[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KFTJDC2W4R99CC8XECKX0D":3,"skill-same:01M6KFTJDC2W4R99CC8XECKX0D":62},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":45,"ownerHtmlUrl":46,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M6KFTJDC2W4R99CC8XECKX0D","run2_pdf-text-extraction",null,"Extract text from PDF files using PyPDF2 with pdfplumber fallback; optimized for title\u002Fabstract extraction for classification.","cxcscmu\u002FSkillLearnBench","cxcscmu","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F142838272?v=4","01M6KCQDFQWPDSN0MKZY96MSQP","01M6KCQDM7G70TKJ28NTSQC0RZ",93,"MIT","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fb2-self-feedback-claude-sonnet-4-6\u002Forganize-messy-files\u002Frun2_pdf-text-extraction\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],"PDF","extraction","text","pdf text extraction","run2 pdf text extraction","classification","extract","files","fallback","with","pdfplumber","for","2026-11-10 10:12:30",false,"---\nname: run2_pdf-text-extraction\ndescription: Extract text from PDF files using PyPDF2 with pdfplumber fallback; optimized for title\u002Fabstract extraction for classification.\n---\n\n# PDF Text Extraction Skill (Improved)\n\n## Overview\nExtract text from PDF files for content analysis. The first 3-4 pages contain title, abstract, and introduction — sufficient for classification.\n\n## Installation\n```bash\npip install PyPDF2 pdfplumber --break-system-packages\n```\n\n## Key Insight\n- PyPDF2 is faster but may miss some text\n- pdfplumber handles complex layouts better\n- For classification, extracting title + abstract (first 2 pages) is usually sufficient\n- Always use both libraries with fallback for robustness\n\n## Robust Extraction Function\n```python\nimport PyPDF2\nimport pdfplumber\n\ndef extract_pdf_text(filepath, max_pages=4):\n    \"\"\"Extract text from PDF, trying PyPDF2 first, then pdfplumber fallback.\"\"\"\n    text = \"\"\n    try:\n        with open(filepath, 'rb') as f:\n            reader = PyPDF2.PdfReader(f)\n            for page in reader.pages[:max_pages]:\n                try:\n                    page_text = page.extract_text()\n                    if page_text:\n                        text += page_text + \"\\n\"\n                except:\n                    pass\n    except Exception:\n        pass\n\n    # If PyPDF2 didn't get much, try pdfplumber\n    if len(text.strip()) \u003C 200:\n        try:\n            with pdfplumber.open(filepath) as pdf:\n                for page in pdf.pages[:max_pages]:\n                    try:\n                        page_text = page.extract_text()\n                        if page_text:\n                            text += page_text + \"\\n\"\n                    except:\n                        pass\n        except Exception:\n            pass\n\n    return text\n```\n\n## Notes\n- Some PDFs with score=0 may need manual review — check the title from the first few lines\n- arXiv PDFs generally work well with both libraries\n- PDFs with equations may have garbled text but keywords like \"trapped ion\", \"DNA\" still appear\n","# PDF Text Extraction Skill (Improved)\n\n## Overview\nExtract text from PDF files for content analysis. The first 3-4 pages contain title, abstract, and introduction — sufficient for classification.\n\n## Installation\n```bash\npip install PyPDF2 pdfplumber --break-system-packages\n```\n\n## Key Insight\n- PyPDF2 is faster but may miss some text\n- pdfplumber handles complex layouts better\n- For classification, extracting title + abstract (first 2 pages) is usually sufficient\n- Always use both libraries with fallback for robustness\n\n## Robust Extraction Function\n```python\nimport PyPDF2\nimport pdfplumber\n\ndef extract_pdf_text(filepath, max_pages=4):\n    \"\"\"Extract text from PDF, trying PyPDF2 first, then pdfplumber fallback.\"\"\"\n    text = \"\"\n    try:\n        with open(filepath, 'rb') as f:\n            reader = PyPDF2.PdfReader(f)\n            for page in reader.pages[:max_pages]:\n                try:\n                    page_text = page.extract_text()\n                    if page_text:\n                        text += page_text + \"\\n\"\n                except:\n                    pass\n    except Exception:\n        pass\n\n    # If PyPDF2 didn't get much, try pdfplumber\n    if len(text.strip()) \u003C 200:\n        try:\n            with pdfplumber.open(filepath) as pdf:\n                for page in pdf.pages[:max_pages]:\n                    try:\n                        page_text = page.extract_text()\n                        if page_text:\n                            text += page_text + \"\\n\"\n                    except:\n                        pass\n        except Exception:\n            pass\n\n    return text\n```\n\n## Notes\n- Some PDFs with score=0 may need manual review — check the title from the first few lines\n- arXiv PDFs generally work well with both libraries\n- PDFs with equations may have garbled text but keywords like \"trapped ion\", \"DNA\" still appear\n",{"name":5,"description":7},"main","726e1f79b96b0cb3d729d0e55a1c847e0b5353ae","skills\u002Fb2-self-feedback-claude-sonnet-4-6\u002Forganize-messy-files\u002Frun2_pdf-text-extraction",8,"https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench","https:\u002F\u002Fcxcscmu.github.io\u002FSkillLearnBench","https:\u002F\u002Fgithub.com\u002Fcxcscmu","2026-10-02 22:55:36",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add cxcscmu\u002FSkillLearnBench --skill run2_pdf-text-extraction",{"tool":54,"command":55},"bunx","bunx skills add cxcscmu\u002FSkillLearnBench --skill run2_pdf-text-extraction",{"tool":57,"command":58},"pnpm","pnpm dlx skills add cxcscmu\u002FSkillLearnBench --skill run2_pdf-text-extraction","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fb2-self-feedback-claude-sonnet-4-6\u002Forganize-messy-files\u002Frun2_pdf-text-extraction\u002FSKILL.md",true,[],[63,79,103,121,141,153],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":72,"publishedAt":35},"01M6KM5KH175P5ABP5JMX2SBDQ","object_counter","Count occurrences of an object in the image using computer vision algorithm.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Fvideo-object-counting\u002Fobject_counter\u002FSKILL.md",[69],{"categoryNo":70,"categoryName":71,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",[73,74,75,76,77,78],"object counter","object","vision","computer","Computer Vision","image",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":88,"publishedAt":35},"01M6KM51TMVXG79MMPCS6Y8G86","travel-planning-workflow","Invoke this skill when performing travel planning. It defines a structured workflow for generating itineraries. Following this workflow is essential to ensure the final plan satisfies user requirements.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftravel-planning\u002Ftravel-planning-workflow\u002FSKILL.md",[85],{"categoryNo":86,"categoryName":87,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[89,90,91,92,93,94,95,96,97,34,98,99,100,101,102],"workflow","planning","planning workflow","travel","travel planning","travel planning workflow","structured","performing","plan","user","it","requirements","essential","itineraries",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":35},"01M6KM4DY820XHS9YTSK5QP5HD","bundled-dataset-search-tool","invoke this skill when you need to perform database search for travel planning. This skill provides some useful pre-packaged tools to look up accommodations, attractions, cities, driving distance, flights, and restaurants from the bundled dataset.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftravel-planning\u002Fbundled-dataset-search-tool\u002FSKILL.md",[],[110,111,112,113,114,115,116,92,117,118,93,119,34,120,90],"search","tool","dataset","bundled dataset search tool","restaurants","Tools","up","look","flights","you","database",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":35},"01M6KM465BB9PQ0B548HQSVAWZ","glm-output","Output-processing guidance for GLM tasks. Especially useful after glm-basics and glm-calibration when you need verifier-matching metrics from output.nc and a final \u002Froot\u002Fmetrics.json.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-output\u002FSKILL.md",[],[128,129,130,34,131,132,133,134,135,136,137,138,119,139,140],"glm output","output","glm","tasks","metrics","json","basics","guidance","matching","verifier","processing","root","calibration",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":148,"publishedAt":35},"01M6KM40KY3QWDW5W97S39R2BC","glm-calibration","Calibration guidance for GLM tasks. Often most effective after glm-basics has clarified the setup; glm-output is the companion skill for exact final metric computation.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-calibration\u002FSKILL.md",[147],{"categoryNo":86,"categoryName":87,"taxonomyType":20,"taxonomyTypeDesc":21},[149,140,130,129,135,134,131,150,151,34,152],"glm calibration","setup","companion","metric",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":35},"01M6KM3VHHVSGMGHJQB3PPT6YG","glm-basics","A good starting point for GLM calibration tasks. Use to inspect glm3.nml, confirm how GLM runs, and identify the relevant files before moving on to calibration and output evaluation.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-basics\u002FSKILL.md",[],[160,130,134,161,149,140,34,129,162,30,163,164,165,166,131],"glm basics","inspect","relevant","good","use","how","Evaluation"]