 可选 JD 关键词覆盖,不是招聘方评分。
  63. - 只能原样引用工具返回的数值;**不得改写为其他数值、主观数字区间或“实际分数”**。
  64. 需要对招聘方视角作判断时,只允许定性标签并列出简历证据。
  65. - 未提供 JD 时 `jd_match.coverage` 必须为 `null`,报告写明不能判断岗位匹配。
  66. - `jd_match` 使用版本化固定词表,只检查明确关键词,不做语义匹配或岗位排名;
  67. 必须同时展示 `lexicon_version` 和 `limitations`。
  68. - 报告必须区分“工具规则发现”“智能体复核发现”“待用户确认事实”。
  69. 智能体额外发现不得冒充工具输出,且必须引用简历原文或来源页。
  70. - 规则不能判断招聘竞争力、面试通过率或 Offer 结果;必须列入 `unknowns`。
  71. ## 行业扩展
  72. - `industry_detection` 根据简历明确关键词识别行业,只使用可见内容,不读取受保护属性。
  73. - 当前可区分网络安全、软件研发、数据与人工智能、业务运营和通用兜底。
  74. - 网络安全已有 6 个岗位族和 18 道种子题;其他行业暂用通用证据与追问维度。
  75. - 新增行业时扩展 `data/industry-registry.json` 及 Schema,不需要修改主分析流程。
  76. - 多个行业信号接近时 `status=ambiguous`,不得自行猜测行业。
  77. ## 渐进披露
  78. - 详细输入格式、CLI 退出码和浏览器要求见 [references/usage.md](references/usage.md)。
  79. - 常见问题见 [references/faq.md](references/faq.md)。
  80. - 自然语言说法见 [references/trigger-examples.md](references/trigger-examples.md)。
  81. - 端到端工作流见 [references/workflow-examples.md](references/workflow-examples.md)。
  82. - 行业、岗位族、题库、来源与 HR 权限契约见 [references/data-contracts.md](references/data-contracts.md)。
  83. ## 自检
  84. ```bash
  85. python scripts/yotta_resume.py doctor
  86. ```
  87. 源码仓库维护者运行完整自动化测试;测试文件不作为终端用户运行前提。
README.md · README · 122 lines
  1. <p align="center"><b>Language</b>: English · <a href="./README.zh-CN.md">中文</a></p>
  2. <p align="center"><img src="./assets/banner.png" alt="yotta-resume banner" /></p>
  3. <h1 align="center">yotta-resume · Yuan Jian</h1>
  4. <p align="center">Analyze a resume locally, ask for missing evidence, suggest factual improvements, and export DOCX/PDF.</p>
  5. <p align="center">
  6. <a href="LICENSE"><img alt="License: MIT" src="https://img.shields.io/badge/license-MIT-blue" /></a>
  7. <a href="https://www.npmjs.com/package/@yottameta/yotta-resume"><img alt="npm package" src="https://img.shields.io/npm/v/@yottameta/yotta-resume" /></a>
  8. <a href="https://github.com/YottaMeta/yotta-resume"><img alt="GitHub stars" src="https://img.shields.io/github/stars/YottaMeta/yotta-resume" /></a>
  9. </p>
  10. ## What it is
  11. yotta-resume is a job-seeker resume analysis and export tool. It reads Markdown,
  12. UTF-8 text, DOCX, and text-layer PDF resumes, detects an industry from visible resume
  13. content, identifies sections, experience bullets, metrics, contact information, and
  14. JD keyword gaps, then returns high-value questions and improvement suggestions.
  15. After the job seeker confirms the facts, the same resume can be exported to DOCX,
  16. HTML, or PDF.
  17. The core analyzer uses the Python standard library. It makes no network requests,
  18. does not submit resumes, and never invents experience or numbers. PDF input uses
  19. local PyMuPDF and fails clearly when the dependency is missing or the file cannot
  20. be parsed.
  21. ## When to use
  22. - Review resume structure, evidence, and measurable outcomes.
  23. - Compare a resume with a target job description.
  24. - Prepare focused follow-up questions for missing facts.
  25. - Export a confirmed resume as DOCX/PDF.
  26. **Do not use it** to submit applications, fabricate experience, predict interviews or offers, evaluate protected personal attributes, or create complex design portfolios.
  27. ## Quick usage
  28. ```bash
  29. # Check the installed package and optional PDF capabilities
  30. python scripts/yotta_resume.py doctor
  31. # Analyze a resume and print a Markdown report
  32. python scripts/yotta_resume.py audit --resume resume.md
  33. # Analyze a text-layer PDF directly
  34. python scripts/yotta_resume.py audit --resume resume.pdf
  35. # Analyze with a JD and output JSON
  36. python scripts/yotta_resume.py audit --resume resume.md --jd jd.txt --format json
  37. # Export DOCX, HTML, and PDF
  38. python scripts/yotta_resume.py export --input revised.md --docx revised.docx --html revised.html --pdf revised.pdf
  39. # Validate role, question-bank, source, ledger, and dual-role contracts offline
  40. python scripts/yotta_resume.py contracts --format json
  41. ```
  42. PDF export requires a local Chromium, Chrome, or Edge browser. PDF input requires
  43. `pip install pymupdf`. Missing browsers, missing PDF dependencies, encrypted files,
  44. and image-only PDFs fail clearly instead of producing a misleading result.
  45. Multi-format export renders into a temporary area and commits only after every
  46. requested format succeeds, so a failed PDF does not leave new DOCX/HTML partial files.
  47. The `readiness.score` field is a structural rule score only. It is not a recruiter
  48. score. When no JD is provided, job-match coverage is `null`. JD matching uses a
  49. versioned fixed vocabulary and reports its limitations; it is not semantic matching
  50. or a hiring recommendation.
  51. Industry detection uses a versioned registry. Cybersecurity currently has the
  52. detailed role map and seed question bank; future industries can be added by extending
  53. `data/industry-registry.json` and its schema without changing the main analysis flow.
  54. See [references/usage.md](references/usage.md) for input format, fields, and exit codes.
  55. See [references/faq.md](references/faq.md) for common questions.
  56. See [references/data-contracts.md](references/data-contracts.md) for the bundled data contracts.
  57. ## Installation
  58. Choose one of the methods below. Skill files are distributed through **npm**; GitHub hosts source code and issues.
  59. ### Method 1: npm one-liner (recommended)
  60. ```text
  61. npx -y @yottameta/yotta-resume --agent <agent-name>
  62. npx -y @yottameta/yotta-resume --dir <agent-skills-dir>
  63. ```
  64. - `--agent <name>` installs to that agent's default user-level skills directory.
  65. - `--dir <path>` installs to a specified skills directory.
  66. - `--list` shows supported agent defaults.
  67. - If a China mirror has not synced the package, append `--registry=https://registry.npmjs.org/`.
  68. ### Method 2: git clone
  69. ```text
  70. git clone https://github.com/YottaMeta/yotta-resume.git <agent-skills-dir>/yotta-resume
  71. ```
  72. ### Method 3: Download ZIP
  73. Download the ZIP from `YottaMeta/yotta-resume`, then move the `yotta-resume` folder into your agent skills directory.
  74. ### Method 4: install.sh
  75. ```text
  76. bash install.sh --agent <agent-name>
  77. bash install.sh --dir <skills-dir>
  78. bash install.sh --list
  79. ```
  80. ## Validation
  81. Run `python scripts/yotta_resume.py doctor` after installation. It checks the bundled
  82. contracts, required files, optional PDF backends, browser availability, temporary
  83. directory access, and Python version. Full development tests live in the source
  84. repository and are not required to use the installed skill.
  85. ## License
  86. MIT © YottaMeta — see [LICENSE](./LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.