{"id":"a5a99200-26a3-4a50-b94e-04133d78ff59","entityType":"agent","slug":"clawhub-tuobadaidai-resume-to-tags","name":"Resume To Tags","canonicalUrl":"https://www.xpersona.co/agent/clawhub-tuobadaidai-resume-to-tags","canonicalPath":"/agent/clawhub-tuobadaidai-resume-to-tags","generatedAt":"2026-10-11T21:00:21.953Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T16:39:27.416Z","emptyReason":null},"description":"从简历到纯标签矩阵的完整流程。接受简历文本/文件 → LLM 提取原子标签（含近义词扩展） → 创建飞书多维表格（多选标签字段） → 批量录入候选人 → 清理空白行列 → 输出可搜索的人才标签库。当用户提供简历并要求\"生成标签矩阵\"、\"人才标签库\"、\"简历转表格\"、\"候选人打标\"时使用。 Skill: Resume To Tags Owner: tuobadaidai Summary: 从简历到纯标签矩阵的完整流程。接受简历文本/文件 → LLM 提取原子标签（含近义词扩展） → 创建飞书多维表格（多选标签字段） → 批量录入候选人 → 清理空白行列 → 输出可搜索的人才标签库。当用户提供简历并要求\"生成标签矩阵\"、\"人才标签库\"、\"简历转表格\"、\"候选人打标\"时使用。 Tags: latest:1.0.1 Version history: v1.0.1 | 2026-07-24T09:18:59.707Z | user Restore from backup - resume to tags matrix workflow v1.0.0 | 2026-04-23T11:00:22.257Z | user 简历到纯标签矩阵的完整流程，含近义词扩展 Archive index: Archive v1.0.1: 5","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s171s30jbmhtrc2kxbr4hxmyn583gsk3:resume-to-tags","sourceUrl":"https://clawhub.ai/tuobadaidai/resume-to-tags","homepage":"https://clawhub.ai/tuobadaidai/skills/resume-to-tags","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/tuobadaidai/resume-to-tags","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/tuobadaidai/skills/resume-to-tags","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"从简历到纯标签矩阵的完整流程。接受简历文本/文件 → LLM 提取原子标签（含近义词扩展） → 创建飞书多维表格（多选标签字段） → 批量录入候选人 → 清理空白行列 → 输出可搜索的人才标签库。当用户提供简历并要求\"生成标签矩阵\"、\"人才标签库\"、\"简历转表格\"、\"候选人打标\"时使用。 Skill: Resume T"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T16:39:27.416Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T16:39:27.416Z","emptyReason":null},"stars":null,"forks":null,"downloads":1026,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.1","tractionLabel":"1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T16:39:27.237Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T16:39:27.416Z","lastCrawledAt":"2026-10-11T16:39:27.237Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T16:39:27.237Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.1","createdAt":"2026-07-24T09:18:59.707Z","changelog":"Restore from backup - resume to tags matrix workflow","fileCount":5,"zipByteSize":9885},{"version":"1.0.0","createdAt":"2026-04-23T11:00:22.257Z","changelog":"简历到纯标签矩阵的完整流程，含近义词扩展","fileCount":5,"zipByteSize":9881}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s171s30jbmhtrc2kxbr4hxmyn583gsk3:resume-to-tags","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-tuobadaidai-resume-to-tags/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-tuobadaidai-resume-to-tags/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-tuobadaidai-resume-to-tags/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-tuobadaidai-resume-to-tags/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-tuobadaidai-resume-to-tags/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-tuobadaidai-resume-to-tags/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T21:00:21.952Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-tuobadaidai-resume-to-tags/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-tuobadaidai-resume-to-tags/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-tuobadaidai-resume-to-tags/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-tuobadaidai-resume-to-tags/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T16:39:27.416Z","emptyReason":null},"readme":"Skill: Resume To Tags\n\nOwner: tuobadaidai\n\nSummary: 从简历到纯标签矩阵的完整流程。接受简历文本/文件 → LLM 提取原子标签（含近义词扩展） → 创建飞书多维表格（多选标签字段） → 批量录入候选人 → 清理空白行列 → 输出可搜索的人才标签库。当用户提供简历并要求\"生成标签矩阵\"、\"人才标签库\"、\"简历转表格\"、\"候选人打标\"时使用。\n\nTags: latest:1.0.1\n\nVersion history:\n\nv1.0.1 | 2026-07-24T09:18:59.707Z | user\n\nRestore from backup - resume to tags matrix workflow\n\nv1.0.0 | 2026-04-23T11:00:22.257Z | user\n\n简历到纯标签矩阵的完整流程，含近义词扩展\n\nArchive index:\n\nArchive v1.0.1: 5 files, 9885 bytes\n\nFiles: references/synonyms.json (6797b), scripts/extract_tags.py (4215b), skill-card.md (2172b), SKILL.md (6099b), _meta.json (133b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: resume-to-tags\ndescription: 从简历到纯标签矩阵的完整流程。接受简历文本/文件 → LLM 提取原子标签（含近义词扩展） → 创建飞书多维表格（多选标签字段） → 批量录入候选人 → 清理空白行列 → 输出可搜索的人才标签库。当用户提供简历并要求\"生成标签矩阵\"、\"人才标签库\"、\"简历转表格\"、\"候选人打标\"时使用。\n---\n\n# Resume-to-Tags — 简历到纯标签矩阵\n\n从简历提取原子标签，构建可搜索、可匹配的人才标签矩阵。\n\n## 核心设计理念\n\n**描述 → 标签**：将简历中的描述性内容拆解为标准化原子标签，使人才匹配 = 标签重合度计算。\n\n### 标签拆解规则\n\n| 维度 | 原始描述 | 拆解标签 |\n|------|---------|---------|\n| 院校 | 香港城市大学 | `海外` `硕士` `QS前100` `社科` |\n| 院校 | 同济大学 | `本科` `985` `211` `理工科` |\n| 院校 | 清华大学 | `本科` `C9` `985` `211` |\n| 公司 | 携程集团 | `大厂` `OTA` `旅游` `上市公司` |\n| 公司 | 京东集团 | `大厂` `电商` `上市公司` |\n| 公司 | 明略科技 | `AI创业` |\n| 技能 | LLMOps/RAG链路优化 | `LLMOps` `RAG` `LLM应用` |\n| 技能 | 大模型知识库 | `RAG` `知识库` `LLM应用` |\n\n## 完整工作流\n\n### Step 1: 标签提取\n\n从简历文本提取原子标签，输出标准 JSON。\n\n```bash\npython3 skills/resume-to-tags/scripts/extract_tags.py --text \"简历内容...\"\n```\n\n或读取文件：\n```bash\npython3 skills/resume-to-tags/scripts/extract_tags.py --file resume.txt\n```\n\n### Step 2: 近义词扩展\n\n提取后自动扩充近义词标签，提高匹配覆盖率。近义词映射表见 `references/synonyms.json`。\n\n### Step 3: 创建多维表格\n\n使用飞书工具创建表格结构：\n1. 创建应用：`feishu_bitable_app` (action=create)\n2. 重命名默认表：`feishu_bitable_app_table` (action=patch)\n3. 重命名主字段为\"姓名\"：`feishu_bitable_app_table_field` (action=update, fldFdaHuOL)\n4. 创建 7 个多选标签字段 + 1 个数字字段：\n\n| 字段名 | 类型 | 说明 |\n|--------|------|------|\n| 姓名 | 文本(1) | 主键 |\n| 院校标签 | 多选(4) | 985/211/C9/QS前100/海外/本科/硕士... |\n| 公司标签 | 多选(4) | 大厂/OTA/电商/AI创业/外企/旅游... |\n| 技能标签 | 多选(4) | RAG/Agent/招聘管理/数据分析... |\n| 工具标签 | 多选(4) | LangChain/Dify/SQL/SPSS... |\n| 领域标签 | 多选(4) | AI/LLM/HR/BD/产品/咨询... |\n| 语言标签 | 多选(4) | 中文母语/英语工作/日语... |\n| 证书标签 | 多选(4) | 初级经济师/CET6/N3... |\n| 工作年限 | 数字(2) | 总经验年数 |\n\n5. 删除默认空白字段（单选 fld21nkFl6、日期 fld8rfpQsc、附件 fld84GszEh）：\n `feishu_bitable_app_table_field` (action=delete)\n\n### Step 4: 录入候选人\n\n批量插入记录：`feishu_bitable_app_table_record` (action=batch_create)\n\nMultiSelect 字段的值会自动创建新选项（无需预定义）。\n\n### Step 5: 清理空白行列\n\n删除默认空白列：\n```\nfeishu_bitable_app_table_field: delete fld21nkFl6 (单选)\nfeishu_bitable_app_table_field: delete fld8rfpQsc (日期)\nfeishu_bitable_app_table_field: delete fld84GszEh (附件)\n```\n\n## 标签分类体系\n\n### 院校标签\n`985` `211` `双一流` `C9` `G5` `常春藤` `QS前50` `QS前100` `QS前200` `海外` `本科` `硕士` `博士` `理工科` `社科` `商科` `在职教育`\n\n### 公司标签\n`大厂` `互联网` `OTA` `旅游` `电商` `金融` `AI创业` `外企` `国企` `上市公司` `独角兽` `ToB` `ToC` `本地生活` `支付` `物流` `制造` `咨询` `教育` `医疗` `游戏` `社交` `内容` `SaaS`\n\n### 技能标签（含近义词映射）\n\n| 标准标签 | 近义词/变体 |\n|---------|-----------|\n| RAG | 检索增强生成、大模型知识库、RAG链路优化 |\n| Agent | 智能体、Agentic Workflow、AI Agent |\n| LLM应用 | 大模型应用、LLM应用开发 |\n| 微服务 | 微服务架构、分布式架构 |\n| 高并发 | 高并发架构、高并发异步处理 |\n| Prompt | Prompt Engineering、提示词工程 |\n| 数据分析 | 数据清洗、回归分析、统计分析 |\n| 人才寻源 | 人才搜寻、Sourcing |\n| 胜任力模型 | 胜任力画像构建、胜任力模型 |\n| 招聘漏斗 | 招聘漏斗分析 |\n| 人才Mapping | 人才地图、Competitor Mapping |\n| 业务拓展 | BD、商务拓展 |\n| 大客户管理 | KA管理、Key Account |\n| OTA运营 | OTA渠道运营 |\n| 市场趋势 | 市场趋势分析 |\n| 收益管理 | 定价策略、Revenue Management |\n| 合同谈判 | 商务谈判 |\n| 客户关系 | 客户关系维护、CRM |\n| 战略规划 | SP/BP、战略规划制定 |\n| 知识萃取 | 知识工程 |\n| 抽象建模 | 系统建模 |\n| 产品架构 | 产品架构设计 |\n| 解决方案 | 解决方案孵化 |\n| 生态合作 | 合作伙伴管理 |\n| AI中台 | AI平台建设、AI中台建设 |\n| 人脸识别 | 人脸技术 |\n| 图像识别 | CV、计算机视觉 |\n| 智能语音 | 语音识别、TTS、ASR |\n| 大数据 | 大数据架构 |\n| NLP | 自然语言处理 |\n\n### 工具标签\n`LangChain` `Dify` `n8n` `OpenClaw` `Pinecone` `Milvus` `MySQL` `Redis` `Kafka` `ClickHouse` `Docker` `K8S` `AWS` `阿里云` `SQL` `SPSS` `Stata` `Pandas` `Excel` `CRM` `OTA平台` `AI中台` `OCR` `猎聘` `LinkedIn`\n\n### 领域标签\n`AI/LLM` `HR/招聘` `BD/销售` `产品` `技术架构` `OTA/旅游` `电商` `金融` `数据分析` `咨询` `教育` `医疗` `游戏` `社交`\n\n### 语言标签\n`中文母语` `英语工作` `英语流利` `日语` `CET6` `托福` `雅思`\n\n### 证书标签\n`初级经济师` `PMP` `CET6` `日语N3` `日语N2` `数学竞赛` `英语专八`\n\n## 人才匹配逻辑\n\n给定岗位需求标签集合 R，候选人标签集合 C：\n- **匹配度** = |R ∩ C| / |R| × 100%\n- 可按匹配度排序推荐候选人\n\n## 相关文件\n\n- `scripts/extract_tags.py` — LLM 标签提取脚本\n- `references/synonyms.json` — 近义词映射表（标准标签 → 变体列表）\n- `references/taxonomy.md` — 完整标签分类体系\n\nFile v1.0.1:_meta.json\n\n{\n \"ownerId\": \"kn70tx725606ywwb5gfj0vpxjx83admr\",\n \"slug\": \"resume-to-tags\",\n \"version\": \"1.0.1\",\n \"publishedAt\": 1784884739707\n}\n\nFile v1.0.1:references/synonyms.json\n\n{\n \"院校近义词\": {\n \"985\": [\"985工程\", \"985高校\"],\n \"211\": [\"211工程\", \"211高校\"],\n \"双一流\": [\"双一流高校\", \"双一流大学\"],\n \"C9\": [\"C9联盟\", \"九校联盟\"],\n \"G5\": [\"G5超级精英大学\", \"英国G5\"],\n \"常春藤\": [\"Ivy League\", \"美国常春藤\"],\n \"QS前50\": [\"QS50\", \"世界前50\"],\n \"QS前100\": [\"QS100\", \"世界前100\", \"百强大学\"],\n \"QS前200\": [\"QS200\", \"世界前200\"],\n \"海外\": [\"留学\", \"境外\", \"港澳台\"],\n \"本科\": [\"学士\", \"大学本科\", \"BSc\", \"BA\"],\n \"硕士\": [\"研究生\", \"硕士研究生\", \"MSc\", \"MA\"],\n \"博士\": [\"博士研究生\", \"PhD\", \"Doctor\"],\n \"理工科\": [\"理工\", \"工科\", \"STEM\"],\n \"社科\": [\"社会科学\", \"人文社科\"],\n \"商科\": [\"商科\", \"Business\", \"MBA\"],\n \"在职教育\": [\"在职\", \"在职攻读\", \"非全日制\"]\n },\n \"公司近义词\": {\n \"大厂\": [\"头部大厂\", \"互联网大厂\", \"一线大厂\", \"BAT\", \"字节\", \"阿里\", \"腾讯\", \"美团\", \"拼多多\"],\n \"互联网\": [\"Internet\", \"网络\"],\n \"OTA\": [\"在线旅游\", \"Online Travel\"],\n \"旅游\": [\"旅游业\", \"Travel\", \"商旅\", \"酒店\"],\n \"电商\": [\"电子商务\", \"E-commerce\", \"零售电商\"],\n \"金融\": [\"FinTech\", \"金融科技\", \"银行\", \"保险\", \"证券\", \"支付\"],\n \"AI创业\": [\"AI创业公司\", \"人工智能创业\", \"AI Startup\"],\n \"外企\": [\"外资\", \"Foreign\", \"跨国公司\", \"MNC\"],\n \"国企\": [\"央企\", \"国有企业\", \"SOE\"],\n \"上市公司\": [\"上市\", \"Public Company\"],\n \"独角兽\": [\"Unicorn\", \"估值超10亿\"],\n \"ToB\": [\"B2B\", \"企业服务\", \"企业级\"],\n \"ToC\": [\"B2C\", \"消费者\"],\n \"本地生活\": [\"O2O\", \"本地生活服务\"],\n \"物流\": [\"快递\", \"仓储\", \"供应链\"],\n \"制造\": [\"制造业\", \"Manufacturing\", \"工厂\"],\n \"咨询\": [\"Consulting\", \"管理咨询\"],\n \"教育\": [\"EdTech\", \"培训\", \"学校\"],\n \"医疗\": [\"HealthTech\", \"医药\", \"医院\"],\n \"游戏\": [\"Gaming\", \"手游\", \"网游\"],\n \"社交\": [\"Social\", \"社交平台\"],\n \"内容\": [\"Content\", \"媒体\", \"短视频\", \"直播\"],\n \"SaaS\": [\"Software as a Service\", \"软件服务\"]\n },\n \"技能近义词\": {\n \"RAG\": [\"检索增强生成\", \"大模型知识库\", \"RAG链路优化\", \"Retrieval-Augmented Generation\"],\n \"Agent\": [\"智能体\", \"Agentic Workflow\", \"AI Agent\", \"自主Agent\"],\n \"LLM应用\": [\"大模型应用\", \"LLM应用开发\", \"大语言模型应用\"],\n \"LLMOps\": [\"LLM运维\", \"大模型运维\", \"MLOps\"],\n \"Prompt\": [\"Prompt Engineering\", \"提示词工程\", \"提示工程\"],\n \"微服务\": [\"微服务架构\", \"分布式架构\", \"Microservices\"],\n \"高并发\": [\"高并发架构\", \"高并发异步处理\", \"高可用\"],\n \"流控降级\": [\"限流降级\", \"熔断\", \"Circuit Breaker\"],\n \"向量检索\": [\"Vector Search\", \"向量数据库\", \"语义检索\"],\n \"语义缓存\": [\"Semantic Cache\", \"语义缓存优化\"],\n \"ROI评估\": [\"投资回报评估\", \"ROI分析\"],\n \"知识萃取\": [\"知识工程\", \"Knowledge Engineering\"],\n \"抽象建模\": [\"系统建模\", \"System Modeling\"],\n \"Java\": [\"JVM\", \"Spring\", \"Spring Boot\"],\n \"Python\": [\"Py\", \"Python开发\"],\n \"Go\": [\"Golang\"],\n \"数据分析\": [\"数据清洗\", \"回归分析\", \"统计分析\", \"描述性统计\", \"数据挖掘\"],\n \"人才寻源\": [\"人才搜寻\", \"Sourcing\", \"被动候选人寻访\"],\n \"胜任力模型\": [\"胜任力画像构建\", \"Competency Model\", \"能力模型\"],\n \"招聘漏斗\": [\"招聘漏斗分析\", \"招聘转化分析\"],\n \"人才Mapping\": [\"人才地图\", \"Competitor Mapping\", \"人才竞争分析\"],\n \"招聘管理\": [\"招聘\", \"Recruiting\", \"人才获取\"],\n \"薪酬核算\": [\"薪酬管理\", \"Compensation\", \"薪资计算\"],\n \"工作流自动化\": [\"流程自动化\", \"Workflow\", \"RPA\"],\n \"业务拓展\": [\"BD\", \"商务拓展\", \"Business Development\"],\n \"大客户管理\": [\"KA管理\", \"Key Account\", \"大客户\"],\n \"区域管理\": [\"区域运营\", \"大区管理\"],\n \"OTA运营\": [\"OTA渠道运营\", \"OTA平台运营\"],\n \"市场趋势\": [\"市场趋势分析\", \"市场分析\"],\n \"团队管理\": [\"团队搭建\", \"Team Management\"],\n \"收益管理\": [\"定价策略\", \"Revenue Management\", \"收益优化\"],\n \"合同谈判\": [\"商务谈判\", \"Negotiation\"],\n \"客户关系\": [\"客户关系维护\", \"CRM\", \"客户成功\"],\n \"战略规划\": [\"SP/BP\", \"战略规划制定\", \"Strategic Planning\"],\n \"产品架构\": [\"产品架构设计\", \"产品规划\"],\n \"解决方案\": [\"解决方案孵化\", \"Solution Design\"],\n \"生态合作\": [\"合作伙伴管理\", \"生态建设\"],\n \"AI中台\": [\"AI平台建设\", \"AI中台建设\", \"AI Platform\"],\n \"人脸识别\": [\"人脸技术\", \"Face Recognition\"],\n \"图像识别\": [\"CV\", \"计算机视觉\", \"Computer Vision\"],\n \"智能语音\": [\"语音识别\", \"TTS\", \"ASR\", \"NLP语音\"],\n \"大数据\": [\"大数据架构\", \"Big Data\"],\n \"NLP\": [\"自然语言处理\", \"Natural Language Processing\"],\n \"OCR\": [\"文字识别\", \"光学字符识别\"]\n },\n \"工具近义词\": {\n \"LangChain\": [\"Langchain\"],\n \"Dify\": [\"Dify平台\"],\n \"n8n\": [\"N8N\"],\n \"MySQL\": [\"Mysql\", \"MySQL数据库\"],\n \"Redis\": [\"redis\", \"Redis缓存\"],\n \"Kafka\": [\"消息队列\", \"Kafka消息\"],\n \"Docker\": [\"容器化\", \"Docker容器\"],\n \"K8S\": [\"Kubernetes\", \"K8s\"],\n \"AWS\": [\"Amazon Web Services\"],\n \"阿里云\": [\"Alibaba Cloud\", \"AliCloud\"],\n \"Excel\": [\"Microsoft Excel\", \"Excel表格\"],\n \"SPSS\": [\"SPSS统计\"],\n \"Stata\": [\"Stata统计\"],\n \"SQL\": [\"SQL查询\", \"数据库\"],\n \"Pandas\": [\"pandas\"],\n \"CRM\": [\"客户关系管理系统\"],\n \"OCR\": [\"OCR引擎\"]\n },\n \"领域近义词\": {\n \"AI/LLM\": [\"人工智能\", \"大模型\", \"AIGC\", \"生成式AI\", \"大语言模型\"],\n \"HR/招聘\": [\"人力资源\", \"人才管理\", \"People Operations\"],\n \"BD/销售\": [\"销售\", \"商务\", \"Revenue\"],\n \"OTA/旅游\": [\"在线旅游\", \"Travel Tech\", \"商旅\"],\n \"技术架构\": [\"架构\", \"Architecture\", \"技术\"],\n \"数据分析\": [\"Data\", \"BI\", \"数据科学\"]\n },\n \"语言近义词\": {\n \"中文母语\": [\"中文\", \"普通话\", \"Mandarin\", \"Native Chinese\"],\n \"英语工作\": [\"英语\", \"English\", \"工作英语\", \"英语熟练\"],\n \"英语流利\": [\"英语精通\", \"Fluent English\", \"英语口语流利\"],\n \"日语\": [\"Japanese\", \"日文\"],\n \"CET6\": [\"大学英语六级\", \"CET-6\"],\n \"日语N3\": [\"JLPT N3\", \"日语三级\"],\n \"日语N2\": [\"JLPT N2\", \"日语二级\"]\n },\n \"证书近义词\": {\n \"初级经济师\": [\"经济师初级\"],\n \"PMP\": [\"项目管理专业人士\", \"Project Management Professional\"],\n \"CET6\": [\"大学英语六级\"],\n \"日语N3\": [\"JLPT N3\"],\n \"日语N2\": [\"JLPT N2\"]\n }\n}\n\nFile v1.0.1:skill-card.md\n\n## Description:\n\nResume To Tags helps agents turn resume text or files into normalized talent tags, expand synonyms, and structure the results for a searchable Feishu talent tag table.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[tuobadaidai](https://clawhub.ai/user/tuobadaidai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nRecruiters, sourcers, and HR operations teams use this skill to extract standardized candidate tags from resumes and create a searchable Feishu talent tag matrix for matching roles to candidates.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill processes resumes and may expose sensitive candidate data, including contact details and employment history.\n\nMitigation: Use only resumes you are allowed to process, avoid retaining unnecessary contact details, and apply the organization's candidate-data handling policy before sharing outputs.\n\nRisk: LLM-generated tags can be inaccurate, overbroad, or biased if imported without review.\n\nMitigation: Review and validate extracted tags against source resumes before using them for screening, matching, or Feishu import.\n\nRisk: The workflow can create, delete, or batch-import Feishu table fields and records.\n\nMitigation: Confirm the target Feishu app and table, then inspect planned create, delete, and batch import actions before execution.\n\n## Reference(s):\n\n- [Synonym mapping reference](references/synonyms.json)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, JSON, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with JSON tag extraction output and shell command examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May involve Feishu table creation and batch record import when the agent has appropriate tool access.]\n\n## Skill Version(s):\n\n1.0.1 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.0: 5 files, 9881 bytes\n\nFiles: references/synonyms.json (6797b), scripts/extract_tags.py (4215b), skill-card.md (2231b), SKILL.md (6099b), _meta.json (133b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: resume-to-tags\ndescription: 从简历到纯标签矩阵的完整流程。接受简历文本/文件 → LLM 提取原子标签（含近义词扩展） → 创建飞书多维表格（多选标签字段） → 批量录入候选人 → 清理空白行列 → 输出可搜索的人才标签库。当用户提供简历并要求\"生成标签矩阵\"、\"人才标签库\"、\"简历转表格\"、\"候选人打标\"时使用。\n---\n\n# Resume-to-Tags — 简历到纯标签矩阵\n\n从简历提取原子标签，构建可搜索、可匹配的人才标签矩阵。\n\n## 核心设计理念\n\n**描述 → 标签**：将简历中的描述性内容拆解为标准化原子标签，使人才匹配 = 标签重合度计算。\n\n### 标签拆解规则\n\n| 维度 | 原始描述 | 拆解标签 |\n|------|---------|---------|\n| 院校 | 香港城市大学 | `海外` `硕士` `QS前100` `社科` |\n| 院校 | 同济大学 | `本科` `985` `211` `理工科` |\n| 院校 | 清华大学 | `本科` `C9` `985` `211` |\n| 公司 | 携程集团 | `大厂` `OTA` `旅游` `上市公司` |\n| 公司 | 京东集团 | `大厂` `电商` `上市公司` |\n| 公司 | 明略科技 | `AI创业` |\n| 技能 | LLMOps/RAG链路优化 | `LLMOps` `RAG` `LLM应用` |\n| 技能 | 大模型知识库 | `RAG` `知识库` `LLM应用` |\n\n## 完整工作流\n\n### Step 1: 标签提取\n\n从简历文本提取原子标签，输出标准 JSON。\n\n```bash\npython3 skills/resume-to-tags/scripts/extract_tags.py --text \"简历内容...\"\n```\n\n或读取文件：\n```bash\npython3 skills/resume-to-tags/scripts/extract_tags.py --file resume.txt\n```\n\n### Step 2: 近义词扩展\n\n提取后自动扩充近义词标签，提高匹配覆盖率。近义词映射表见 `references/synonyms.json`。\n\n### Step 3: 创建多维表格\n\n使用飞书工具创建表格结构：\n1. 创建应用：`feishu_bitable_app` (action=create)\n2. 重命名默认表：`feishu_bitable_app_table` (action=patch)\n3. 重命名主字段为\"姓名\"：`feishu_bitable_app_table_field` (action=update, fldFdaHuOL)\n4. 创建 7 个多选标签字段 + 1 个数字字段：\n\n| 字段名 | 类型 | 说明 |\n|--------|------|------|\n| 姓名 | 文本(1) | 主键 |\n| 院校标签 | 多选(4) | 985/211/C9/QS前100/海外/本科/硕士... |\n| 公司标签 | 多选(4) | 大厂/OTA/电商/AI创业/外企/旅游... |\n| 技能标签 | 多选(4) | RAG/Agent/招聘管理/数据分析... |\n| 工具标签 | 多选(4) | LangChain/Dify/SQL/SPSS... |\n| 领域标签 | 多选(4) | AI/LLM/HR/BD/产品/咨询... |\n| 语言标签 | 多选(4) | 中文母语/英语工作/日语... |\n| 证书标签 | 多选(4) | 初级经济师/CET6/N3... |\n| 工作年限 | 数字(2) | 总经验年数 |\n\n5. 删除默认空白字段（单选 fld21nkFl6、日期 fld8rfpQsc、附件 fld84GszEh）：\n `feishu_bitable_app_table_field` (action=delete)\n\n### Step 4: 录入候选人\n\n批量插入记录：`feishu_bitable_app_table_record` (action=batch_create)\n\nMultiSelect 字段的值会自动创建新选项（无需预定义）。\n\n### Step 5: 清理空白行列\n\n删除默认空白列：\n```\nfeishu_bitable_app_table_field: delete fld21nkFl6 (单选)\nfeishu_bitable_app_table_field: delete fld8rfpQsc (日期)\nfeishu_bitable_app_table_field: delete fld84GszEh (附件)\n```\n\n## 标签分类体系\n\n### 院校标签\n`985` `211` `双一流` `C9` `G5` `常春藤` `QS前50` `QS前100` `QS前200` `海外` `本科` `硕士` `博士` `理工科` `社科` `商科` `在职教育`\n\n### 公司标签\n`大厂` `互联网` `OTA` `旅游` `电商` `金融` `AI创业` `外企` `国企` `上市公司` `独角兽` `ToB` `ToC` `本地生活` `支付` `物流` `制造` `咨询` `教育` `医疗` `游戏` `社交` `内容` `SaaS`\n\n### 技能标签（含近义词映射）\n\n| 标准标签 | 近义词/变体 |\n|---------|-----------|\n| RAG | 检索增强生成、大模型知识库、RAG链路优化 |\n| Agent | 智能体、Agentic Workflow、AI Agent |\n| LLM应用 | 大模型应用、LLM应用开发 |\n| 微服务 | 微服务架构、分布式架构 |\n| 高并发 | 高并发架构、高并发异步处理 |\n| Prompt | Prompt Engineering、提示词工程 |\n| 数据分析 | 数据清洗、回归分析、统计分析 |\n| 人才寻源 | 人才搜寻、Sourcing |\n| 胜任力模型 | 胜任力画像构建、胜任力模型 |\n| 招聘漏斗 | 招聘漏斗分析 |\n| 人才Mapping | 人才地图、Competitor Mapping |\n| 业务拓展 | BD、商务拓展 |\n| 大客户管理 | KA管理、Key Account |\n| OTA运营 | OTA渠道运营 |\n| 市场趋势 | 市场趋势分析 |\n| 收益管理 | 定价策略、Revenue Management |\n| 合同谈判 | 商务谈判 |\n| 客户关系 | 客户关系维护、CRM |\n| 战略规划 | SP/BP、战略规划制定 |\n| 知识萃取 | 知识工程 |\n| 抽象建模 | 系统建模 |\n| 产品架构 | 产品架构设计 |\n| 解决方案 | 解决方案孵化 |\n| 生态合作 | 合作伙伴管理 |\n| AI中台 | AI平台建设、AI中台建设 |\n| 人脸识别 | 人脸技术 |\n| 图像识别 | CV、计算机视觉 |\n| 智能语音 | 语音识别、TTS、ASR |\n| 大数据 | 大数据架构 |\n| NLP | 自然语言处理 |\n\n### 工具标签\n`LangChain` `Dify` `n8n` `OpenClaw` `Pinecone` `Milvus` `MySQL` `Redis` `Kafka` `ClickHouse` `Docker` `K8S` `AWS` `阿里云` `SQL` `SPSS` `Stata` `Pandas` `Excel` `CRM` `OTA平台` `AI中台` `OCR` `猎聘` `LinkedIn`\n\n### 领域标签\n`AI/LLM` `HR/招聘` `BD/销售` `产品` `技术架构` `OTA/旅游` `电商` `金融` `数据分析` `咨询` `教育` `医疗` `游戏` `社交`\n\n### 语言标签\n`中文母语` `英语工作` `英语流利` `日语` `CET6` `托福` `雅思`\n\n### 证书标签\n`初级经济师` `PMP` `CET6` `日语N3` `日语N2` `数学竞赛` `英语专八`\n\n## 人才匹配逻辑\n\n给定岗位需求标签集合 R，候选人标签集合 C：\n- **匹配度** = |R ∩ C| / |R| × 100%\n- 可按匹配度排序推荐候选人\n\n## 相关文件\n\n- `scripts/extract_tags.py` — LLM 标签提取脚本\n- `references/synonyms.json` — 近义词映射表（标准标签 → 变体列表）\n- `references/taxonomy.md` — 完整标签分类体系\n\nFile v1.0.0:_meta.json\n\n{\n \"ownerId\": \"kn70tx725606ywwb5gfj0vpxjx83admr\",\n \"slug\": \"resume-to-tags\",\n \"version\": \"1.0.0\",\n \"publishedAt\": 1776942022257\n}\n\nFile v1.0.0:references/synonyms.json\n\n{\n \"院校近义词\": {\n \"985\": [\"985工程\", \"985高校\"],\n \"211\": [\"211工程\", \"211高校\"],\n \"双一流\": [\"双一流高校\", \"双一流大学\"],\n \"C9\": [\"C9联盟\", \"九校联盟\"],\n \"G5\": [\"G5超级精英大学\", \"英国G5\"],\n \"常春藤\": [\"Ivy League\", \"美国常春藤\"],\n \"QS前50\": [\"QS50\", \"世界前50\"],\n \"QS前100\": [\"QS100\", \"世界前100\", \"百强大学\"],\n \"QS前200\": [\"QS200\", \"世界前200\"],\n \"海外\": [\"留学\", \"境外\", \"港澳台\"],\n \"本科\": [\"学士\", \"大学本科\", \"BSc\", \"BA\"],\n \"硕士\": [\"研究生\", \"硕士研究生\", \"MSc\", \"MA\"],\n \"博士\": [\"博士研究生\", \"PhD\", \"Doctor\"],\n \"理工科\": [\"理工\", \"工科\", \"STEM\"],\n \"社科\": [\"社会科学\", \"人文社科\"],\n \"商科\": [\"商科\", \"Business\", \"MBA\"],\n \"在职教育\": [\"在职\", \"在职攻读\", \"非全日制\"]\n },\n \"公司近义词\": {\n \"大厂\": [\"头部大厂\", \"互联网大厂\", \"一线大厂\", \"BAT\", \"字节\", \"阿里\", \"腾讯\", \"美团\", \"拼多多\"],\n \"互联网\": [\"Internet\", \"网络\"],\n \"OTA\": [\"在线旅游\", \"Online Travel\"],\n \"旅游\": [\"旅游业\", \"Travel\", \"商旅\", \"酒店\"],\n \"电商\": [\"电子商务\", \"E-commerce\", \"零售电商\"],\n \"金融\": [\"FinTech\", \"金融科技\", \"银行\", \"保险\", \"证券\", \"支付\"],\n \"AI创业\": [\"AI创业公司\", \"人工智能创业\", \"AI Startup\"],\n \"外企\": [\"外资\", \"Foreign\", \"跨国公司\", \"MNC\"],\n \"国企\": [\"央企\", \"国有企业\", \"SOE\"],\n \"上市公司\": [\"上市\", \"Public Company\"],\n \"独角兽\": [\"Unicorn\", \"估值超10亿\"],\n \"ToB\": [\"B2B\", \"企业服务\", \"企业级\"],\n \"ToC\": [\"B2C\", \"消费者\"],\n \"本地生活\": [\"O2O\", \"本地生活服务\"],\n \"物流\": [\"快递\", \"仓储\", \"供应链\"],\n \"制造\": [\"制造业\", \"Manufacturing\", \"工厂\"],\n \"咨询\": [\"Consulting\", \"管理咨询\"],\n \"教育\": [\"EdTech\", \"培训\", \"学校\"],\n \"医疗\": [\"HealthTech\", \"医药\", \"医院\"],\n \"游戏\": [\"Gaming\", \"手游\", \"网游\"],\n \"社交\": [\"Social\", \"社交平台\"],\n \"内容\": [\"Content\", \"媒体\", \"短视频\", \"直播\"],\n \"SaaS\": [\"Software as a Service\", \"软件服务\"]\n },\n \"技能近义词\": {\n \"RAG\": [\"检索增强生成\", \"大模型知识库\", \"RAG链路优化\", \"Retrieval-Augmented Generation\"],\n \"Agent\": [\"智能体\", \"Agentic Workflow\", \"AI Agent\", \"自主Agent\"],\n \"LLM应用\": [\"大模型应用\", \"LLM应用开发\", \"大语言模型应用\"],\n \"LLMOps\": [\"LLM运维\", \"大模型运维\", \"MLOps\"],\n \"Prompt\": [\"Prompt Engineering\", \"提示词工程\", \"提示工程\"],\n \"微服务\": [\"微服务架构\", \"分布式架构\", \"Microservices\"],\n \"高并发\": [\"高并发架构\", \"高并发异步处理\", \"高可用\"],\n \"流控降级\": [\"限流降级\", \"熔断\", \"Circuit Breaker\"],\n \"向量检索\": [\"Vector Search\", \"向量数据库\", \"语义检索\"],\n \"语义缓存\": [\"Semantic Cache\", \"语义缓存优化\"],\n \"ROI评估\": [\"投资回报评估\", \"ROI分析\"],\n \"知识萃取\": [\"知识工程\", \"Knowledge Engineering\"],\n \"抽象建模\": [\"系统建模\", \"System Modeling\"],\n \"Java\": [\"JVM\", \"Spring\", \"Spring Boot\"],\n \"Python\": [\"Py\", \"Python开发\"],\n \"Go\": [\"Golang\"],\n \"数据分析\": [\"数据清洗\", \"回归分析\", \"统计分析\", \"描述性统计\", \"数据挖掘\"],\n \"人才寻源\": [\"人才搜寻\", \"Sourcing\", \"被动候选人寻访\"],\n \"胜任力模型\": [\"胜任力画像构建\", \"Competency Model\", \"能力模型\"],\n \"招聘漏斗\": [\"招聘漏斗分析\", \"招聘转化分析\"],\n \"人才Mapping\": [\"人才地图\", \"Competitor Mapping\", \"人才竞争分析\"],\n \"招聘管理\": [\"招聘\", \"Recruiting\", \"人才获取\"],\n \"薪酬核算\": [\"薪酬管理\", \"Compensation\", \"薪资计算\"],\n \"工作流自动化\": [\"流程自动化\", \"Workflow\", \"RPA\"],\n \"业务拓展\": [\"BD\", \"商务拓展\", \"Business Development\"],\n \"大客户管理\": [\"KA管理\", \"Key Account\", \"大客户\"],\n \"区域管理\": [\"区域运营\", \"大区管理\"],\n \"OTA运营\": [\"OTA渠道运营\", \"OTA平台运营\"],\n \"市场趋势\": [\"市场趋势分析\", \"市场分析\"],\n \"团队管理\": [\"团队搭建\", \"Team Management\"],\n \"收益管理\": [\"定价策略\", \"Revenue Management\", \"收益优化\"],\n \"合同谈判\": [\"商务谈判\", \"Negotiation\"],\n \"客户关系\": [\"客户关系维护\", \"CRM\", \"客户成功\"],\n \"战略规划\": [\"SP/BP\", \"战略规划制定\", \"Strategic Planning\"],\n \"产品架构\": [\"产品架构设计\", \"产品规划\"],\n \"解决方案\": [\"解决方案孵化\", \"Solution Design\"],\n \"生态合作\": [\"合作伙伴管理\", \"生态建设\"],\n \"AI中台\": [\"AI平台建设\", \"AI中台建设\", \"AI Platform\"],\n \"人脸识别\": [\"人脸技术\", \"Face Recognition\"],\n \"图像识别\": [\"CV\", \"计算机视觉\", \"Computer Vision\"],\n \"智能语音\": [\"语音识别\", \"TTS\", \"ASR\", \"NLP语音\"],\n \"大数据\": [\"大数据架构\", \"Big Data\"],\n \"NLP\": [\"自然语言处理\", \"Natural Language Processing\"],\n \"OCR\": [\"文字识别\", \"光学字符识别\"]\n },\n \"工具近义词\": {\n \"LangChain\": [\"Langchain\"],\n \"Dify\": [\"Dify平台\"],\n \"n8n\": [\"N8N\"],\n \"MySQL\": [\"Mysql\", \"MySQL数据库\"],\n \"Redis\": [\"redis\", \"Redis缓存\"],\n \"Kafka\": [\"消息队列\", \"Kafka消息\"],\n \"Docker\": [\"容器化\", \"Docker容器\"],\n \"K8S\": [\"Kubernetes\", \"K8s\"],\n \"AWS\": [\"Amazon Web Services\"],\n \"阿里云\": [\"Alibaba Cloud\", \"AliCloud\"],\n \"Excel\": [\"Microsoft Excel\", \"Excel表格\"],\n \"SPSS\": [\"SPSS统计\"],\n \"Stata\": [\"Stata统计\"],\n \"SQL\": [\"SQL查询\", \"数据库\"],\n \"Pandas\": [\"pandas\"],\n \"CRM\": [\"客户关系管理系统\"],\n \"OCR\": [\"OCR引擎\"]\n },\n \"领域近义词\": {\n \"AI/LLM\": [\"人工智能\", \"大模型\", \"AIGC\", \"生成式AI\", \"大语言模型\"],\n \"HR/招聘\": [\"人力资源\", \"人才管理\", \"People Operations\"],\n \"BD/销售\": [\"销售\", \"商务\", \"Revenue\"],\n \"OTA/旅游\": [\"在线旅游\", \"Travel Tech\", \"商旅\"],\n \"技术架构\": [\"架构\", \"Architecture\", \"技术\"],\n \"数据分析\": [\"Data\", \"BI\", \"数据科学\"]\n },\n \"语言近义词\": {\n \"中文母语\": [\"中文\", \"普通话\", \"Mandarin\", \"Native Chinese\"],\n \"英语工作\": [\"英语\", \"English\", \"工作英语\", \"英语熟练\"],\n \"英语流利\": [\"英语精通\", \"Fluent English\", \"英语口语流利\"],\n \"日语\": [\"Japanese\", \"日文\"],\n \"CET6\": [\"大学英语六级\", \"CET-6\"],\n \"日语N3\": [\"JLPT N3\", \"日语三级\"],\n \"日语N2\": [\"JLPT N2\", \"日语二级\"]\n },\n \"证书近义词\": {\n \"初级经济师\": [\"经济师初级\"],\n \"PMP\": [\"项目管理专业人士\", \"Project Management Professional\"],\n \"CET6\": [\"大学英语六级\"],\n \"日语N3\": [\"JLPT N3\"],\n \"日语N2\": [\"JLPT N2\"]\n }\n}\n\nFile v1.0.0:skill-card.md\n\n## Description:
\nResume-to-Tags turns resume text or files into a searchable candidate tag matrix by generating an LLM extraction prompt, expanding tags with synonyms, and guiding Feishu Bitable record creation.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[tuobadaidai](https://clawhub.ai/user/tuobadaidai)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nRecruiters, HR teams, and talent operations users can use this skill to standardize resumes into atomic school, company, skill, tool, domain, language, certificate, and experience tags for search and candidate matching. It also guides creation of a Feishu Bitable candidate tag database.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Resume inputs and generated outputs can contain candidate contact details and raw resume content.
\nMitigation: Use only resumes the operator is authorized to process, redact contact details before sharing outputs, and apply retention and access controls for candidate data.
\nRisk: The workflow can write candidate records into a Feishu Bitable workspace.
\nMitigation: Confirm the exact Feishu workspace, app, table, and access permissions before creating or batch-inserting records.
\n\n\n## Reference(s):
\n- [ClawHub release page](https://clawhub.ai/tuobadaidai/resume-to-tags)
\n- [references/synonyms.json](references/synonyms.json)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, JSON, shell commands, configuration, guidance]
\n**Output Format:** [Markdown guidance with shell command examples and JSON extraction output]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Generated extraction prompts may include resume excerpts up to 5000 characters and basic contact details detected from the input.]
\n\n## Skill Version(s):
\n1.0.0 (source: server release evidence)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
","readmeExcerpt":"Skill: Resume To Tags Owner: tuobadaidai Summary: 从简历到纯标签矩阵的完整流程。接受简历文本/文件 → LLM 提取原子标签（含近义词扩展） → 创建飞书多维表格（多选标签字段） → 批量录入候选人 → 清理空白行列 → 输出可搜索的人才标签库。当用户提供简历并要求\"生成标签矩阵\"、\"人才标签库\"、\"简历转表格\"、\"候选人打标\"时使用。 Tags: latest:1.0.1 Version history: v1.0.1 | 2026-07-24T09:18:59.707Z | user Restore from backup - resume to tags matrix workflow v1.0.0 | 2026-04-23T11:00:22.257Z | user 简历到纯标签矩阵的完整流程，含近义词扩展 Archive index: Archive v1.0.1: 5 ","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"python3 skills/resume-to-tags/scripts/extract_tags.py --text \"简历内容...\""},{"language":"bash","snippet":"python3 skills/resume-to-tags/scripts/extract_tags.py --file resume.txt"},{"language":"text","snippet":"feishu_bitable_app_table_field: delete fld21nkFl6 (单选)\nfeishu_bitable_app_table_field: delete fld8rfpQsc (日期)\nfeishu_bitable_app_table_field: delete fld84GszEh (附件)"},{"language":"bash","snippet":"python3 skills/resume-to-tags/scripts/extract_tags.py --text \"简历内容...\""},{"language":"bash","snippet":"python3 skills/resume-to-tags/scripts/extract_tags.py --file resume.txt"},{"language":"text","snippet":"feishu_bitable_app_table_field: delete fld21nkFl6 (单选)\nfeishu_bitable_app_table_field: delete fld8rfpQsc (日期)\nfeishu_bitable_app_table_field: delete fld84GszEh (附件)"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: resume-to-tags\ndescription: 从简历到纯标签矩阵的完整流程。接受简历文本/文件 → LLM 提取原子标签（含近义词扩展） → 创建飞书多维表格（多选标签字段） → 批量录入候选人 → 清理空白行列 → 输出可搜索的人才标签库。当用户提供简历并要求\"生成标签矩阵\"、\"人才标签库\"、\"简历转表格\"、\"候选人打标\"时使用。\n---\n\n# Resume-to-Tags — 简历到纯标签矩阵\n\n从简历提取原子标签，构建可搜索、可匹配的人才标签矩阵。\n\n## 核心设计理念\n\n**描述 → 标签**：将简历中的描述性内容拆解为标准化原子标签，使人才匹配 = 标签重合度计算。\n\n### 标签拆解规则\n\n| 维度 | 原始描述 | 拆解标签 |\n|------|---------|---------|\n| 院校 | 香港城市大学 | `海外` `硕士` `QS前100` `社科` |\n| 院校 | 同济大学 | `本科` `985` `211` `理工科` |\n| 院校 | 清华大学 | `本科` `C9` `985` `211` |\n| 公司 | 携程集团 | `大厂` `OTA` `旅游` `上市公司` |\n| 公司 | 京东集团 | `大厂` `电商` `上市公司` |\n| 公司 | 明略科技 | `AI创业` |\n| 技能 | LLMOps/RAG链路优化 | `LLMOps` `RAG` `LLM应用` |\n| 技能 | 大模型知识库 | `RAG` `知识库` `LLM应用` |\n\n## 完整工作流\n\n### Step 1: 标签提取\n\n从简历文本提取原子标签，输出标准 JSON。\n\n```bash\npython3 skills/resume-to-tags/scripts/extract_tags.py --text \"简历内容...\"\n```\n\n或读取文件：\n```bash\npython3 skills/resume-to-tags/scripts/extract_tags.py --file resume.txt\n```\n\n### Step 2: 近义词扩展\n\n提取后自动扩充近义词标签，提高匹配覆盖率。近义词映射表见 `references/synonyms.json`。\n\n### Step 3: 创建多维表格\n\n使用飞书工具创建表格结构：\n1. 创建应用：`feishu_bitable_app` (action=create)\n2. 重命名默认表：`feishu_bitable_app_table` (action=patch)\n3. 重命名主字段为\"姓名\"：`feishu_bitable_app_table_field` (action=update, fldFdaHuOL)\n4. 创建 7 个多选标签字段 + 1 个数字字段：\n\n| 字段名 | 类型 | 说明 |\n|--------|------|------|\n| 姓名 | 文本(1) | 主键 |\n| 院校标签 | 多选(4) | 985/211/C9/QS前100/海外/本科/硕士... |\n| 公司标签 | 多选(4) | 大厂/OTA/电商/AI创业/外企/旅游... |\n| 技能标签 | 多选(4) | RAG/Agent/招聘管理/数据分析... |\n| 工具标签 | 多选(4) | LangChain/Dify/SQL/SPSS... |\n| 领域标签 | 多选(4) | AI/LLM/HR/BD/产品/咨询... |\n| 语言标签 | 多选(4) | 中文母语/英语工作/日语... |\n| 证书标签 | 多选(4) | 初级经济师/CET6/N3... |\n| 工作年限 | 数字(2) | 总经验年数 |\n\n5. 删除默认空白字段（单选 fld21nkFl6、日期 fld8rfpQsc、附件 fld84GszEh）：\n `feishu_bitable_app_table_field` (action=delete)\n\n### Step 4: 录入候选人\n\n批量插入记录：`feishu_bitable_app_table_record` (action=batch_create)\n\nMultiSelect 字段的值会自动创建新选项（无需预定义）。\n\n### Step 5: 清理空白行列\n\n删除默认空白列：\n```\nfeishu_bitable_app_table_field: delete fld21nkFl6 (单选)\nfeishu_bitable_app_table_field: delete fld8rfpQsc (日期)\nfeishu_bitable_app_table_field: delete fld84GszEh (附件)\n```\n\n## 标签分类体系\n\n### 院校标签\n`985` `211` `双一流` `C9` `G5` `常春藤` `QS前50` `QS前100` `QS前200` `海外` `本科` `硕士` `博士` `理工科` `社科` `商科` `在职教育`\n\n### 公司标签\n`大厂` `互联网` `OTA` `旅游` `电商` `金融` `AI创业` `外企` `国企` `上市公司` `独角兽` `ToB` `ToC` `本地生活` `支付` `物流` `制造` `咨询` `教育` `医疗` `游戏` `社交` `内容` `SaaS`\n\n### 技能标签（含近义词映射）\n\n| 标准标签 | 近义词/变体 |\n|---------|-----------|\n| RAG | 检索增强生成、大模型知识库、RAG链路优化 |\n| Agent | 智能体、Agentic Workflow、AI Agent |\n| LLM应用 | 大模型应用、LLM应用开发 |\n| 微服务 | 微服务架构、分布式架构 |\n| 高并发 | 高并发架构、高并发异步处理 |\n| Prompt | Prompt Engineering、提示词工程 |\n| 数据分析 | 数据清洗、回归分析、统计分析 |\n| 人才寻源 | 人才搜寻、Sourcing |\n| 胜任力模型 | 胜任力画像构建、胜任力模型 |\n| 招聘漏斗 | 招聘漏斗分析 |\n| 人才Mapping | 人才地图、Competitor Mapping |\n| 业务拓展 | BD、商务拓展 |\n| 大客户管理 | KA管理、Key Account |\n| OTA运营 | OTA渠道运营 |\n| 市场趋势 | 市场趋势分析 |\n| 收益管理 | 定价策略、Revenue Management |\n| 合同谈判 | 商务谈判 |\n| 客户关系 | 客户关系维护、CRM |\n| 战略规划 | SP/BP、战略规划制定 |\n| 知识萃取 | 知识工程 |\n| 抽象建模 | 系统建模 |\n| 产品架构 | 产品架构设计 |\n| 解决方案 | 解决方案孵化 |\n| 生态合作 | 合作伙伴管理 |\n| AI中台 | AI平台建设、AI中台建设 |\n| 人脸识别 | 人脸技术 |\n| 图像识别 | CV、计算机视觉 |\n| "},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn70tx725606ywwb5gfj0vpxjx83admr\",\n \"slug\": \"resume-to-tags\",\n \"version\": \"1.0.1\",\n \"publishedAt\": 1784884739707\n}"},{"path":"references/synonyms.json","content":"{\n \"院校近义词\": {\n \"985\": [\"985工程\", \"985高校\"],\n \"211\": [\"211工程\", \"211高校\"],\n \"双一流\": [\"双一流高校\", \"双一流大学\"],\n \"C9\": [\"C9联盟\", \"九校联盟\"],\n \"G5\": [\"G5超级精英大学\", \"英国G5\"],\n \"常春藤\": [\"Ivy League\", \"美国常春藤\"],\n \"QS前50\": [\"QS50\", \"世界前50\"],\n \"QS前100\": [\"QS100\", \"世界前100\", \"百强大学\"],\n \"QS前200\": [\"QS200\", \"世界前200\"],\n \"海外\": [\"留学\", \"境外\", \"港澳台\"],\n \"本科\": [\"学士\", \"大学本科\", \"BSc\", \"BA\"],\n \"硕士\": [\"研究生\", \"硕士研究生\", \"MSc\", \"MA\"],\n \"博士\": [\"博士研究生\", \"PhD\", \"Doctor\"],\n \"理工科\": [\"理工\", \"工科\", \"STEM\"],\n \"社科\": [\"社会科学\", \"人文社科\"],\n \"商科\": [\"商科\", \"Business\", \"MBA\"],\n \"在职教育\": [\"在职\", \"在职攻读\", \"非全日制\"]\n },\n \"公司近义词\": {\n \"大厂\": [\"头部大厂\", \"互联网大厂\", \"一线大厂\", \"BAT\", \"字节\", \"阿里\", \"腾讯\", \"美团\", \"拼多多\"],\n \"互联网\": [\"Internet\", \"网络\"],\n \"OTA\": [\"在线旅游\", \"Online Travel\"],\n \"旅游\": [\"旅游业\", \"Travel\", \"商旅\", \"酒店\"],\n \"电商\": [\"电子商务\", \"E-commerce\", \"零售电商\"],\n \"金融\": [\"FinTech\", \"金融科技\", \"银行\", \"保险\", \"证券\", \"支付\"],\n \"AI创业\": [\"AI创业公司\", \"人工智能创业\", \"AI Startup\"],\n \"外企\": [\"外资\", \"Foreign\", \"跨国公司\", \"MNC\"],\n \"国企\": [\"央企\", \"国有企业\", \"SOE\"],\n \"上市公司\": [\"上市\", \"Public Company\"],\n \"独角兽\": [\"Unicorn\", \"估值超10亿\"],\n \"ToB\": [\"B2B\", \"企业服务\", \"企业级\"],\n \"ToC\": [\"B2C\", \"消费者\"],\n \"本地生活\": [\"O2O\", \"本地生活服务\"],\n \"物流\": [\"快递\", \"仓储\", \"供应链\"],\n \"制造\": [\"制造业\", \"Manufacturing\", \"工厂\"],\n \"咨询\": [\"Consulting\", \"管理咨询\"],\n \"教育\": [\"EdTech\", \"培训\", \"学校\"],\n \"医疗\": [\"HealthTech\", \"医药\", \"医院\"],\n \"游戏\": [\"Gaming\", \"手游\", \"网游\"],\n \"社交\": [\"Social\", \"社交平台\"],\n \"内容\": [\"Content\", \"媒体\", \"短视频\", \"直播\"],\n \"SaaS\": [\"Software as a Service\", \"软件服务\"]\n },\n \"技能近义词\": {\n \"RAG\": [\"检索增强生成\", \"大模型知识库\", \"RAG链路优化\", \"Retrieval-Augmented Generation\"],\n \"Agent\": [\"智能体\", \"Agentic Workflow\", \"AI Agent\", \"自主Agent\"],\n \"LLM应用\": [\"大模型应用\", \"LLM应用开发\", \"大语言模型应用\"],\n \"LLMOps\": [\"LLM运维\", \"大模型运维\", \"MLOps\"],\n \"Prompt\": [\"Prompt Engineering\", \"提示词工程\", \"提示工程\"],\n \"微服务\": [\"微服务架构\", \"分布式架构\", \"Microservices\"],\n \"高并发\": [\"高并发架构\", \"高并发异步处理\", \"高可用\"],\n \"流控降级\": [\"限流降级\", \"熔断\", \"Circuit Breaker\"],\n \"向量检索\": [\"Vector Search\", \"向量数据库\", \"语义检索\"],\n \"语义缓存\": [\"Semantic Cache\", \"语义缓存优化\"],\n \"ROI评估\": [\"投资回报评估\", \"ROI分析\"],\n \"知识萃取\": [\"知识工程\", \"Knowledge Engineering\"],\n \"抽象建模\": [\"系统建模\", \"System Modeling\"],\n \"Java\": [\"JVM\", \"Spring\", \"Spring Boot\"],\n \"Python\": [\"Py\", \"Python开发\"],\n \"Go\": [\"Golang\"],\n \"数据分析\": [\"数据清洗\", \"回归分析\", \"统计分析\", \"描述性统计\", \"数据挖掘\"],\n \"人才寻源\": [\"人才搜寻\", \"Sourcing\", \"被动候选人寻访\"],\n \"胜任力模型\": [\"胜任力画像构建\", \"Competency Model\", \"能力模型\"],\n \"招聘漏斗\": [\"招聘漏斗分析\", \"招聘转化分析\"],\n \"人才Mapping\": [\"人才地图\", \"Competitor Mapping\", \"人才竞争分析\"],\n \"招聘管理\": [\"招聘\", \"Recruiting\", \"人才获取\"],\n \"薪酬核算\": [\"薪酬管理\", \"Compensation\", \"薪资计算\"],\n \"工作流自动化\": [\"流程自动化\", \"Workflow\", \"RPA\"],\n \"业务拓展\": [\"BD\", \"商务拓展\", \"Business Development\"],\n \"大客户管理\": [\"KA管理\", \"Key Account\", \"大客户\"],\n \"区域管理\": [\"区域运营\", \"大区管理\"],\n \"OTA运营\": [\"OTA渠道运营\", \"OTA平台运营\"],\n \"市场趋势\": [\"市场趋势分析\", \"市场分析\"],\n \"团队管理\": [\"团队搭建\", \"Team Management\"],\n \"收益管理\": [\"定价策略\", \"Revenue Management\", \"收益优化\"],\n \"合同谈判\": [\"商务谈判\", \"Negotiation\"],\n \"客户关系\": [\"客户关系维护\", \""},{"path":"skill-card.md","content":"## Description:\n\nResume To Tags helps agents turn resume text or files into normalized talent tags, expand synonyms, and structure the results for a searchable Feishu talent tag table.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[tuobadaidai](https://clawhub.ai/user/tuobadaidai)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nRecruiters, sourcers, and HR operations teams use this skill to extract standardized candidate tags from resumes and create a searchable Feishu talent tag matrix for matching roles to candidates.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill processes resumes and may expose sensitive candidate data, including contact details and employment history.\n\nMitigation: Use only resumes you are allowed to process, avoid retaining unnecessary contact details, and apply the organization's candidate-data handling policy before sharing outputs.\n\nRisk: LLM-generated tags can be inaccurate, overbroad, or biased if imported without review.\n\nMitigation: Review and validate extracted tags against source resumes before using them for screening, matching, or Feishu import.\n\nRisk: The workflow can create, delete, or batch-import Feishu table fields and records.\n\nMitigation: Confirm the target Feishu app and table, then inspect planned create, delete, and batch import actions before execution.\n\n## Reference(s):\n\n- [Synonym mapping reference](references/synonyms.json)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, JSON, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown guidance with JSON tag extraction output and shell command examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May involve Feishu table creation and batch record import when the agent has appropriate tool access.]\n\n## Skill Version(s):\n\n1.0.1 (source: server release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"从简历到纯标签矩阵的完整流程。接受简历文本/文件 → LLM 提取原子标签（含近义词扩展） → 创建飞书多维表格（多选标签字段） → 批量录入候选人 → 清理空白行列 → 输出可搜索的人才标签库。当用户提供简历并要求\"生成标签矩阵\"、\"人才标签库\"、\"简历转表格\"、\"候选人打标\"时使用。 Skill: Resume To Tags Owner: tuobadaidai Summary: 从简历到纯标签矩阵的完整流程。接受简历文本/文件 → LLM 提取原子标签（含近义词扩展） → 创建飞书多维表格（多选标签字段） → 批量录入候选人 → 清理空白行列 → 输出可搜索的人才标签库。当用户提供简历并要求\"生成标签矩阵\"、\"人才标签库\"、\"简历转表格\"、\"候选人打标\"时使用。 Tags: latest:1.0.1 Version history: v1.0.1 | 2026-07-24T09:18:59.707Z | user Restore from backup - resume to tags matrix workflow v1.0.0 | 2026-04-23T11:00:22.257Z | user 简历到纯标签矩阵的完整流程，含近义词扩展 Archive index: Archive v1.0.1: 5","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":926,"uniquenessScore":59,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T16:39:27.416Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T16:39:27.416Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T21:00:21.953Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}