[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-aidenwu0209-paddleocr-text-recognition-ms":3,"guides-for-aidenwu0209-paddleocr-text-recognition":221,"similar-k17b9480w9tdwjwad0rkr80e11867wpb":222},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":20,"identity":188,"isFallback":193,"parentExtension":194,"providers":195,"relations":199,"repo":201,"workflow":218},1778053339109.6736,"k17b9480w9tdwjwad0rkr80e11867wpb",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"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","https://github.com/aidenwu0209/paddleocr-skills/tree/HEAD/skills/paddleocr-text-recognition",[15,16,17,18,19],"ocr","text-extraction","image-to-text","pdf","python",{"_creationTime":21,"_id":22,"extensionId":5,"locale":23,"result":24,"trustSignals":176,"workflow":186},1778053352237.2942,"kn7fsd9hr4j4qkhrdqjhgvjbv1867c8k","en",{"checks":25,"evaluatedAt":166,"extensionSummary":167,"promptVersionExtension":168,"promptVersionScoring":169,"rationale":170,"score":171,"summary":172,"tags":173,"targetMarket":174,"tier":175},[26,31,34,37,41,44,48,52,55,58,62,67,70,74,77,80,83,86,89,92,95,99,103,108,112,115,118,121,125,128,131,134,137,140,144,147,150,153,156,159,163],{"category":27,"check":28,"severity":29,"summary":30},"Practical Utility","Problem relevance","pass","The description clearly states the problem: extracting text from images, photos, scans, and PDFs, with specific trigger terms provided.",{"category":27,"check":32,"severity":29,"summary":33},"Unique selling proposition","The skill offers OCR capabilities with strong accuracy for CJK, small print, and handwritten text, which is a distinct value proposition beyond basic LLM text extraction.",{"category":27,"check":35,"severity":29,"summary":36},"Production readiness","The skill is production-ready, providing clear installation instructions, configuration guidance, and a functional script for its stated use case.",{"category":38,"check":39,"severity":29,"summary":40},"Scope","Single responsibility principle","The extension focuses solely on text recognition from images and PDFs, adhering to a single responsibility.",{"category":38,"check":42,"severity":29,"summary":43},"Description quality","The displayed description is concise, readable, and accurately reflects the skill's functionality and trigger terms.",{"category":45,"check":46,"severity":29,"summary":47},"Invocation","Scoped tools","The skill uses a single, well-defined script (`ocr_caller.py`) that takes specific arguments for input source and output, rather than a generalist command.",{"category":49,"check":50,"severity":29,"summary":51},"Documentation","Configuration & parameter reference","All necessary environment variables and script parameters (file-url, file-path, file-type, output, stdout, pretty) are documented with clear usage instructions.",{"category":38,"check":53,"severity":29,"summary":54},"Tool naming","The primary tool is invoked via `uv run scripts/ocr_caller.py`, which is descriptive of its function within the skill's context.",{"category":38,"check":56,"severity":29,"summary":57},"Minimal I/O surface","The script accepts specific input parameters (file-url, file-path, file-type) and returns a structured JSON output, avoiding unnecessary complexity.",{"category":59,"check":60,"severity":29,"summary":61},"License","License usability","The extension is licensed under Apache-2.0, a permissive open-source license.",{"category":63,"check":64,"severity":65,"summary":66},"Maintenance","Commit recency","not_applicable","The repository's commit history is not available in the provided context, so this check is not applicable.",{"category":63,"check":68,"severity":29,"summary":69},"Dependency Management","The skill uses inline PEP 723 dependencies managed by uv, which is a modern and robust dependency management approach.",{"category":71,"check":72,"severity":29,"summary":73},"Security","Secret Management","Secrets are handled via environment variables (`PADDLEOCR_ACCESS_TOKEN`), not hardcoded, and the documentation guides users to configure them securely.",{"category":71,"check":75,"severity":29,"summary":76},"Injection","The script processes inputs like file paths and URLs but does not appear to execute arbitrary code from external data sources.",{"category":71,"check":78,"severity":29,"summary":79},"Transitive Supply-Chain Grenades","The skill relies on a documented API and local execution of provided scripts, with no runtime downloads or execution of arbitrary external code.",{"category":71,"check":81,"severity":29,"summary":82},"Sandbox Isolation","The script operates locally with provided files or URLs and uses standard Python libraries; it does not interact with the file system outside of its designated output path or temporary files.",{"category":71,"check":84,"severity":29,"summary":85},"Sandbox escape primitives","No evidence of detached process spawns or retry loops around denied tool calls found in the provided scripts.",{"category":71,"check":87,"severity":29,"summary":88},"Data Exfiltration","The skill makes an outbound call to a configured API URL for OCR processing. The documentation guides users on credential management and does not indicate any undocumented outbound calls or exfiltration of sensitive data.",{"category":71,"check":90,"severity":29,"summary":91},"Hidden Text Tricks","The bundled files do not contain any hidden text tricks, invisible Unicode characters, or other obfuscation techniques.",{"category":71,"check":93,"severity":29,"summary":94},"Opaque code execution","The Python scripts are provided as plain, readable source code with inline dependency declarations.",{"category":96,"check":97,"severity":29,"summary":98},"Portability","Structural Assumption","The script uses standard Python libraries and OS temporary directories, with no specific structural assumptions about the user's project layout.",{"category":100,"check":101,"severity":65,"summary":102},"Trust","Issues Attention","Issue data is not available for this repository.",{"category":104,"check":105,"severity":106,"summary":107},"Versioning","Release Management","warning","No explicit versioning information (e.g., a version field in SKILL.md or package.json, or a CHANGELOG) is present for the skill itself. The README references a specific commit hash from the upstream repository.",{"category":109,"check":110,"severity":29,"summary":111},"Code Execution","Validation","Input arguments are validated through argparse, and file types are inferred or explicitly set. The script handles various input scenarios gracefully.",{"category":71,"check":113,"severity":29,"summary":114},"Unguarded Destructive Operations","The skill is read-only in nature, performing OCR operations without any destructive actions on the user's system or remote services.",{"category":109,"check":116,"severity":29,"summary":117},"Error Handling","The script includes robust error handling for API requests, file operations, and configuration issues, returning structured JSON errors.",{"category":109,"check":119,"severity":29,"summary":120},"Logging","The script logs messages to stderr for output file paths and script status, providing audit information.",{"category":122,"check":123,"severity":29,"summary":124},"Compliance","GDPR","The skill processes image data for OCR and does not explicitly handle personal data unless it is present within the image content itself, which is then processed by the OCR engine.",{"category":122,"check":126,"severity":29,"summary":127},"Target market","The skill's functionality is global, processing images and PDFs without regional restrictions. The target market is 'global'.",{"category":96,"check":129,"severity":29,"summary":130},"Runtime stability","The skill specifies Python 3.9+ and uses standard libraries, making it portable across different environments. It handles potential issues like Windows console encoding.",{"category":45,"check":132,"severity":29,"summary":133},"Precise Purpose","The description clearly defines the skill's purpose (text extraction from images/PDFs) and explicitly lists non-goals (plain text files, complex documents).",{"category":45,"check":135,"severity":29,"summary":136},"Concise Frontmatter","The SKILL.md frontmatter is concise and effectively summarizes the core capability and trigger terms.",{"category":49,"check":138,"severity":29,"summary":139},"Concise Body","The SKILL.md body is well-structured and stays within reasonable length, with detailed output schema and examples in separate files.",{"category":141,"check":142,"severity":29,"summary":143},"Context","Progressive Disclosure","Detailed output schema information is provided in a separate `references/output_schema.md` file, demonstrating progressive disclosure.",{"category":141,"check":145,"severity":65,"summary":146},"Forked exploration","This skill is not designed for deep exploration or code review; it performs a single OCR task and returns the result, so 'context: fork' is not applicable.",{"category":27,"check":148,"severity":29,"summary":149},"Usage examples","Multiple clear and ready-to-use examples are provided for URL OCR, local file OCR, explicit file typing, and stdout output.",{"category":27,"check":151,"severity":29,"summary":152},"Edge cases","The documentation addresses potential errors like configuration issues, authentication failures, unsupported formats, and no text detection, providing guidance for each.",{"category":109,"check":154,"severity":65,"summary":155},"Tool Fallback","The skill does not rely on external tools like an MCP server and uses only Claude-internal tools, making this check not applicable.",{"category":96,"check":157,"severity":29,"summary":158},"Stack assumptions","The skill specifies Python 3.9+ and lists `uv` as a requirement, and the scripts include PEP 723 metadata for dependency resolution.",{"category":160,"check":161,"severity":29,"summary":162},"Safety","Halt on unexpected state","The skill's scripts and error handling are designed to report issues and exit non-zero on unexpected states, rather than proceeding destructively or silently.",{"category":96,"check":164,"severity":29,"summary":165},"Cross-skill coupling","The skill is self-contained and does not implicitly rely on other skills; its functionality is distinct and clearly defined.",1778053350408,"This skill leverages the PaddleOCR API to perform optical character recognition on images and PDF documents. It returns extracted text with optional line-level bounding box coordinates, supporting various file types and providing detailed error handling and configuration guidance.","2.0.0","3.4.0","This is a high-quality, well-documented, and robust skill. It clearly defines its purpose, provides excellent usage examples, handles errors gracefully, and ensures security through environment variables for credentials. The only minor point is the lack of explicit versioning for the skill itself, which is noted but does not detract significantly from its overall quality.",95,"A highly reliable and well-documented skill for extracting text from images and PDFs using PaddleOCR.",[15,16,17,18,19],"global","verified",{"codeQuality":177,"collectedAt":178,"documentation":179,"maintenance":181,"security":182,"testCoverage":185},{},1778053340555,{"descriptionLength":180,"readmeSize":8},431,{},{"hasNpmPackage":183,"license":184,"smitheryVerified":183},false,"Apache-2.0",{"hasCi":183,"hasTests":183},{"updatedAt":187},1778053352237,{"githubOwner":189,"githubRepo":190,"locale":23,"slug":191,"type":192},"aidenwu0209","paddleocr-skills","paddleocr-text-recognition","skill",true,null,{"extract":196,"llm":198},{"commitSha":197,"license":184},"ca41406b66e5a475f43b073a5b731dfd1b9c50b1",{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":200},"kd7b1t00prnctc7258swvw0hs5865sjq",{"_creationTime":202,"_id":200,"identity":203,"providers":205,"workflow":215},1777995558409.8687,{"githubOwner":189,"githubRepo":190,"sourceUrl":204},"https://github.com/aidenwu0209/paddleocr-skills",{"discover":206,"github":209},{"sources":207},[208],"skills-sh",{"closedIssues90d":8,"forks":210,"license":184,"openIssues90d":8,"pushedAt":211,"readmeSize":212,"stars":213,"topics":214},2,1778047331000,2405,20,[],{"discoverAt":216,"extractAt":217,"githubAt":217,"updatedAt":217},1777995558409,1778053339816,{"anyEnrichmentAt":219,"extractAt":220,"githubAt":219,"llmAt":187,"updatedAt":187},1778053339393,1778053339109,[],[223,244,270,290,315,336],{"_creationTime":224,"_id":225,"community":226,"display":227,"identity":236,"providers":238,"relations":242,"workflow":243},1778053339109.673,"k170fjdnm4zmjtz1rgs8zwq4418663pv",{"reviewCount":8},{"description":228,"installMethods":229,"name":230,"sourceUrl":231,"tags":232},"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.",{},"PaddleOCR Document Parsing","https://github.com/aidenwu0209/paddleocr-skills/tree/HEAD/skills/paddleocr-doc-parsing",[18,233,15,234,235,19],"document-parsing","layout-analysis","paddleocr",{"githubOwner":189,"githubRepo":190,"locale":23,"slug":237,"type":192},"paddleocr-doc-parsing",{"extract":239,"llm":240},{"commitSha":197,"license":184},{"promptVersionExtension":168,"promptVersionScoring":169,"score":241,"targetMarket":174,"tier":175},98,{"repoId":200},{"anyEnrichmentAt":219,"extractAt":220,"githubAt":219,"llmAt":187,"updatedAt":187},{"_creationTime":245,"_id":246,"community":247,"display":248,"identity":255,"providers":259,"relations":264,"workflow":266},1778053148350.465,"k17207fprgpyp6yp2b2a4csry1866v1c",{"reviewCount":8},{"description":249,"installMethods":250,"name":251,"sourceUrl":252,"tags":253},"Extract text from scanned PDFs using optical character recognition",{},"PDF OCR Extraction","https://github.com/claude-office-skills/skills/tree/HEAD/pdf-ocr",[18,15,16,254],"mcp",{"githubOwner":256,"githubRepo":257,"locale":23,"slug":258,"type":192},"claude-office-skills","skills","pdf-ocr-extraction",{"extract":260,"llm":263},{"commitSha":261,"license":262},"9c4c7d5cd2813a8936bf2c9fdb174ea883b85a11","MIT",{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":265},"kd7fw7xbj58qc2z8whrrjptbed8659db",{"anyEnrichmentAt":267,"extractAt":268,"githubAt":267,"llmAt":269,"updatedAt":269},1778053151766,1778053148350,1778053561145,{"_creationTime":271,"_id":272,"community":273,"display":274,"identity":283,"providers":285,"relations":288,"workflow":289},1778053148350.4656,"k171nxqak0bb4qq89mkfwf02s5867cf6",{"reviewCount":8},{"description":275,"installMethods":276,"name":277,"sourceUrl":278,"tags":279},"Convert PDF files to editable Word documents using pdf2docx",{},"PDF to DOCX Converter","https://github.com/claude-office-skills/skills/tree/HEAD/pdf-to-docx",[18,280,281,282,19],"docx","conversion","document-processing",{"githubOwner":256,"githubRepo":257,"locale":23,"slug":284,"type":192},"pdf-to-docx",{"extract":286,"llm":287},{"commitSha":261,"license":262},{"promptVersionExtension":168,"promptVersionScoring":169,"score":241,"targetMarket":174,"tier":175},{"repoId":265},{"anyEnrichmentAt":267,"extractAt":268,"githubAt":267,"llmAt":269,"updatedAt":269},{"_creationTime":291,"_id":292,"community":293,"display":294,"identity":307,"providers":309,"relations":313,"workflow":314},1778053148350.4617,"k1758w1kjmv1kaems0xes3h8m9866dtz",{"reviewCount":8},{"description":295,"installMethods":296,"name":297,"sourceUrl":298,"tags":299},"MCP server with 39 tools for Word, Excel, PowerPoint, PDF, OCR operations",{},"Office MCP Server","https://github.com/claude-office-skills/skills/tree/HEAD/office-mcp",[300,254,18,301,302,303,15,304,305,306],"office","excel","word","powerpoint","automation","typescript","nodejs",{"githubOwner":256,"githubRepo":257,"locale":23,"slug":308,"type":192},"office-mcp",{"extract":310,"llm":311},{"commitSha":261,"license":262},{"promptVersionExtension":168,"promptVersionScoring":169,"score":312,"targetMarket":174,"tier":175},94,{"repoId":265},{"anyEnrichmentAt":267,"extractAt":268,"githubAt":267,"llmAt":269,"updatedAt":269},{"_creationTime":316,"_id":317,"community":318,"display":319,"identity":328,"providers":330,"relations":334,"workflow":335},1778053148350.4373,"k1776t2fdx4h35mkwpc5h201dd866zms",{"reviewCount":8},{"description":320,"installMethods":321,"name":322,"sourceUrl":323,"tags":324},">",{},"Document Parser Skill","https://github.com/claude-office-skills/skills/tree/HEAD/doc-parser",[325,282,18,19,15,326,234,327],"parsing","extraction","docling",{"githubOwner":256,"githubRepo":257,"locale":23,"slug":329,"type":192},"doc-parser",{"extract":331,"llm":332},{"commitSha":261,"license":262},{"promptVersionExtension":168,"promptVersionScoring":169,"score":333,"targetMarket":174,"tier":175},92,{"repoId":265},{"anyEnrichmentAt":267,"extractAt":268,"githubAt":267,"llmAt":269,"updatedAt":269},{"_creationTime":337,"_id":338,"community":339,"display":340,"identity":349,"providers":351,"relations":359,"workflow":362},1778003232571.9153,"k17259226wsvv093qff3xnjqe5865r06",{"reviewCount":8},{"description":341,"installMethods":342,"name":343,"sourceUrl":344,"tags":345},"Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.",{},"PDF Processing Guide","https://github.com/anthropics/skills/tree/HEAD/skills/pdf",[18,282,19,16,15,346,347,348],"form-filling","productivity","data-analytics",{"githubOwner":350,"githubRepo":257,"locale":23,"slug":18,"type":192},"anthropics",{"extract":352,"smithery":355},{"commitSha":353,"license":354},"d230a6dd6eb1a0dbee9fec55e2f00a96e28dff81","Proprietary",{"qualityScore":356,"totalActivations":357,"uniqueUsers":358,"useCount":8,"verified":183},0.996426,920,410,{"parentExtensionId":360,"repoId":361},"k173j5mjcps56pe131t0b18eg18658ay","kd72m31vxr2nd4hahhzvp0cyrn864eyx",{"anyEnrichmentAt":363,"extractAt":364,"githubAt":365,"invalidatedAt":363,"llmAt":366,"smitheryAt":363,"updatedAt":363},1778008076651,1778003232571,1778003234861,1778007125066]