[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MVN4SW0FRTHGV9CYSFPHJC":3,"skill-same:01M6MVN4SW0FRTHGV9CYSFPHJC":108},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M6MVN4SW0FRTHGV9CYSFPHJC","pdf-text-extractor",null,"Extract text from PDFs with OCR support. Perfect for digitizing documents, processing invoices, or analyzing content. Zero dependencies required.","Kernel8901\u002Fai-agent-skills-classification","Kernel8901","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F72647553?v=4","01M6KV388J2H5PNC8D8P940BJD","01M6KV38CS5B3AY63RKZB410YM",7,"MIT","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FPDF及文件\u002Fpdf-text-extractor\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"PDF","pdf text extractor","text","for","invoices","with","processing","dependencies","document","extract","Tools","ocr","analyzing","ZeRO","extraction","content","documents","support","2026-11-10 10:12:30",false,"---\nname: pdf-text-extractor\ndescription: Extract text from PDFs with OCR support. Perfect for digitizing documents, processing invoices, or analyzing content. Zero dependencies required.\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"version\": \"1.0.0\",\n        \"author\": \"Vernox\",\n        \"license\": \"MIT\",\n        \"tags\": [\"pdf\", \"ocr\", \"text\", \"extraction\", \"document\", \"digitization\"],\n        \"category\": \"tools\"\n      }\n  }\n---\n\n# PDF-Text-Extractor - Extract Text from PDFs\n\n**Vernox Utility Skill - Perfect for document digitization.**\n\n## Overview\n\nPDF-Text-Extractor is a zero-dependency tool for extracting text content from PDF files. Supports both embedded text extraction (for text-based PDFs) and OCR (for scanned documents).\n\n## Features\n\n### ✅ Text Extraction\n- Extract text from PDFs without external tools\n- Support for both text-based and scanned PDFs\n- Preserve document structure and formatting\n- Fast extraction (milliseconds for text-based)\n\n### ✅ OCR Support\n- Use Tesseract.js for scanned documents\n- Support multiple languages (English, Spanish, French, German)\n- Configurable OCR quality\u002Fspeed\n- Fallback to text extraction when possible\n\n### ✅ Batch Processing\n- Process multiple PDFs at once\n- Batch extraction for document workflows\n- Progress tracking for large files\n- Error handling and retry logic\n\n### ✅ Output Options\n- Plain text output\n- JSON output with metadata\n- Markdown conversion\n- HTML output (preserving links)\n\n### ✅ Utility Features\n- Page-by-page extraction\n- Character\u002Fword counting\n- Language detection\n- Metadata extraction (author, title, creation date)\n\n## Installation\n\n```bash\nclawhub install pdf-text-extractor\n```\n\n## Quick Start\n\n### Extract Text from PDF\n\n```javascript\nconst result = await extractText({\n  pdfPath: '.\u002Fdocument.pdf',\n  options: {\n    outputFormat: 'text',\n    ocr: true,\n    language: 'eng'\n  }\n});\n\nconsole.log(result.text);\nconsole.log(`Pages: ${result.pages}`);\nconsole.log(`Words: ${result.wordCount}`);\n```\n\n### Batch Extract Multiple PDFs\n\n```javascript\nconst results = await extractBatch({\n  pdfFiles: [\n    '.\u002Fdocument1.pdf',\n    '.\u002Fdocument2.pdf',\n    '.\u002Fdocument3.pdf'\n  ],\n  options: {\n    outputFormat: 'json',\n    ocr: true\n  }\n});\n\nconsole.log(`Extracted ${results.length} PDFs`);\n```\n\n### Extract with OCR\n\n```javascript\nconst result = await extractText({\n  pdfPath: '.\u002Fscanned-document.pdf',\n  options: {\n    ocr: true,\n    language: 'eng',\n    ocrQuality: 'high'\n  }\n});\n\n\u002F\u002F OCR will be used (scanned document detected)\n```\n\n## Tool Functions\n\n### `extractText`\nExtract text content from a single PDF file.\n\n**Parameters:**\n- `pdfPath` (string, required): Path to PDF file\n- `options` (object, optional): Extraction options\n  - `outputFormat` (string): 'text' | 'json' | 'markdown' | 'html'\n  - `ocr` (boolean): Enable OCR for scanned docs\n  - `language` (string): OCR language code ('eng', 'spa', 'fra', 'deu')\n  - `preserveFormatting` (boolean): Keep headings\u002Fstructure\n  - `minConfidence` (number): Minimum OCR confidence score (0-100)\n\n**Returns:**\n- `text` (string): Extracted text content\n- `pages` (number): Number of pages processed\n- `wordCount` (number): Total word count\n- `charCount` (number): Total character count\n- `language` (string): Detected language\n- `metadata` (object): PDF metadata (title, author, creation date)\n- `method` (string): 'text' or 'ocr' (extraction method)\n\n### `extractBatch`\nExtract text from multiple PDF files at once.\n\n**Parameters:**\n- `pdfFiles` (array, required): Array of PDF file paths\n- `options` (object, optional): Same as extractText\n\n**Returns:**\n- `results` (array): Array of extraction results\n- `totalPages` (number): Total pages across all PDFs\n- `successCount` (number): Successfully extracted\n- `failureCount` (number): Failed extractions\n- `errors` (array): Error details for failures\n\n### `countWords`\nCount words in extracted text.\n\n**Parameters:**\n- `text` (string, required): Text to count\n- `options` (object, optional):\n  - `minWordLength` (number): Minimum characters per word (default: 3)\n  - `excludeNumbers` (boolean): Don't count numbers as words\n  - `countByPage` (boolean): Return word count per page\n\n**Returns:**\n- `wordCount` (number): Total word count\n- `charCount` (number): Total character count\n- `pageCounts` (array): Word count per page\n- `averageWordsPerPage` (number): Average words per page\n\n### `detectLanguage`\nDetect the language of extracted text.\n\n**Parameters:**\n- `text` (string, required): Text to analyze\n- `minConfidence` (number): Minimum confidence for detection\n\n**Returns:**\n- `language` (string): Detected language code\n- `languageName` (string): Full language name\n- `confidence` (number): Confidence score (0-100)\n\n## Use Cases\n\n### Document Digitization\n- Convert paper documents to digital text\n- Process invoices and receipts\n- Digitize contracts and agreements\n- Archive physical documents\n\n### Content Analysis\n- Extract text for analysis tools\n- Prepare content for LLM processing\n- Clean up scanned documents\n- Parse PDF-based reports\n\n### Data Extraction\n- Extract data from PDF reports\n- Parse tables from PDFs\n- Pull structured data\n- Automate document workflows\n\n### Text Processing\n- Prepare content for translation\n- Clean up OCR output\n- Extract specific sections\n- Search within PDF content\n\n## Performance\n\n### Text-Based PDFs\n- **Speed:** ~100ms for 10-page PDF\n- **Accuracy:** 100% (exact text)\n- **Memory:** ~10MB for typical document\n\n### OCR Processing\n- **Speed:** ~1-3s per page (high quality)\n- **Accuracy:** 85-95% (depends on scan quality)\n- **Memory:** ~50-100MB peak during OCR\n\n## Technical Details\n\n### PDF Parsing\n- Uses native PDF.js library\n- Extracts text layer directly (no OCR needed)\n- Preserves document structure\n- Handles password-protected PDFs\n\n### OCR Engine\n- Tesseract.js under the hood\n- Supports 100+ languages\n- Adjustable quality\u002Fspeed tradeoff\n- Confidence scoring for accuracy\n\n### Dependencies\n- **ZERO external dependencies**\n- Uses Node.js built-in modules only\n- PDF.js included in skill\n- Tesseract.js bundled\n\n## Error Handling\n\n### Invalid PDF\n- Clear error message\n- Suggest fix (check file format)\n- Skip to next file in batch\n\n### OCR Failure\n- Report confidence score\n- Suggest rescan at higher quality\n- Fallback to basic extraction\n\n### Memory Issues\n- Stream processing for large files\n- Progress reporting\n- Graceful degradation\n\n## Configuration\n\n### Edit `config.json`:\n```json\n{\n  \"ocr\": {\n    \"enabled\": true,\n    \"defaultLanguage\": \"eng\",\n    \"quality\": \"medium\",\n    \"languages\": [\"eng\", \"spa\", \"fra\", \"deu\"]\n  },\n  \"output\": {\n    \"defaultFormat\": \"text\",\n    \"preserveFormatting\": true,\n    \"includeMetadata\": true\n  },\n  \"batch\": {\n    \"maxConcurrent\": 3,\n    \"timeoutSeconds\": 30\n  }\n}\n```\n\n## Examples\n\n### Extract from Invoice\n```javascript\nconst invoice = await extractText('.\u002Finvoice.pdf');\nconsole.log(invoice.text);\n\u002F\u002F \"INVOICE #12345 Date: 2026-02-04...\"\n```\n\n### Extract from Scanned Contract\n```javascript\nconst contract = await extractText('.\u002Fscanned-contract.pdf', {\n  ocr: true,\n  language: 'eng',\n  ocrQuality: 'high'\n});\nconsole.log(contract.text);\n\u002F\u002F \"AGREEMENT This contract between...\"\n```\n\n### Batch Process Documents\n```javascript\nconst docs = await extractBatch([\n  '.\u002Fdoc1.pdf',\n  '.\u002Fdoc2.pdf',\n  '.\u002Fdoc3.pdf',\n  '.\u002Fdoc4.pdf'\n]);\nconsole.log(`Processed ${docs.successCount}\u002F${docs.results.length} documents`);\n```\n\n## Troubleshooting\n\n### OCR Not Working\n- Check if PDF is truly scanned (not text-based)\n- Try different quality settings (low\u002Fmedium\u002Fhigh)\n- Ensure language matches document\n- Check image quality of scan\n\n### Extraction Returns Empty\n- PDF may be image-only\n- OCR failed with low confidence\n- Try different language setting\n\n### Slow Processing\n- Large PDF takes longer\n- Reduce quality for speed\n- Process in smaller batches\n\n## Tips\n\n### Best Results\n- Use text-based PDFs when possible (faster, 100% accurate)\n- High-quality scans for OCR (300 DPI+)\n- Clean background before scanning\n- Use correct language setting\n\n### Performance Optimization\n- Batch processing for multiple files\n- Disable OCR for text-based PDFs\n- Lower OCR quality for speed when acceptable\n\n## Roadmap\n\n- [ ] PDF\u002FA support\n- [ ] Advanced OCR pre-processing\n- [ ] Table extraction from OCR\n- [ ] Handwriting OCR\n- [ ] PDF form field extraction\n- [ ] Batch language detection\n- [ ] Confidence scoring visualization\n\n## License\n\nMIT\n\n---\n\n**Extract text from PDFs. Fast, accurate, zero dependencies.** ?\n","# PDF-Text-Extractor - Extract Text from PDFs\n\n**Vernox Utility Skill - Perfect for document digitization.**\n\n## Overview\n\nPDF-Text-Extractor is a zero-dependency tool for extracting text content from PDF files. Supports both embedded text extraction (for text-based PDFs) and OCR (for scanned documents).\n\n## Features\n\n### ✅ Text Extraction\n- Extract text from PDFs without external tools\n- Support for both text-based and scanned PDFs\n- Preserve document structure and formatting\n- Fast extraction (milliseconds for text-based)\n\n### ✅ OCR Support\n- Use Tesseract.js for scanned documents\n- Support multiple languages (English, Spanish, French, German)\n- Configurable OCR quality\u002Fspeed\n- Fallback to text extraction when possible\n\n### ✅ Batch Processing\n- Process multiple PDFs at once\n- Batch extraction for document workflows\n- Progress tracking for large files\n- Error handling and retry logic\n\n### ✅ Output Options\n- Plain text output\n- JSON output with metadata\n- Markdown conversion\n- HTML output (preserving links)\n\n### ✅ Utility Features\n- Page-by-page extraction\n- Character\u002Fword counting\n- Language detection\n- Metadata extraction (author, title, creation date)\n\n## Installation\n\n```bash\nclawhub install pdf-text-extractor\n```\n\n## Quick Start\n\n### Extract Text from PDF\n\n```javascript\nconst result = await extractText({\n  pdfPath: '.\u002Fdocument.pdf',\n  options: {\n    outputFormat: 'text',\n    ocr: true,\n    language: 'eng'\n  }\n});\n\nconsole.log(result.text);\nconsole.log(`Pages: ${result.pages}`);\nconsole.log(`Words: ${result.wordCount}`);\n```\n\n### Batch Extract Multiple PDFs\n\n```javascript\nconst results = await extractBatch({\n  pdfFiles: [\n    '.\u002Fdocument1.pdf',\n    '.\u002Fdocument2.pdf',\n    '.\u002Fdocument3.pdf'\n  ],\n  options: {\n    outputFormat: 'json',\n    ocr: true\n  }\n});\n\nconsole.log(`Extracted ${results.length} PDFs`);\n```\n\n### Extract with OCR\n\n```javascript\nconst result = await extractText({\n  pdfPath: '.\u002Fscanned-document.pdf',\n  options: {\n    ocr: true,\n    language: 'eng',\n    ocrQuality: 'high'\n  }\n});\n\n\u002F\u002F OCR will be used (scanned document detected)\n```\n\n## Tool Functions\n\n### `extractText`\nExtract text content from a single PDF file.\n\n**Parameters:**\n- `pdfPath` (string, required): Path to PDF file\n- `options` (object, optional): Extraction options\n  - `outputFormat` (string): 'text' | 'json' | 'markdown' | 'html'\n  - `ocr` (boolean): Enable OCR for scanned docs\n  - `language` (string): OCR language code ('eng', 'spa', 'fra', 'deu')\n  - `preserveFormatting` (boolean): Keep headings\u002Fstructure\n  - `minConfidence` (number): Minimum OCR confidence score (0-100)\n\n**Returns:**\n- `text` (string): Extracted text content\n- `pages` (number): Number of pages processed\n- `wordCount` (number): Total word count\n- `charCount` (number): Total character count\n- `language` (string): Detected language\n- `metadata` (object): PDF metadata (title, author, creation date)\n- `method` (string): 'text' or 'ocr' (extraction method)\n\n### `extractBatch`\nExtract text from multiple PDF files at once.\n\n**Parameters:**\n- `pdfFiles` (array, required): Array of PDF file paths\n- `options` (object, optional): Same as extractText\n\n**Returns:**\n- `results` (array): Array of extraction results\n- `totalPages` (number): Total pages across all PDFs\n- `successCount` (number): Successfully extracted\n- `failureCount` (number): Failed extractions\n- `errors` (array): Error details for failures\n\n### `countWords`\nCount words in extracted text.\n\n**Parameters:**\n- `text` (string, required): Text to count\n- `options` (object, optional):\n  - `minWordLength` (number): Minimum characters per word (default: 3)\n  - `excludeNumbers` (boolean): Don't count numbers as words\n  - `countByPage` (boolean): Return word count per page\n\n**Returns:**\n- `wordCount` (number): Total word count\n- `charCount` (number): Total character count\n- `pageCounts` (array): Word count per page\n- `averageWordsPerPage` (number): Average words per page\n\n### `detectLanguage`\nDetect the language of extracted text.\n\n**Parameters:**\n- `text` (string, required): Text to analyze\n- `minConfidence` (number): Minimum confidence for detection\n\n**Returns:**\n- `language` (string): Detected language code\n- `languageName` (string): Full language name\n- `confidence` (number): Confidence score (0-100)\n\n## Use Cases\n\n### Document Digitization\n- Convert paper documents to digital text\n- Process invoices and receipts\n- Digitize contracts and agreements\n- Archive physical documents\n\n### Content Analysis\n- Extract text for analysis tools\n- Prepare content for LLM processing\n- Clean up scanned documents\n- Parse PDF-based reports\n\n### Data Extraction\n- Extract data from PDF reports\n- Parse tables from PDFs\n- Pull structured data\n- Automate document workflows\n\n### Text Processing\n- Prepare content for translation\n- Clean up OCR output\n- Extract specific sections\n- Search within PDF content\n\n## Performance\n\n### Text-Based PDFs\n- **Speed:** ~100ms for 10-page PDF\n- **Accuracy:** 100% (exact text)\n- **Memory:** ~10MB for typical document\n\n### OCR Processing\n- **Speed:** ~1-3s per page (high quality)\n- **Accuracy:** 85-95% (depends on scan quality)\n- **Memory:** ~50-100MB peak during OCR\n\n## Technical Details\n\n### PDF Parsing\n- Uses native PDF.js library\n- Extracts text layer directly (no OCR needed)\n- Preserves document structure\n- Handles password-protected PDFs\n\n### OCR Engine\n- Tesseract.js under the hood\n- Supports 100+ languages\n- Adjustable quality\u002Fspeed tradeoff\n- Confidence scoring for accuracy\n\n### Dependencies\n- **ZERO external dependencies**\n- Uses Node.js built-in modules only\n- PDF.js included in skill\n- Tesseract.js bundled\n\n## Error Handling\n\n### Invalid PDF\n- Clear error message\n- Suggest fix (check file format)\n- Skip to next file in batch\n\n### OCR Failure\n- Report confidence score\n- Suggest rescan at higher quality\n- Fallback to basic extraction\n\n### Memory Issues\n- Stream processing for large files\n- Progress reporting\n- Graceful degradation\n\n## Configuration\n\n### Edit `config.json`:\n```json\n{\n  \"ocr\": {\n    \"enabled\": true,\n    \"defaultLanguage\": \"eng\",\n    \"quality\": \"medium\",\n    \"languages\": [\"eng\", \"spa\", \"fra\", \"deu\"]\n  },\n  \"output\": {\n    \"defaultFormat\": \"text\",\n    \"preserveFormatting\": true,\n    \"includeMetadata\": true\n  },\n  \"batch\": {\n    \"maxConcurrent\": 3,\n    \"timeoutSeconds\": 30\n  }\n}\n```\n\n## Examples\n\n### Extract from Invoice\n```javascript\nconst invoice = await extractText('.\u002Finvoice.pdf');\nconsole.log(invoice.text);\n\u002F\u002F \"INVOICE #12345 Date: 2026-02-04...\"\n```\n\n### Extract from Scanned Contract\n```javascript\nconst contract = await extractText('.\u002Fscanned-contract.pdf', {\n  ocr: true,\n  language: 'eng',\n  ocrQuality: 'high'\n});\nconsole.log(contract.text);\n\u002F\u002F \"AGREEMENT This contract between...\"\n```\n\n### Batch Process Documents\n```javascript\nconst docs = await extractBatch([\n  '.\u002Fdoc1.pdf',\n  '.\u002Fdoc2.pdf',\n  '.\u002Fdoc3.pdf',\n  '.\u002Fdoc4.pdf'\n]);\nconsole.log(`Processed ${docs.successCount}\u002F${docs.results.length} documents`);\n```\n\n## Troubleshooting\n\n### OCR Not Working\n- Check if PDF is truly scanned (not text-based)\n- Try different quality settings (low\u002Fmedium\u002Fhigh)\n- Ensure language matches document\n- Check image quality of scan\n\n### Extraction Returns Empty\n- PDF may be image-only\n- OCR failed with low confidence\n- Try different language setting\n\n### Slow Processing\n- Large PDF takes longer\n- Reduce quality for speed\n- Process in smaller batches\n\n## Tips\n\n### Best Results\n- Use text-based PDFs when possible (faster, 100% accurate)\n- High-quality scans for OCR (300 DPI+)\n- Clean background before scanning\n- Use correct language setting\n\n### Performance Optimization\n- Batch processing for multiple files\n- Disable OCR for text-based PDFs\n- Lower OCR quality for speed when acceptable\n\n## Roadmap\n\n- [ ] PDF\u002FA support\n- [ ] Advanced OCR pre-processing\n- [ ] Table extraction from OCR\n- [ ] Handwriting OCR\n- [ ] PDF form field extraction\n- [ ] Batch language detection\n- [ ] Confidence scoring visualization\n\n## License\n\nMIT\n\n---\n\n**Extract text from PDFs. Fast, accurate, zero dependencies.** ?\n",{"name":5,"metadata":46,"description":7},{"openclaw":47},{"tags":48,"author":51,"license":14,"version":52,"category":53},[49,34,25,37,31,50],"pdf","digitization","Vernox","1.0.0","tools","main","f4cb2d49f7667e79ef7804f50396d5aaffdf1f56","PDF及文件\u002Fpdf-text-extractor",1,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification","https:\u002F\u002Fgithub.com\u002FKernel8901","a little little little dobe in life but science geek","2026-04-05 16:43:56",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add Kernel8901\u002Fai-agent-skills-classification --skill pdf-text-extractor",{"tool":68,"command":69},"bunx","bunx skills add Kernel8901\u002Fai-agent-skills-classification --skill pdf-text-extractor",{"tool":71,"command":72},"pnpm","pnpm dlx skills add Kernel8901\u002Fai-agent-skills-classification --skill pdf-text-extractor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FPDF及文件\u002Fpdf-text-extractor\u002FSKILL.md",true,[76,82,86,92,96,100,104],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"_meta.json","REFERENCE","参考文档",296,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FPDF及文件\u002Fpdf-text-extractor\u002F_meta.json",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"config.json",362,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FPDF及文件\u002Fpdf-text-extractor\u002Fconfig.json",{"path":87,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":90,"sourceHtmlUrl":91},"index.js","SCRIPT","脚本",6965,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FPDF及文件\u002Fpdf-text-extractor\u002Findex.js",{"path":93,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":94,"sourceHtmlUrl":95},"package-lock.json",28528,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FPDF及文件\u002Fpdf-text-extractor\u002Fpackage-lock.json",{"path":97,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":98,"sourceHtmlUrl":99},"package.json",542,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FPDF及文件\u002Fpdf-text-extractor\u002Fpackage.json",{"path":101,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":102,"sourceHtmlUrl":103},"README.md",4281,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FPDF及文件\u002Fpdf-text-extractor\u002FREADME.md",{"path":105,"resourceType":88,"resourceTypeDesc":89,"sizeBytes":106,"sourceHtmlUrl":107},"test.js",2499,"https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002FPDF及文件\u002Fpdf-text-extractor\u002Ftest.js",[109,133,167,178,188,217],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":41},"01M6Q5R6WZ06RRB9RQTW54B34B","zyfai","Earn yield on any Ethereum wallet on Base, Arbitrum, and Plasma. Use when a user wants passive DeFi yield on their funds. Deploys a non-custodial subaccount (Safe) linked to their EOA, enables automated yield optimization, and lets them deposit\u002Fwithdraw anytime.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzyfai-sdk\u002FSKILL.md",[],[111,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132],"safe","ethereum","defi","Optimization","user","use","Wallet","base","deposit","withdraw","yield","arbitrum","non-custodial","passive","defi yield","earn","yield optimization",{"skillNo":134,"name":135,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":149,"publishedAt":41},"01M6Q5R337B5JSNER4P4YS03TN","zerion-api","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api\u002FSKILL.md",[138,141,144],{"categoryNo":139,"categoryName":140,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":142,"categoryName":143,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":145,"categoryName":146,"taxonomyType":147,"taxonomyTypeDesc":148},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[150,151,152,153,154,155,156,118,157,122,158,159,160,161,162,163,164,165,166],"api","zerion api","zerion","MCP","mcp server","server","blockchain","transactions","crypto wallet","crypto","evm","solana","query","across","positions","token","prices",{"skillNo":168,"name":169,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":175,"publishedAt":41},"01M6Q5QZFYTDAZMZ27BN5VZXAR","zerion-api-skill","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-skill\u002FSKILL.md",[172,173,174],{"categoryNo":139,"categoryName":140,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":142,"categoryName":143,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":145,"categoryName":146,"taxonomyType":147,"taxonomyTypeDesc":148},[150,176,177,151,152,153,154,155,156,118,157,122,159,160,161,162,163,164,165,166],"api skill","zerion api skill",{"skillNo":179,"name":180,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":186,"publishedAt":41},"01M6Q5QW17QW98RA3FE45E4RD8","zerion-api-mcp","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fzerion-api-mcp\u002FSKILL.md",[183,184,185],{"categoryNo":139,"categoryName":140,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":142,"categoryName":143,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":145,"categoryName":146,"taxonomyType":147,"taxonomyTypeDesc":148},[153,150,187,151,152,154,155,118,157,122,158,159,160,161,162,163,164,165,166],"zerion api mcp",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":197,"publishedAt":41},"01M6Q5QQYZB7A501BDEQWKGSJT","yahoo-finance-forex","Fetches real-time FOREX news and market data from Yahoo Finance for major currency pairs (EUR\u002FUSD, GBP\u002FUSD, USD\u002FJPY, etc.). Analyzes sentiment and provides trading context.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fyahoo-finance-forex\u002FSKILL.md",[194],{"categoryNo":195,"categoryName":196,"taxonomyType":147,"taxonomyTypeDesc":148},"01JBSEEDCAT000000000000040","财务",[198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,26],"finance","yahoo finance","forex","yahoo","yahoo finance forex","github","https","sentiment","real-time","python3","install","Market","usd","news","time","currency","gbp","pip","market data",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":224,"publishedAt":41},"01M6Q5QM6VS84WZVM7BKXXPF32","yahoo-finance","This skill should be used when the user asks to \"get stock prices\", \"check stock quotes\", \"look up earnings\", \"get financial data\", \"find trending stocks\", or needs stock market data from Yahoo Finance.","https:\u002F\u002Fgithub.com\u002FKernel8901\u002Fai-agent-skills-classification\u002Fblob\u002Fmain\u002F金融\u002Fyahoo-finance-cli\u002FSKILL.md",[223],{"categoryNo":195,"categoryName":196,"taxonomyType":147,"taxonomyTypeDesc":148},[198,199,201,225,226,227,228,229,230,209,231,232,233,234,235,236,237,238,166,216],"cli","homebrew","find","check","brew","up","local","get","stock","link","trending","sf","quotes","ln"]