[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-PaddlePaddle-paddleocr-text-recognition-en":3,"guides-for-PaddlePaddle-paddleocr-text-recognition":356,"similar-k17a43s5382jae1sgtne8ngfg586m9f0-en":357},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":246,"isFallback":237,"parentExtension":251,"providers":252,"relations":257,"repo":259,"tags":352,"workflow":353},1778695189192.851,"k17a43s5382jae1sgtne8ngfg586m9f0",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":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.",{"claudeCode":12},"PaddlePaddle/PaddleOCR","paddleocr-text-recognition","https://github.com/PaddlePaddle/PaddleOCR",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":227,"workflow":244},1778695224039.224,"kn7829d7r1kwt4y4fjbt520m3586m9xm","en",{"checks":20,"evaluatedAt":195,"extensionSummary":196,"features":197,"nonGoals":203,"promptVersionExtension":207,"promptVersionScoring":208,"purpose":209,"rationale":210,"score":211,"summary":212,"tags":213,"targetMarket":220,"tier":221,"useCases":222},[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","The description clearly identifies the problem of extracting text from images and documents and names specific use cases and trigger terms.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value beyond a simple prompt by providing robust OCR capabilities with high accuracy for various text types and languages, integrating a specific model (PaddleOCR) and handling different input formats.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill is production-ready, offering installation instructions, clear usage examples, error handling, and a well-defined workflow for extracting text from images and PDFs.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension focuses solely on text extraction from images and PDFs using OCR, adhering to a single responsibility.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's capabilities, including input types, output format, accuracy claims, and trigger terms.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This is a skill-based extension, not a tool-based one, so this check does not apply.",{"category":45,"check":46,"severity":24,"summary":47},"Documentation","Configuration & parameter reference","All necessary configurations (API URL, token, timeout) are clearly documented with environment variables, and parameters like file-url, file-path, and file-type are explained.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","This check applies to extensions exposing multiple tools; this skill has a single primary function.",{"category":33,"check":52,"severity":24,"summary":53},"Minimal I/O surface","The input parameters (file_url, file_path, file_type) are specific and necessary for the OCR task. The output is the extracted text and structured result, with clear error reporting.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The license is Apache-2.0, clearly indicated in the LICENSE file and the SKILL.md frontmatter, and is a permissive open-source license.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The repository shows recent commits, indicating active maintenance.",{"category":59,"check":63,"severity":24,"summary":64},"Dependency Management","The `uv` dependency manager is used to resolve dependencies, and PEP 723 is leveraged for inline dependency declaration, which is a suitable measure for updating and managing dependencies.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","Secrets (API URL and token) are handled via environment variables, and the documentation guides users to configure them through standard methods, avoiding hardcoding or direct chat submission.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill processes provided file paths and URLs as data and does not appear to execute instructions from external content.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill relies on installed dependencies managed by `uv` and does not fetch remote code or content at runtime for execution.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The script operates within its designated environment and does not appear to modify files outside the project folder or use absolute paths.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No detached processes or deny-retry loops were observed in the provided scripts.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill only makes outbound calls to the configured PaddleOCR API endpoint, and there are no instructions to exfiltrate confidential data.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content and descriptions appear free of hidden steering tricks or obfuscation.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The provided scripts are in plain Python and do not contain obfuscated code, base64 payloads, or runtime script fetching.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill operates on provided file paths or URLs and does not make assumptions about the user's project structure.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","The number of opened and closed issues in the last 90 days suggests active maintainer engagement and responsiveness.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The project utilizes semantic versioning and has recent releases, indicating good release management practices.",{"category":104,"check":105,"severity":24,"summary":106},"Execution","Validation","Input parameters like file paths, URLs, and file types are validated, and the output schema is structured, implying good validation practices.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","This skill is read-only and does not perform destructive operations.",{"category":111,"check":112,"severity":24,"summary":113},"Code Execution","Error Handling","Errors are caught, categorized (INPUT_ERROR, CONFIG_ERROR, API_ERROR), and reported with meaningful messages, and the CLI tool exits with appropriate non-zero codes on failure.",{"category":111,"check":115,"severity":24,"summary":116},"Logging","The script logs informational messages and errors to stderr, providing auditability for operations and outcomes.",{"category":118,"check":119,"severity":24,"summary":120},"Compliance","GDPR","The skill processes image and PDF data for OCR and does not appear to operate on personal data without sanitization.",{"category":118,"check":122,"severity":24,"summary":123},"Target market","The extension is designed for global use, supporting multiple languages and relying on a cloud API without regional restrictions.",{"category":92,"check":125,"severity":24,"summary":126},"Runtime stability","The skill requires Python 3.9+ and standard libraries like httpx, with clear instructions for environment setup, making it portable across POSIX-compliant systems.",{"category":45,"check":128,"severity":24,"summary":129},"README","The README file is comprehensive, detailing features, installation, usage, and community aspects.",{"category":33,"check":131,"severity":42,"summary":132},"Tool surface size","This is a skill-based extension with a single primary function, not a set of tools.",{"category":40,"check":134,"severity":42,"summary":135},"Overlapping near-synonym tools","This skill does not expose multiple tools, so there are no overlapping synonyms.",{"category":45,"check":137,"severity":24,"summary":138},"Phantom features","All advertised features, such as OCR from various sources and detailed output options, are implemented and demonstrable via the provided scripts and documentation.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","The SKILL.md and README provide clear installation instructions using `uv` and include runnable copy-paste examples with usage scenarios.",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","Errors provide specific codes (e.g., INPUT_ERROR, CONFIG_ERROR, API_ERROR), human-readable messages, and often suggest remediation steps or point to documentation.",{"category":104,"check":148,"severity":24,"summary":149},"Pinned dependencies","Dependencies are managed via `uv` and declared inline using PEP 723, ensuring pinned versions and interpreter specifications.",{"category":33,"check":151,"severity":24,"summary":152},"Dry-run preview","The extension is read-only in terms of user data processing; it sends requests to an external API but does not modify local files or perform destructive operations, thus not requiring a dry-run mode.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The API client has a configurable timeout, and the library handles API errors and timeouts with retryable error messages, though the idempotency of the upstream API is assumed.",{"category":118,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The extension does not appear to emit telemetry; all operations are user-initiated and driven by explicit commands.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The description clearly defines the purpose (text extraction from images/PDFs) and when to use it, with specific trigger terms and explicit non-goals.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter is concise, self-contained, and includes relevant trigger terms for effective routing.",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured and avoids excessive length by delegating deep material to reference files.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md outlines the workflow and links to reference documentation for schema details, following progressive disclosure principles.",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","This skill is a direct action skill and does not involve deep exploration or code review, thus `context: fork` is not applicable.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","Multiple clear, end-to-end usage examples are provided for different scenarios (URL, local file, output options), demonstrating invocation and expected behavior.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The documentation addresses edge cases such as configuration errors, API failures, unsupported formats, and no text detection, providing symptoms and remediation steps.",{"category":111,"check":183,"severity":42,"summary":184},"Tool Fallback","This skill does not rely on external MCP servers or tools that would require a fallback mechanism.",{"category":92,"check":186,"severity":24,"summary":187},"Stack assumptions","The skill declares its Python version requirement (3.9+) and uses standard libraries, with dependencies managed via `uv`, ensuring portability.",{"category":189,"check":190,"severity":24,"summary":191},"Safety","Halt on unexpected state","The skill's error handling mechanism ensures it halts on unexpected states (like configuration errors or API issues) and reports them clearly.",{"category":92,"check":193,"severity":24,"summary":194},"Cross-skill coupling","The skill operates as a standalone OCR tool and does not implicitly rely on other skills or mention cross-skill coordination.",1778695223914,"This skill uses the PaddleOCR library to extract text from images, photos, scans, screenshots, and scanned PDFs. It returns machine-readable strings with optional bounding box coordinates and supports various languages and text types. The skill can be invoked with local file paths or URLs and provides detailed output, including raw API results and error information.",[198,199,200,201,202],"Extract text from images and PDFs","Support for CJK, small print, and handwritten text","Line-level text and optional bbox coordinates","Handles local files and URLs","Returns structured JSON output with error details",[204,205,206],"Extracting text from plain text, code, or markdown files directly.","Parsing complex document layouts like tables, formulas, or charts.","Replacing direct text file reading capabilities.","3.0.0","4.4.0","Extract text from images, photos, scans, screenshots, or scanned PDFs with high accuracy, providing machine-readable strings and optional coordinate data for downstream processing.","The skill is exceptionally well-documented, robust in its error handling and security practices, and adheres to all best practices. The only minor points are related to non-applicability of certain checks due to its nature as a single-function skill.",99,"Highly accurate and well-documented OCR skill for extracting text from images and PDFs.",[214,215,216,217,218,219],"ocr","text-extraction","image-to-text","document-parsing","pdf","python","global","verified",[223,224,225,226],"Extracting text from scanned documents for data entry.","Getting text from screenshots for analysis.","Digitizing text from photos of signs or documents.","Processing scanned PDFs to make their text searchable.",{"codeQuality":228,"collectedAt":230,"documentation":231,"maintenance":234,"security":241,"testCoverage":243},{"hasLockfile":229},true,1778695207427,{"descriptionLength":232,"readmeSize":233},431,23379,{"closedIssues90d":235,"forks":236,"hasChangelog":237,"openIssues90d":238,"pushedAt":239,"stars":240},60,10426,false,58,1778674559000,77756,{"hasNpmPackage":237,"license":242,"smitheryVerified":237},"Apache-2.0",{"hasCi":229,"hasTests":229},{"updatedAt":245},1778695224039,{"basePath":247,"githubOwner":248,"githubRepo":249,"locale":18,"slug":13,"type":250},"skills/paddleocr-text-recognition","PaddlePaddle","PaddleOCR","skill",null,{"evaluate":253,"extract":255},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":254,"targetMarket":220,"tier":221},[214,215,216,217,218,219],{"commitSha":256},"HEAD",{"repoId":258},"kd77seqrqsfst3qefpyp2ape5h86mhqy",{"_creationTime":260,"_id":258,"identity":261,"providers":262,"workflow":348},1778695167335.008,{"githubOwner":248,"githubRepo":249,"sourceUrl":14},{"classify":263,"discover":330,"github":333},{"commitSha":256,"extensions":264},[265,290,300,318],{"basePath":266,"description":267,"displayName":268,"installMethods":269,"rationale":270,"selectedPaths":271,"source":289,"sourceLanguage":18,"type":250},"skills/paddleocr-doc-parsing","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-doc-parsing",{"claudeCode":12},"SKILL.md frontmatter at skills/paddleocr-doc-parsing/SKILL.md",[272,275,278,281,283,285,287],{"path":273,"priority":274},"SKILL.md","mandatory",{"path":276,"priority":277},"references/output_schema.md","medium",{"path":279,"priority":280},"scripts/layout_caller.py","low",{"path":282,"priority":280},"scripts/lib.py",{"path":284,"priority":280},"scripts/optimize_file.py",{"path":286,"priority":280},"scripts/smoke_test.py",{"path":288,"priority":280},"scripts/split_pdf.py","rule",{"basePath":247,"description":10,"displayName":13,"installMethods":291,"rationale":292,"selectedPaths":293,"source":289,"sourceLanguage":18,"type":250},{"claudeCode":12},"SKILL.md frontmatter at skills/paddleocr-text-recognition/SKILL.md",[294,295,296,297,299],{"path":273,"priority":274},{"path":276,"priority":277},{"path":282,"priority":280},{"path":298,"priority":280},"scripts/ocr_caller.py",{"path":286,"priority":280},{"basePath":301,"installMethods":302,"rationale":304,"selectedPaths":305,"source":289,"sourceLanguage":18,"type":317},"",{"pypi":303},"paddleocr","cli ecosystem detected at /",[306,308,310,312,315],{"path":307,"priority":274},"pyproject.toml",{"path":309,"priority":274},"setup.py",{"path":311,"priority":274},"README.md",{"path":313,"priority":314},"LICENSE","high",{"path":316,"priority":277},"paddleocr/__main__.py","cli",{"basePath":319,"displayName":320,"installMethods":321,"rationale":322,"selectedPaths":323,"source":289,"sourceLanguage":328,"type":329},"mcp_server","paddleocr_mcp",{"pypi":320},"pyproject.toml with mcp/fastmcp dependency + scripts at mcp_server/pyproject.toml",[324,325,326],{"path":307,"priority":274},{"path":311,"priority":274},{"path":327,"priority":277},"paddleocr_mcp/__main__.py","fr","mcp",{"sources":331},[332],"manual",{"closedIssues90d":235,"description":334,"forks":236,"homepage":335,"license":242,"openIssues90d":238,"pushedAt":239,"readmeSize":233,"stars":240,"topics":336},"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",[214,337,338,339,340,217,341,342,343,344,345,346,347],"chineseocr","pdf2markdown","pp-ocr","pp-structure","document-translation","kie","ai4science","pdf-extractor-rag","pdf-parser","rag","paddleocr-vl",{"classifiedAt":349,"discoverAt":350,"extractAt":351,"githubAt":351,"updatedAt":349},1778695188896,1778695167335,1778695186352,[217,216,214,218,219,215],{"evaluatedAt":245,"extractAt":354,"updatedAt":355},1778695189192,1778695313155,[],[358,380,406,437,467,491],{"_creationTime":359,"_id":360,"community":361,"display":362,"identity":365,"providers":366,"relations":375,"tags":376,"workflow":377},1778695189192.8508,"k17f6kj5nsqfvjy2vj7tyj9kz186mpgh",{"reviewCount":8},{"description":267,"installMethods":363,"name":364,"sourceUrl":14},{"claudeCode":12},"PaddleOCR Document Parsing",{"basePath":266,"githubOwner":248,"githubRepo":249,"locale":18,"slug":268,"type":250},{"evaluate":367,"extract":374},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":368,"targetMarket":220,"tier":221},[214,217,218,369,370,371,372,373],"image-processing","layout-analysis","structure-extraction","markdown","json",{"commitSha":256,"license":242},{"repoId":258},[217,369,373,370,372,214,218,371],{"evaluatedAt":378,"extractAt":354,"updatedAt":379},1778695207150,1778695313334,{"_creationTime":381,"_id":382,"community":383,"display":384,"identity":390,"providers":393,"relations":399,"tags":402,"workflow":403},1778686940775.5723,"k17d40zvn2sfy64zvq7rzpzksh86mndd",{"reviewCount":8},{"description":385,"installMethods":386,"name":388,"sourceUrl":389},"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":387},"firecrawl/cli","firecrawl-parse","https://github.com/firecrawl/cli",{"basePath":391,"githubOwner":392,"githubRepo":317,"locale":18,"slug":388,"type":250},"skills/firecrawl-parse","firecrawl",{"evaluate":394,"extract":398},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":395,"targetMarket":220,"tier":221},[396,217,372,218,397,317],"file-conversion","docx",{"commitSha":256},{"parentExtensionId":400,"repoId":401},"k17axfavjpz72cd3qqzn86shb186ncqt","kd7csd1wb06dg9c1jfy5063f2586ne60",[317,217,397,396,372,218],{"evaluatedAt":404,"extractAt":405,"updatedAt":404},1778687175227,1778686940775,{"_creationTime":407,"_id":408,"community":409,"display":410,"identity":416,"providers":421,"relations":430,"tags":433,"workflow":434},1778691104675.9805,"k173dwe2djyydbkrp6qr8dbrfs86nk8d",{"reviewCount":8},{"description":411,"installMethods":412,"name":414,"sourceUrl":415},"Extract structured data from documents using AI-powered field extraction.",{"claudeCode":413},"iterationlayer/skills","Document Extraction API","https://github.com/iterationlayer/skills",{"basePath":417,"githubOwner":418,"githubRepo":419,"locale":18,"slug":420,"type":250},"skills/document-extraction-api","iterationlayer","skills","document-extraction-api",{"evaluate":422,"extract":428},{"promptVersionExtension":207,"promptVersionScoring":208,"score":211,"tags":423,"targetMarket":220,"tier":221},[424,425,426,427,218,214],"document-processing","data-extraction","ai","api",{"commitSha":256,"license":429},"MIT",{"parentExtensionId":431,"repoId":432},"k1721s0xmp59902ybtpakrrffn86n10s","kd76p4g2qmtrkgx99cnab3683d86n4g8",[426,427,425,424,214,218],{"evaluatedAt":435,"extractAt":436,"updatedAt":435},1778691504579,1778691104676,{"_creationTime":438,"_id":439,"community":440,"display":441,"identity":447,"providers":450,"relations":460,"tags":462,"workflow":463},1778695810823.162,"k1704fp8n8znrmyrxm482pgpr586nfzx",{"reviewCount":8},{"description":442,"installMethods":443,"name":445,"sourceUrl":446},"Process documents with Nutrient DWS. Use when the user wants to generate PDFs from HTML or URLs, convert Office/images/PDFs, assemble or split packets, OCR scans, extract text/tables/key-value pairs, redact PII, watermark, sign, fill forms, optimize PDFs, or produce compliance outputs like PDF/A or PDF/UA. Triggers include convert to PDF, merge these PDFs, OCR this scan, extract tables, redact PII, sign this PDF, make this PDF/A, or linearize for web delivery.",{"claudeCode":444},"PSPDFKit-labs/nutrient-agent-skill","nutrient-document-processing","https://github.com/PSPDFKit-labs/nutrient-agent-skill",{"basePath":445,"githubOwner":448,"githubRepo":449,"locale":18,"slug":445,"type":250},"PSPDFKit-labs","nutrient-agent-skill",{"evaluate":451,"extract":459},{"promptVersionExtension":207,"promptVersionScoring":208,"score":452,"tags":453,"targetMarket":220,"tier":221},98,[424,218,214,454,455,456,457,458],"conversion","redaction","signing","compliance","extraction",{"commitSha":256},{"repoId":461},"kd71fjmn43awb0bgafy6r3vers86ngqg",[457,454,424,458,214,218,455,456],{"evaluatedAt":464,"extractAt":465,"updatedAt":466},1778695838272,1778695810823,1778695861458,{"_creationTime":468,"_id":469,"community":470,"display":471,"identity":475,"providers":478,"relations":487,"tags":488,"workflow":489},1778691104676.001,"k1748qrw8s6xk96r6zt2qtgas586mphs",{"reviewCount":8},{"description":472,"installMethods":473,"name":474,"sourceUrl":415},"Generate a branded restaurant menu PDF with sections, items, prices, and descriptions.",{"claudeCode":413},"Generate Restaurant Menu",{"basePath":476,"githubOwner":418,"githubRepo":419,"locale":18,"slug":477,"type":250},"skills/generate-restaurant-menu","generate-restaurant-menu",{"evaluate":479,"extract":486},{"promptVersionExtension":207,"promptVersionScoring":208,"score":480,"tags":481,"targetMarket":220,"tier":221},100,[482,218,483,484,485],"document-generation","menu","restaurant","branding",{"commitSha":256,"license":429},{"parentExtensionId":431,"repoId":432},[485,482,483,218,484],{"evaluatedAt":490,"extractAt":436,"updatedAt":490},1778693352753,{"_creationTime":492,"_id":493,"community":494,"display":495,"identity":499,"providers":501,"relations":507,"tags":508,"workflow":509},1778691104675.9834,"k17bwxnh9scy64bmm9anmf7bbx86mtvn",{"reviewCount":8},{"description":496,"installMethods":497,"name":498,"sourceUrl":415},"Extract vehicle identification, owner details, registration dates, and technical specifications from vehicle registration documents.",{"claudeCode":413},"extract-fleet-vehicle-registration",{"basePath":500,"githubOwner":418,"githubRepo":419,"locale":18,"slug":498,"type":250},"skills/extract-fleet-vehicle-registration",{"evaluate":502,"extract":506},{"promptVersionExtension":207,"promptVersionScoring":208,"score":480,"tags":503,"targetMarket":220,"tier":221},[424,425,504,505,218],"fleet-management","api-integration",{"commitSha":256},{"parentExtensionId":431,"repoId":432},[505,425,424,504,218],{"evaluatedAt":510,"extractAt":436,"updatedAt":510},1778691789036]