{"id":"5ff03664-e4c5-480b-aed3-933caa5aab47","slug":"sputnicyoji-resumex","name":"resume-extractor","description":"HR 简历结构化提取专家。Use when: 需要从简历 (PDF/DOCX/TXT) 中提取 候选人信息、工作经历、教育背景、技能、自我评价、求职意向、资质证书。 适用于: 简历解析、人才数据库构建、候选人搜索、JD匹配、招聘数据分析。 基于 Google LangExtract 算法层重构，针对 HR 场景深度优化。 提供: (1) 7种HR提取类型分类框架 (2) 中文简历Few-shot模板库 (3) 7步后处理管道 (时间标准化/Source Grounding/去重/评分/消歧/关系推断/KG转换) (4) PDF/DOCX文档解析器 (5) SQLite人才数据库+导入/查询/匹配CLI (6) JD-候选人智能匹配 (5维加权评分)。 仅需 PyMuPDF + python-docx，无需外部 API。","canonicalUrl":"https://www.xpersona.co/skill/sputnicyoji-resumex","sourceUrl":"https://github.com/sputnicyoji/resumeX","homepage":null,"source":"GITHUB_OPENCLEW","vendor":{"slug":"sputnicyoji","label":"Sputnicyoji","url":"https://github.com/sputnicyoji/resumeX"},"protocols":["OPENCLEW"],"capabilities":[],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-04-14T22:26:45.554Z","freshnessLabel":"Apr 14, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"Apr 14, 2026"},{"label":"Vendor","value":"Sputnicyoji"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"Unpublished"}],"factsPreview":[{"factKey":"docs_crawl","category":"integration","label":"Crawlable docs","value":"6 indexed pages on the official domain","href":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceUrl":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceType":"search_document","confidence":"medium","observedAt":"2026-04-15T05:03:46.393Z","isPublic":true},{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Sputnicyoji","href":"https://github.com/sputnicyoji/resumeX","sourceUrl":"https://github.com/sputnicyoji/resumeX","sourceType":"profile","confidence":"medium","observedAt":"2026-04-14T22:26:45.554Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/sputnicyoji-resumex/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/sputnicyoji-resumex/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-04-14T22:26:45.554Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"1 GitHub stars","href":"https://github.com/sputnicyoji/resumeX","sourceUrl":"https://github.com/sputnicyoji/resumeX","sourceType":"profile","confidence":"medium","observedAt":"2026-04-14T22:26:45.554Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/sputnicyoji-resumex/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/sputnicyoji-resumex/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["1 GitHub stars","Trust evidence available"],"agentCard":{"name":"resume-extractor","description":"HR 简历结构化提取专家。Use when: 需要从简历 (PDF/DOCX/TXT) 中提取 候选人信息、工作经历、教育背景、技能、自我评价、求职意向、资质证书。 适用于: 简历解析、人才数据库构建、候选人搜索、JD匹配、招聘数据分析。 基于 Google LangExtract 算法层重构，针对 HR 场景深度优化。 提供: (1) 7种HR提取类型分类框架 (2) 中文简历Few-shot模板库 (3) 7步后处理管道 (时间标准化/Source Grounding/去重/评分/消歧/关系推断/KG转换) (4) PDF/DOCX文档解析器 (5) SQLite人才数据库+导入/查询/匹配CLI (6) JD-候选人智能匹配 (5维加权评分)。 仅需 PyMuPDF + python-docx，无需外部 API。","source":"GITHUB_OPENCLEW","sourceId":"github:1153428039","repository":"https://github.com/sputnicyoji/resumeX","documentation":"https://www.xpersona.co/skill/sputnicyoji-resumex/agent/sputnicyoji-resumex","protocols":["OPENCLEW"],"languages":["typescript"],"install":{"command":"git clone https://github.com/sputnicyoji/resumeX.git","ecosystem":"git"},"examples":[{"kind":"example","language":"text","snippet":"我需要处理简历?\n    |\n    +-- 输入格式是什么?\n    |   +-- .pdf       --> python parse.py --input resume.pdf --output resume.md\n    |   +-- .docx/.doc --> python parse.py --input resume.docx --output resume.md\n    |   +-- .txt/.md   --> 直接使用，无需解析\n    |\n    +-- Step 1: 解析为纯文本 (parse.py)\n    |\n    +-- Step 2: 选择预设 (resume.json)\n    |\n    +-- Step 3: Claude 提取 (7种HR类型，按 Few-shot 模板)\n    |\n    +-- Step 4: 运行后处理管道 (pipeline.py)\n    |\n    +-- Step 5: 导入数据库 (import_resume.py)\n    |   +-- 单文件: --input result.json\n    |   +-- 批量:   --input-dir ./results/\n    |\n    +-- Step 6: 查询 / 匹配\n        +-- 搜索:  python query.py search \"Python 北京\"\n        +-- 统计:  python query.py stats --by skill\n        +-- 详情:  python query.py detail 1\n        +-- JD匹配: python match.py --jd jd.txt --top 10"},{"kind":"example","language":"bash","snippet":"# 单文件\npython scripts/parse.py --input resume.pdf --output resume.md\n\n# 批量模式\npython scripts/parse.py --input-dir ./resumes/ --output-dir ./parsed/"}]}}