[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-PaddlePaddle-paddleocr-doc-parsing-zh-CN":3,"guides-for-PaddlePaddle-paddleocr-doc-parsing":375,"similar-k17bzyrmcvq9pxfc933nmpkjhd86mzkt-zh-CN":376},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":260,"isFallback":251,"parentExtension":266,"providers":267,"relations":273,"repo":276,"tags":371,"workflow":372},1778695287770.3098,"k17bzyrmcvq9pxfc933nmpkjhd86mzkt",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"使用此技能可从 PDF 和文档图像中提取结构化 Markdown/JSON — 表格（精确到单元格）、公式（LaTeX 格式）、图形、印章、图表、页眉/页脚、多栏布局和正确的阅读顺序。触发词：文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表, 阅读顺序; reading order, formula, LaTeX, layout parsing, structure extraction, PP-StructureV3, PaddleOCR-VL.",{"claudeCode":12},"PaddlePaddle/PaddleOCR","PaddleOCR 文档解析","https://github.com/PaddlePaddle/PaddleOCR",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":241,"workflow":258},1778695287770.31,"kn7ab188gpxs0yrtn8hyrs0h6186n6pf","zh-CN",{"checks":20,"evaluatedAt":195,"extensionSummary":196,"features":197,"nonGoals":203,"practices":207,"prerequisites":208,"promptVersionExtension":214,"promptVersionScoring":215,"purpose":216,"rationale":217,"score":218,"summary":219,"tags":220,"tier":229,"useCases":230,"workflow":235},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,114,117,121,124,127,130,133,136,139,143,147,150,153,157,160,163,166,169,173,176,179,182,185,188,192],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","描述清楚地说明了从 PDF 和文档图像中提取结构化数据的需求，并重点介绍了表格、公式和布局等特定元素。",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","该技能利用 PaddleOCR-VL 和 PP-StructureV3 等高级模型进行高精度文档解析，提供的功能超越了基础 OCR，并使其区别于简单的包装器。",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","该技能提供了从输入处理到结构化输出的完整工作流程，包括错误处理和处理大文件的指南，使其能够投入生产使用。",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","该技能专注于从 PDF 和图像中进行文档解析，其范围清晰，不扩展到无关的领域。",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","描述准确地反映了该技能从 PDF 和图像中提取结构化数据的能力，包括特定元素和触发词。",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","这是一个技能，而非工具类扩展，因此没有传统意义上的作用域工具。",{"category":45,"check":46,"severity":24,"summary":47},"Documentation","Configuration & parameter reference","SKILL.md 清楚地概述了 API 配置的环境变量和文件类型等可选参数，并解释了它们的作用。",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","这是一个技能，而非工具类扩展，因此没有传统的工具名称。",{"category":33,"check":52,"severity":24,"summary":53},"Minimal I/O surface","CLI 接口和脚本参数定义明确，接受文件路径/URL 和可选参数等特定输入，并且输出是结构化的 JSON。",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","许可证为 Apache-2.0，在 LICENSE 文件和 SKILL.md 中已明确说明，这是一个宽松的开源许可证。",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","截至 2026-05-13，该存储库显示有近期提交，表明维护活跃。",{"category":59,"check":63,"severity":24,"summary":64},"Dependency Management","项目使用 uv 进行依赖管理，确保依赖项得到有效解析和管理。",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","密钥通过环境变量（PADDLEOCR_ACCESS_TOKEN）处理，而非硬编码，并且技能指导用户进行安全配置。",{"category":66,"check":70,"severity":24,"summary":71},"Injection","脚本将文件路径和 URL 作为数据输入进行处理，没有迹象表明会执行加载的第三方数据中的指令。",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","依赖项通过 uv 进行管理，代码似乎不会在运行时获取外部代码或数据进行执行。",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","脚本在提供的文件路径和 URL 上运行，并且似乎不会修改其指定输出位置或范围之外的文件。",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","脚本似乎不包含分离进程或拒绝操作周围的重试循环等模式。",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","该技能通过环境变量处理带有凭证的 API 调用，并且没有出现读取或将机密数据提交给未记录的第三方等模式。",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","捆绑的文件似乎不包含隐藏文本技巧或恶意 Unicode 字符；描述清晰。",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","Python 脚本使用清晰、可读的代码编写，不包含 base64 编码或 eval 等混淆技术。",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","脚本将文件路径和 URL 作为输入进行处理，并且不假定用户特定的项目组织结构（超出提供的输入之外）。",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","在过去 90 天内有 58 个打开和 60 个关闭的 issue，关闭率很高，表明维护者参与度很高。",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","该项目具有清晰的版本控制策略，具有频繁的发布和更新，如近期提交日期和更改日志条目所示。",{"category":104,"check":105,"severity":24,"summary":106},"Execution","Validation","文件路径、URL 和类型等输入参数在传递给库之前会由脚本的参数解析和内部逻辑进行验证。",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","该技能主要执行只读操作，专注于解析和提取，不执行破坏性操作。",{"category":111,"check":112,"severity":24,"summary":113},"Code Execution","Error Handling","`lib.py` 模块始终返回带有代码和消息的结构化错误字典，并且 CLI 脚本能够妥善处理这些错误。",{"category":111,"check":115,"severity":24,"summary":116},"Logging","该脚本使用 Python 的 logging 模块进行内部操作，并且用户面向的输出根据需要通过 stdout/stderr 进行管理。",{"category":118,"check":119,"severity":24,"summary":120},"Compliance","GDPR","该技能处理用户提供的文档内容，并且本身不处理个人数据（除非用户提交或显式处理文档内容）。",{"category":118,"check":122,"severity":24,"summary":123},"Target market","该技能处理文档，似乎没有任何区域或司法管辖区的限制，因此具有全球适用性。",{"category":92,"check":125,"severity":24,"summary":126},"Runtime stability","该技能依赖于标准的 Python 库和 `uv` 进行依赖管理，确保跨平台兼容性。",{"category":45,"check":128,"severity":24,"summary":129},"README","README 提供了全面的概述、功能、安装和用法示例，清晰地说明了扩展的目的。",{"category":33,"check":131,"severity":42,"summary":132},"Tool surface size","这是一个具有单一入口点的技能，而非工具集合。",{"category":40,"check":134,"severity":42,"summary":135},"Overlapping near-synonym tools","这是一个具有单一入口点的技能，而非具有重叠近义词的工具集合。",{"category":45,"check":137,"severity":24,"summary":138},"Phantom features","所有宣传的功能，如文档解析和输出格式，都直接由提供的脚本和文档支持。",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","SKILL.md 提供了清晰的安装说明，使用 `uv` 和可复制粘贴的用法示例，适用于各种场景。",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","错误会附带代码和可读的消息报告，指导用户解决配置、输入或 API 问题。",{"category":104,"check":148,"severity":24,"summary":149},"Pinned dependencies","依赖项通过 `uv` 进行管理，并指定了特定版本，确保了可重现的构建。",{"category":33,"check":151,"severity":42,"summary":152},"Dry-run preview","该技能主要用于数据提取，不执行需要预览模式的状态更改操作。",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","API 客户端具有可配置的超时设置，并且操作不是状态更改的，因此不会引起重试问题。",{"category":118,"check":158,"severity":24,"summary":159},"Telemetry opt-in","该技能默认似乎不发送任何遥测数据，也没有提及退出机制，符合选择加入的原则。",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","描述清楚地定义了要处理的工件（PDF、文档图像）和任务（提取结构化 Markdown/JSON），并附带了特定的触发词。",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","前言简洁，有效地总结了核心功能，并列出了相关的触发词。",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","SKILL.md 结构良好，包含主要说明，并引用了单独的文档文件（如 `output_schema.md`）。",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","详细的模式信息提供在单独的文件（`references/output_schema.md`）中，展示了渐进式披露。",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","该技能是直接处理工具，不涉及需要分叉上下文的深入探索。",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","SKILL.md 中提供了多个清晰、端到端的用法示例，演示了各种输入方法和输出选项。",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","文档解决了潜在问题，如不支持的格式、API 错误和大型文件处理，并提供了恢复步骤。",{"category":111,"check":183,"severity":42,"summary":184},"Tool Fallback","该技能不依赖于 MCP 服务器等外部工具，而是使用自己的库，因此回退机制不适用。",{"category":92,"check":186,"severity":24,"summary":187},"Stack assumptions","SKILL.md 指定了 Python 3.9+ 作为要求，并使用 `uv` 管理的标准库，确保了可移植性。",{"category":189,"check":190,"severity":24,"summary":191},"Safety","Halt on unexpected state","脚本包含对有效输入的检查，并能妥善处理 API 错误，有效地在意外状态下停止。",{"category":92,"check":193,"severity":24,"summary":194},"Cross-skill coupling","该技能独立运行，不隐含依赖其他技能；其功能是自包含的。",1778695206661,"此技能利用 PaddleOCR 的高级模型（PaddleOCR-VL, PP-StructureV3）从 PDF 和文档图像中提取结构化 Markdown/JSON，包括表格、公式、图形和布局信息。它支持各种输入方法（URL、本地路径）、可选的文件类型指定以及可配置的输出处理（保存到文件、stdout）。提供了错误处理和 API 配置指南。",[198,199,200,201,202],"提取具有单元格级别精度的表格","将公式识别为 LaTeX","解析多栏布局和阅读顺序","输出结构化的 Markdown 或 JSON","支持 PDF 和文档图像",[204,205,206],"简单的纯文本 OCR 任务","对简单图像进行速度要求高的 OCR","处理屏幕截图或带有清晰文本的简单图像",[],[209,210,211,212,213],"Python 3.9+","uv 包管理器","用于 API 调用的互联网访问","PADDLEOCR_DOC_PARSING_API_URL 环境变量","PADDLEOCR_ACCESS_TOKEN 环境变量","3.0.0","4.4.0","精确地从复杂的文档和图像中提取结构化信息，使内容易于被 LLM 和下游处理使用。","该扩展具有极其完善的文档和实现，提供全面的用法示例、清晰的错误处理和强大的依赖项管理。它有效地解决了特定的用户需求，并在安全性、可移植性和可维护性方面遵循了最佳实践。",99,"一个非常健壮且文档齐全的技能，用于从 PDF 和文档图像中提取结构化数据。",[221,222,223,224,225,226,227,228],"ocr","document-parsing","pdf","image-processing","layout-analysis","structure-extraction","markdown","json","verified",[231,232,233,234],"处理发票和财务报告","提取学术论文内容","结构化扫描文档数据","分析复杂文档布局",[236,237,238,239,240],"识别输入源（URL 或本地文件）","使用适当的参数执行文档解析脚本","解析 JSON 响应（检查 `ok` 状态和 `error` 字段）","从结构化输出中提取相关数据（文本、表格、公式）","将结果呈现给用户或用于进一步处理",{"codeQuality":242,"collectedAt":244,"documentation":245,"maintenance":248,"security":255,"testCoverage":257},{"hasLockfile":243},true,1778695190156,{"descriptionLength":246,"readmeSize":247},419,23379,{"closedIssues90d":249,"forks":250,"hasChangelog":251,"openIssues90d":252,"pushedAt":253,"stars":254},60,10426,false,58,1778674559000,77756,{"hasNpmPackage":251,"license":256,"smitheryVerified":251},"Apache-2.0",{"hasCi":243,"hasTests":243},{"updatedAt":259},1778695287770,{"basePath":261,"githubOwner":262,"githubRepo":263,"locale":18,"slug":264,"type":265},"skills/paddleocr-doc-parsing","PaddlePaddle","PaddleOCR","paddleocr-doc-parsing","skill",null,{"evaluate":268,"extract":271},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":269,"targetMarket":270,"tier":229},[221,222,223,224,225,226,227,228],"global",{"commitSha":272,"license":256},"HEAD",{"repoId":274,"translatedFrom":275},"kd77seqrqsfst3qefpyp2ape5h86mhqy","k17f6kj5nsqfvjy2vj7tyj9kz186mpgh",{"_creationTime":277,"_id":274,"identity":278,"providers":279,"workflow":367},1778695167335.008,{"githubOwner":262,"githubRepo":263,"sourceUrl":14},{"classify":280,"discover":349,"github":352},{"commitSha":272,"extensions":281},[282,306,319,337],{"basePath":261,"description":283,"displayName":264,"installMethods":284,"rationale":285,"selectedPaths":286,"source":304,"sourceLanguage":305,"type":265},"Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表, 阅读顺序; reading order, formula, LaTeX, layout parsing, structure extraction, PP-StructureV3, PaddleOCR-VL.",{"claudeCode":12},"SKILL.md frontmatter at skills/paddleocr-doc-parsing/SKILL.md",[287,290,293,296,298,300,302],{"path":288,"priority":289},"SKILL.md","mandatory",{"path":291,"priority":292},"references/output_schema.md","medium",{"path":294,"priority":295},"scripts/layout_caller.py","low",{"path":297,"priority":295},"scripts/lib.py",{"path":299,"priority":295},"scripts/optimize_file.py",{"path":301,"priority":295},"scripts/smoke_test.py",{"path":303,"priority":295},"scripts/split_pdf.py","rule","en",{"basePath":307,"description":308,"displayName":309,"installMethods":310,"rationale":311,"selectedPaths":312,"source":304,"sourceLanguage":305,"type":265},"skills/paddleocr-text-recognition","Use this skill whenever the user wants text extracted from images, photos, scans, screenshots, or scanned PDFs. Returns exact machine-readable strings with line-level text and optional bbox coordinates. Strong accuracy for CJK, small print, and handwritten text. Trigger terms: OCR, 文字识别, 图片转文字, 截图识字, 提取图中文字, 扫描识字, 识字, 纯文字, plain text extraction, 坐标, 检测框, bbox, bounding box, image to text, screenshot, photo scan, recognize text.","paddleocr-text-recognition",{"claudeCode":12},"SKILL.md frontmatter at skills/paddleocr-text-recognition/SKILL.md",[313,314,315,316,318],{"path":288,"priority":289},{"path":291,"priority":292},{"path":297,"priority":295},{"path":317,"priority":295},"scripts/ocr_caller.py",{"path":301,"priority":295},{"basePath":320,"installMethods":321,"rationale":323,"selectedPaths":324,"source":304,"sourceLanguage":305,"type":336},"",{"pypi":322},"paddleocr","cli ecosystem detected at /",[325,327,329,331,334],{"path":326,"priority":289},"pyproject.toml",{"path":328,"priority":289},"setup.py",{"path":330,"priority":289},"README.md",{"path":332,"priority":333},"LICENSE","high",{"path":335,"priority":292},"paddleocr/__main__.py","cli",{"basePath":338,"displayName":339,"installMethods":340,"rationale":341,"selectedPaths":342,"source":304,"sourceLanguage":347,"type":348},"mcp_server","paddleocr_mcp",{"pypi":339},"pyproject.toml with mcp/fastmcp dependency + scripts at mcp_server/pyproject.toml",[343,344,345],{"path":326,"priority":289},{"path":330,"priority":289},{"path":346,"priority":292},"paddleocr_mcp/__main__.py","fr","mcp",{"sources":350},[351],"manual",{"closedIssues90d":249,"description":353,"forks":250,"homepage":354,"license":256,"openIssues90d":252,"pushedAt":253,"readmeSize":247,"stars":254,"topics":355},"Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.","https://www.paddleocr.com",[221,356,357,358,359,222,360,361,362,363,364,365,366],"chineseocr","pdf2markdown","pp-ocr","pp-structure","document-translation","kie","ai4science","pdf-extractor-rag","pdf-parser","rag","paddleocr-vl",{"classifiedAt":368,"discoverAt":369,"extractAt":370,"githubAt":370,"updatedAt":368},1778695188896,1778695167335,1778695186352,[222,224,228,225,227,221,223,226],{"evaluatedAt":373,"extractAt":374,"updatedAt":259},1778695207150,1778695189192,[],[377,399,431,457,479,501],{"_creationTime":378,"_id":379,"community":380,"display":381,"identity":385,"providers":386,"relations":393,"tags":395,"workflow":396},1778695287335.507,"k17968e0gk5ecfnn9f6xnfrpqn86nfxq",{"reviewCount":8},{"description":382,"installMethods":383,"name":384,"sourceUrl":14},"当用户希望从图像、照片、扫描件、截图或扫描的 PDF 中提取文本时，请使用此技能。返回机器可读的精确字符串，包含行级文本和可选的 bbox 坐标。对 CJK、小字和手写文本具有很高的准确性。触发词：OCR、文字识别、图片转文字、截图识字、提取图中文字、扫描识字、识字、纯文字、plain text extraction、坐标、检测框、bbox、bounding box、image to text、screenshot、photo scan、recognize text。",{"claudeCode":12},"paddleocr-文本识别",{"basePath":307,"githubOwner":262,"githubRepo":263,"locale":18,"slug":309,"type":265},{"evaluate":387,"extract":392},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":388,"targetMarket":270,"tier":229},[221,389,390,222,223,391],"text-extraction","image-to-text","python",{"commitSha":272},{"repoId":274,"translatedFrom":394},"k17a43s5382jae1sgtne8ngfg586m9f0",[222,390,221,223,391,389],{"evaluatedAt":397,"extractAt":374,"updatedAt":398},1778695224039,1778695287335,{"_creationTime":400,"_id":401,"community":402,"display":403,"identity":409,"providers":414,"relations":424,"tags":427,"workflow":428},1778691104675.98,"k17a012kzjtmn6vm9xf7k1q3d986n6me",{"reviewCount":8},{"description":404,"installMethods":405,"name":407,"sourceUrl":408},"Convert a resume PDF to clean markdown for LLM parsing or candidate pipelines.",{"claudeCode":406},"iterationlayer/skills","Convert Resume to Markdown","https://github.com/iterationlayer/skills",{"basePath":410,"githubOwner":411,"githubRepo":412,"locale":305,"slug":413,"type":265},"skills/convert-resume-to-markdown","iterationlayer","skills","convert-resume-to-markdown",{"evaluate":415,"extract":422},{"promptVersionExtension":214,"promptVersionScoring":215,"score":416,"tags":417,"targetMarket":270,"tier":229},100,[418,223,227,419,420,421],"document-processing","resume","hiring","nlp",{"commitSha":272,"license":423},"MIT",{"parentExtensionId":425,"repoId":426},"k1721s0xmp59902ybtpakrrffn86n10s","kd76p4g2qmtrkgx99cnab3683d86n4g8",[418,420,227,421,223,419],{"evaluatedAt":429,"extractAt":430,"updatedAt":429},1778691474825,1778691104676,{"_creationTime":432,"_id":433,"community":434,"display":435,"identity":441,"providers":444,"relations":450,"tags":453,"workflow":454},1778686940775.5723,"k17d40zvn2sfy64zvq7rzpzksh86mndd",{"reviewCount":8},{"description":436,"installMethods":437,"name":439,"sourceUrl":440},"Efficiently extract and convert the contents of any local file—such as PDF, DOCX, DOC, ODT, RTF, XLSX, XLS, or HTML—into clean, well-formatted markdown saved to disk. Use this skill whenever the user requests to parse, read, or extract information from a file on their computer, including phrases like “parse this PDF”, “convert this document”, “read this file”, “extract text from”, or when a local file path (not a URL) is provided. This skill offers advanced options like generating AI-powered summaries and answering questions based on the file's content. Prefer this tool over `scrape` when handling local files to deliver precise, structured outputs for downstream tasks.\n",{"claudeCode":438},"firecrawl/cli","firecrawl-parse","https://github.com/firecrawl/cli",{"basePath":442,"githubOwner":443,"githubRepo":336,"locale":305,"slug":439,"type":265},"skills/firecrawl-parse","firecrawl",{"evaluate":445,"extract":449},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":446,"targetMarket":270,"tier":229},[447,222,227,223,448,336],"file-conversion","docx",{"commitSha":272},{"parentExtensionId":451,"repoId":452},"k17axfavjpz72cd3qqzn86shb186ncqt","kd7csd1wb06dg9c1jfy5063f2586ne60",[336,222,448,447,227,223],{"evaluatedAt":455,"extractAt":456,"updatedAt":455},1778687175227,1778686940775,{"_creationTime":458,"_id":459,"community":460,"display":461,"identity":465,"providers":468,"relations":475,"tags":476,"workflow":477},1778691104676.005,"k17b3rrsy570h6ysqbn0p324f186mzxv",{"reviewCount":8},{"description":462,"installMethods":463,"name":464,"sourceUrl":408},"Generate a professionally styled PDF document from Markdown content with custom fonts, headers, and page numbers.",{"claudeCode":406},"Markdown to Styled PDF",{"basePath":466,"githubOwner":411,"githubRepo":412,"locale":305,"slug":467,"type":265},"skills/markdown-to-styled-pdf","markdown-to-styled-pdf",{"evaluate":469,"extract":474},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":470,"targetMarket":270,"tier":229},[223,227,471,472,473],"document-generation","content-creation","styling",{"commitSha":272,"license":423},{"parentExtensionId":425,"repoId":426},[472,471,227,223,473],{"evaluatedAt":478,"extractAt":430,"updatedAt":478},1778693710276,{"_creationTime":480,"_id":481,"community":482,"display":483,"identity":487,"providers":490,"relations":497,"tags":498,"workflow":499},1778691104675.9805,"k173dwe2djyydbkrp6qr8dbrfs86nk8d",{"reviewCount":8},{"description":484,"installMethods":485,"name":486,"sourceUrl":408},"Extract structured data from documents using AI-powered field extraction.",{"claudeCode":406},"Document Extraction API",{"basePath":488,"githubOwner":411,"githubRepo":412,"locale":305,"slug":489,"type":265},"skills/document-extraction-api","document-extraction-api",{"evaluate":491,"extract":496},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":492,"targetMarket":270,"tier":229},[418,493,494,495,223,221],"data-extraction","ai","api",{"commitSha":272,"license":423},{"parentExtensionId":425,"repoId":426},[494,495,493,418,221,223],{"evaluatedAt":500,"extractAt":430,"updatedAt":500},1778691504579,{"_creationTime":502,"_id":503,"community":504,"display":505,"identity":511,"providers":514,"relations":524,"tags":527,"workflow":528},1778695859881.682,"k17f8fzr9brbvytcf4mwcrz48h86nz6t",{"reviewCount":8},{"description":506,"installMethods":507,"name":509,"sourceUrl":510},"使用 Nutrient DWS 处理文档。当用户希望从 HTML 或 URL 生成 PDF、转换 Office/图像/PDF、组装或拆分文件包、OCR 扫描件、提取文本/表格/键值对、进行 PII 拟态、添加水印、签名、填充表单、优化 PDF 或生成 PDF/A 或 PDF/UA 等合规性输出时使用。触发器包括转换为 PDF、合并这些 PDF、OCR 此扫描件、提取表格、拟态 PII、签名此 PDF、制作此 PDF/A 或为 Web 交付进行线性化。",{"claudeCode":508},"PSPDFKit-labs/nutrient-agent-skill","nutrient-document-processing","https://github.com/PSPDFKit-labs/nutrient-agent-skill",{"basePath":509,"githubOwner":512,"githubRepo":513,"locale":18,"slug":509,"type":265},"PSPDFKit-labs","nutrient-agent-skill",{"evaluate":515,"extract":523},{"promptVersionExtension":214,"promptVersionScoring":215,"score":516,"tags":517,"targetMarket":270,"tier":229},98,[418,223,221,518,519,520,521,522],"conversion","redaction","signing","compliance","extraction",{"commitSha":272},{"repoId":525,"translatedFrom":526},"kd71fjmn43awb0bgafy6r3vers86ngqg","k1704fp8n8znrmyrxm482pgpr586nfzx",[521,518,418,522,221,223,519,520],{"evaluatedAt":529,"extractAt":530,"updatedAt":531},1778695838272,1778695810823,1778695859881]