[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M756ZT72YHGS2ZGN6P45YNBY":3,"skill-same:01M756ZT72YHGS2ZGN6P45YNBY":86},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":14,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M756ZT72YHGS2ZGN6P45YNBY","ocr-and-documents",null,"Extract text from PDFs\u002Fscans (pymupdf, marker-pdf).","SatangThevalue\u002Fai-skills","SatangThevalue","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F17944930?v=4","01M756VHQQ58XSM5PDS03W79VY","Sa-Tang","01M756VHRNYXRY7HM230S4YHVV",0,"MIT","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Focr-and-documents\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: ocr-and-documents\ndescription: \"Extract text from PDFs\u002Fscans (pymupdf, marker-pdf).\"\nversion: 2.3.0\nauthor: Hermes Agent\nlicense: MIT\nplatforms: [linux, macos, windows]\nmetadata:\n  hermes:\n    reviewed: \\\"2026-06-01 (automated)\\\"\n    tags: [PDF, Documents, Research, Arxiv, Text-Extraction, OCR]\n    related_skills: [powerpoint]\n---\n\n# PDF & Document Extraction\n\nFor DOCX: use `python-docx` (parses actual document structure, far better than OCR).\nFor PPTX: see the `powerpoint` skill (uses `python-pptx` with full slide\u002Fnotes support).\nThis skill covers **PDFs and scanned documents**.\n\n## Step 1: Remote URL Available?\n\nIf the document has a URL, **always try `web_extract` first**:\n\n```\nweb_extract(urls=[\"https:\u002F\u002Farxiv.org\u002Fpdf\u002F2402.03300\"])\nweb_extract(urls=[\"https:\u002F\u002Fexample.com\u002Freport.pdf\"])\n```\n\nThis handles PDF-to-markdown conversion via Firecrawl with no local dependencies.\n\nOnly use local extraction when: the file is local, web_extract fails, or you need batch processing.\n\n## Step 2: Choose Local Extractor\n\n| Feature | pymupdf (~25MB) | marker-pdf (~3-5GB) |\n|---------|-----------------|---------------------|\n| **Text-based PDF** | ✅ | ✅ |\n| **Scanned PDF (OCR)** | ❌ | ✅ (90+ languages) |\n| **Tables** | ✅ (basic) | ✅ (high accuracy) |\n| **Equations \u002F LaTeX** | ❌ | ✅ |\n| **Code blocks** | ❌ | ✅ |\n| **Forms** | ❌ | ✅ |\n| **Headers\u002Ffooters removal** | ❌ | ✅ |\n| **Reading order detection** | ❌ | ✅ |\n| **Images extraction** | ✅ (embedded) | ✅ (with context) |\n| **Images → text (OCR)** | ❌ | ✅ |\n| **EPUB** | ✅ | ✅ |\n| **Markdown output** | ✅ (via pymupdf4llm) | ✅ (native, higher quality) |\n| **Install size** | ~25MB | ~3-5GB (PyTorch + models) |\n| **Speed** | Instant | ~1-14s\u002Fpage (CPU), ~0.2s\u002Fpage (GPU) |\n\n**Decision**: Use pymupdf unless you need OCR, equations, forms, or complex layout analysis.\n\nIf the user needs marker capabilities but the system lacks ~5GB free disk:\n> \"This document needs OCR\u002Fadvanced extraction (marker-pdf), which requires ~5GB for PyTorch and models. Your system has [X]GB free. Options: free up space, provide a URL so I can use web_extract, or I can try pymupdf which works for text-based PDFs but not scanned documents or equations.\"\n\n---\n\n## pymupdf (lightweight)\n\n```bash\npip install pymupdf pymupdf4llm\n```\n\n**Via helper script**:\n```bash\npython scripts\u002Fextract_pymupdf.py document.pdf              # Plain text\npython scripts\u002Fextract_pymupdf.py document.pdf --markdown    # Markdown\npython scripts\u002Fextract_pymupdf.py document.pdf --tables      # Tables\npython scripts\u002Fextract_pymupdf.py document.pdf --images out\u002F # Extract images\npython scripts\u002Fextract_pymupdf.py document.pdf --metadata    # Title, author, pages\npython scripts\u002Fextract_pymupdf.py document.pdf --pages 0-4   # Specific pages\n```\n\n**Inline**:\n```bash\npython3 -c \"\nimport pymupdf\ndoc = pymupdf.open('document.pdf')\nfor page in doc:\n    print(page.get_text())\n\"\n```\n\n---\n\n## marker-pdf (high-quality OCR)\n\n```bash\n# Check disk space first\npython scripts\u002Fextract_marker.py --check\n\npip install marker-pdf\n```\n\n**Via helper script**:\n```bash\npython scripts\u002Fextract_marker.py document.pdf                # Markdown\npython scripts\u002Fextract_marker.py document.pdf --json         # JSON with metadata\npython scripts\u002Fextract_marker.py document.pdf --output_dir out\u002F  # Save images\npython scripts\u002Fextract_marker.py scanned.pdf                 # Scanned PDF (OCR)\npython scripts\u002Fextract_marker.py document.pdf --use_llm      # LLM-boosted accuracy\n```\n\n**CLI** (installed with marker-pdf):\n```bash\nmarker_single document.pdf --output_dir .\u002Foutput\nmarker \u002Fpath\u002Fto\u002Ffolder --workers 4    # Batch\n```\n\n---\n\n## Arxiv Papers\n\n```\n# Abstract only (fast)\nweb_extract(urls=[\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.03300\"])\n\n# Full paper\nweb_extract(urls=[\"https:\u002F\u002Farxiv.org\u002Fpdf\u002F2402.03300\"])\n\n# Search\nweb_search(query=\"arxiv GRPO reinforcement learning 2026\")\n```\n\n## Split, Merge & Search\n\npymupdf handles these natively — use `execute_code` or inline Python:\n\n```python\n# Split: extract pages 1-5 to a new PDF\nimport pymupdf\ndoc = pymupdf.open(\"report.pdf\")\nnew = pymupdf.open()\nfor i in range(5):\n    new.insert_pdf(doc, from_page=i, to_page=i)\nnew.save(\"pages_1-5.pdf\")\n```\n\n```python\n# Merge multiple PDFs\nimport pymupdf\nresult = pymupdf.open()\nfor path in [\"a.pdf\", \"b.pdf\", \"c.pdf\"]:\n    result.insert_pdf(pymupdf.open(path))\nresult.save(\"merged.pdf\")\n```\n\n```python\n# Search for text across all pages\nimport pymupdf\ndoc = pymupdf.open(\"report.pdf\")\nfor i, page in enumerate(doc):\n    results = page.search_for(\"revenue\")\n    if results:\n        print(f\"Page {i+1}: {len(results)} match(es)\")\n        print(page.get_text(\"text\"))\n```\n\nNo extra dependencies needed — pymupdf covers split, merge, search, and text extraction in one package.\n\n---\n\n## Notes\n\n- `web_extract` is always first choice for URLs\n- pymupdf is the safe default — instant, no models, works everywhere\n- marker-pdf is for OCR, scanned docs, equations, complex layouts — install only when needed\n- Both helper scripts accept `--help` for full usage\n- marker-pdf downloads ~2.5GB of models to `~\u002F.cache\u002Fhuggingface\u002F` on first use\n- For Word docs: `pip install python-docx` (better than OCR — parses actual structure)\n- For PowerPoint: see the `powerpoint` skill (uses python-pptx)\n","# PDF & Document Extraction\n\nFor DOCX: use `python-docx` (parses actual document structure, far better than OCR).\nFor PPTX: see the `powerpoint` skill (uses `python-pptx` with full slide\u002Fnotes support).\nThis skill covers **PDFs and scanned documents**.\n\n## Step 1: Remote URL Available?\n\nIf the document has a URL, **always try `web_extract` first**:\n\n```\nweb_extract(urls=[\"https:\u002F\u002Farxiv.org\u002Fpdf\u002F2402.03300\"])\nweb_extract(urls=[\"https:\u002F\u002Fexample.com\u002Freport.pdf\"])\n```\n\nThis handles PDF-to-markdown conversion via Firecrawl with no local dependencies.\n\nOnly use local extraction when: the file is local, web_extract fails, or you need batch processing.\n\n## Step 2: Choose Local Extractor\n\n| Feature | pymupdf (~25MB) | marker-pdf (~3-5GB) |\n|---------|-----------------|---------------------|\n| **Text-based PDF** | ✅ | ✅ |\n| **Scanned PDF (OCR)** | ❌ | ✅ (90+ languages) |\n| **Tables** | ✅ (basic) | ✅ (high accuracy) |\n| **Equations \u002F LaTeX** | ❌ | ✅ |\n| **Code blocks** | ❌ | ✅ |\n| **Forms** | ❌ | ✅ |\n| **Headers\u002Ffooters removal** | ❌ | ✅ |\n| **Reading order detection** | ❌ | ✅ |\n| **Images extraction** | ✅ (embedded) | ✅ (with context) |\n| **Images → text (OCR)** | ❌ | ✅ |\n| **EPUB** | ✅ | ✅ |\n| **Markdown output** | ✅ (via pymupdf4llm) | ✅ (native, higher quality) |\n| **Install size** | ~25MB | ~3-5GB (PyTorch + models) |\n| **Speed** | Instant | ~1-14s\u002Fpage (CPU), ~0.2s\u002Fpage (GPU) |\n\n**Decision**: Use pymupdf unless you need OCR, equations, forms, or complex layout analysis.\n\nIf the user needs marker capabilities but the system lacks ~5GB free disk:\n> \"This document needs OCR\u002Fadvanced extraction (marker-pdf), which requires ~5GB for PyTorch and models. Your system has [X]GB free. Options: free up space, provide a URL so I can use web_extract, or I can try pymupdf which works for text-based PDFs but not scanned documents or equations.\"\n\n---\n\n## pymupdf (lightweight)\n\n```bash\npip install pymupdf pymupdf4llm\n```\n\n**Via helper script**:\n```bash\npython scripts\u002Fextract_pymupdf.py document.pdf              # Plain text\npython scripts\u002Fextract_pymupdf.py document.pdf --markdown    # Markdown\npython scripts\u002Fextract_pymupdf.py document.pdf --tables      # Tables\npython scripts\u002Fextract_pymupdf.py document.pdf --images out\u002F # Extract images\npython scripts\u002Fextract_pymupdf.py document.pdf --metadata    # Title, author, pages\npython scripts\u002Fextract_pymupdf.py document.pdf --pages 0-4   # Specific pages\n```\n\n**Inline**:\n```bash\npython3 -c \"\nimport pymupdf\ndoc = pymupdf.open('document.pdf')\nfor page in doc:\n    print(page.get_text())\n\"\n```\n\n---\n\n## marker-pdf (high-quality OCR)\n\n```bash\n# Check disk space first\npython scripts\u002Fextract_marker.py --check\n\npip install marker-pdf\n```\n\n**Via helper script**:\n```bash\npython scripts\u002Fextract_marker.py document.pdf                # Markdown\npython scripts\u002Fextract_marker.py document.pdf --json         # JSON with metadata\npython scripts\u002Fextract_marker.py document.pdf --output_dir out\u002F  # Save images\npython scripts\u002Fextract_marker.py scanned.pdf                 # Scanned PDF (OCR)\npython scripts\u002Fextract_marker.py document.pdf --use_llm      # LLM-boosted accuracy\n```\n\n**CLI** (installed with marker-pdf):\n```bash\nmarker_single document.pdf --output_dir .\u002Foutput\nmarker \u002Fpath\u002Fto\u002Ffolder --workers 4    # Batch\n```\n\n---\n\n## Arxiv Papers\n\n```\n# Abstract only (fast)\nweb_extract(urls=[\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2402.03300\"])\n\n# Full paper\nweb_extract(urls=[\"https:\u002F\u002Farxiv.org\u002Fpdf\u002F2402.03300\"])\n\n# Search\nweb_search(query=\"arxiv GRPO reinforcement learning 2026\")\n```\n\n## Split, Merge & Search\n\npymupdf handles these natively — use `execute_code` or inline Python:\n\n```python\n# Split: extract pages 1-5 to a new PDF\nimport pymupdf\ndoc = pymupdf.open(\"report.pdf\")\nnew = pymupdf.open()\nfor i in range(5):\n    new.insert_pdf(doc, from_page=i, to_page=i)\nnew.save(\"pages_1-5.pdf\")\n```\n\n```python\n# Merge multiple PDFs\nimport pymupdf\nresult = pymupdf.open()\nfor path in [\"a.pdf\", \"b.pdf\", \"c.pdf\"]:\n    result.insert_pdf(pymupdf.open(path))\nresult.save(\"merged.pdf\")\n```\n\n```python\n# Search for text across all pages\nimport pymupdf\ndoc = pymupdf.open(\"report.pdf\")\nfor i, page in enumerate(doc):\n    results = page.search_for(\"revenue\")\n    if results:\n        print(f\"Page {i+1}: {len(results)} match(es)\")\n        print(page.get_text(\"text\"))\n```\n\nNo extra dependencies needed — pymupdf covers split, merge, search, and text extraction in one package.\n\n---\n\n## Notes\n\n- `web_extract` is always first choice for URLs\n- pymupdf is the safe default — instant, no models, works everywhere\n- marker-pdf is for OCR, scanned docs, equations, complex layouts — install only when needed\n- Both helper scripts accept `--help` for full usage\n- marker-pdf downloads ~2.5GB of models to `~\u002F.cache\u002Fhuggingface\u002F` on first use\n- For Word docs: `pip install python-docx` (better than OCR — parses actual structure)\n- For PowerPoint: see the `powerpoint` skill (uses python-pptx)\n",{"name":5,"author":24,"license":15,"version":25,"metadata":26,"platforms":38,"description":7},"Hermes Agent","2.3.0",{"hermes":27},{"tags":28,"reviewed":35,"related_skills":36},[29,30,31,32,33,34],"PDF","Documents","Research","Arxiv","Text-Extraction","OCR","\\\"2026-06-01 (automated)\\\"",[37],"powerpoint",[39,40,41],"linux","macos","windows","main","236825fbf4e5956a8cd2b0bf843494f0a5dfaf04","skills\u002F.archive\u002Focr-and-documents","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills","https:\u002F\u002Fgithub.com\u002FSatangThevalue","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fsatangthevalue\u002F","Hi, I'm Sa-Tang. 🖐️🖐️🖐️\r\nThanks for following.\r\nสวัสดีครับ สตังค์ครับผม\r\nขอบคุณหรับการติดตามครับ","2026-10-10 12:10:40",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add SatangThevalue\u002Fai-skills --skill ocr-and-documents",{"tool":56,"command":57},"bunx","bunx skills add SatangThevalue\u002Fai-skills --skill ocr-and-documents",{"tool":59,"command":60},"pnpm","pnpm dlx skills add SatangThevalue\u002Fai-skills --skill ocr-and-documents","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Focr-and-documents\u002FSKILL.md",true,[64,70,76,80],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"DESCRIPTION.md","REFERENCE","参考文档",147,"https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Focr-and-documents\u002FDESCRIPTION.md",{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"scripts\u002Fextract_marker.py","SCRIPT","脚本",3034,"https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Focr-and-documents\u002Fscripts\u002Fextract_marker.py",{"path":77,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":78,"sourceHtmlUrl":79},"scripts\u002Fextract_pymupdf.py",3132,"https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Focr-and-documents\u002Fscripts\u002Fextract_pymupdf.py",{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"SKILL.md.bak","OTHER","其他",5280,"https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002F.archive\u002Focr-and-documents\u002FSKILL.md.bak",[87,94,101,108,115,122],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M76TQY0W54NCMRVE9HB8MMTA","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fwriting-plans\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M76TNN9AYY91KD4DT415K1FF","subagent-driven-development","Execute plans via delegate_task subagents (2-stage review).","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fsubagent-driven-development\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M76TME6SXP9SYJZCXX5FFZHR","react-composition-2026","Teaches modern React composition patterns for 2025\u002F2026. Use when designing component APIs, building shared UI libraries, or refactoring prop-heavy components.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Freact-composition-2026\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M76TMAR2D5G9BKZWGEFJKWT2","react-2026","Provides a comprehensive guide to the modern React 2026 stack. Use when starting a new React project or modernizing an existing one with current frameworks, build tools, routing, state management, or AI integration.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Freact-2026\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":19},"01M76TM2FA8ZFZR1S6ZM34WFFK","plan","Plan mode: write markdown plan to .hermes\u002Fplans\u002F, no exec.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fplan\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":19},"01M76TJVNAWDZ7DYQK3ZS0X09J","hermes-s6-container-supervision","Modify, debug, or extend the s6-overlay supervision tree inside the Hermes Agent Docker image — adding new services, debugging profile gateways, understanding the Architecture B main-program pattern.","https:\u002F\u002Fgithub.com\u002FSatangThevalue\u002Fai-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsoftware-development\u002Fhermes-s6-container-supervision\u002FSKILL.md",[],[]]