[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HWQMBYQWADQF039FP8CQ74":3,"skill-same:01M6HWQMBYQWADQF039FP8CQ74":66},{"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":23,"publishedAt":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":44,"ownerDescription":6,"updatedAt":45,"install":46,"resources":59},"01M6HWQMBYQWADQF039FP8CQ74","pdf-text-extraction",null,"Extract text from PDFs using shell tools when read_file fails","HKUDS\u002FAgentPilot","HKUDS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F118165258?v=4","01M6HW8VRNZP64G0P4MVJW2KKQ","✨Data Intelligence Lab@HKU✨","01M6HW8VWZVHBRHYH3T330PFWV",8029,"MIT","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fpdf-text-extraction\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32],"PDF","extraction","text","pdf text extraction","file","Tools","shell","read","extract","2026-11-10 10:12:30",false,"---\nname: pdf-text-extraction\ndescription: Extract text from PDFs using shell tools when read_file fails\n---\n\n# PDF Text Extraction (Fallback Method)\n\n## When to Use This Skill\n\nUse this skill when `read_file` with `filetype='pdf'`:\n- Returns binary image data instead of text\n- Produces errors or incomplete content\n- Fails to extract structured data reliably\n\nThe built-in PDF handler is unreliable for structured text extraction. Shell-based tools provide more robust alternatives.\n\n## Available Methods\n\n### Method 1: pdftotext (Recommended)\n\n```bash\n# Extract text from PDF to stdout\npdftotext \u002Fpath\u002Fto\u002Ffile.pdf -\n\n# Extract text to a file\npdftotext \u002Fpath\u002Fto\u002Ffile.pdf output.txt\n\n# Preserve layout (maintains spacing\u002Fstructure)\npdftotext -layout \u002Fpath\u002Fto\u002Ffile.pdf output.txt\n```\n\n**Usage in agent:**\n```bash\nrun_shell command=\"pdftotext -layout \u002Fpath\u002Fto\u002Fdocument.pdf -\"\n```\n\n### Method 2: pdfinfo (Metadata)\n\n```bash\n# Get PDF metadata (pages, author, creation date, etc.)\npdfinfo \u002Fpath\u002Fto\u002Ffile.pdf\n```\n\n**Usage in agent:**\n```bash\nrun_shell command=\"pdfinfo \u002Fpath\u002Fto\u002Fdocument.pdf\"\n```\n\n### Method 3: Python with PyMuPDF (fitz)\n\n```python\nimport fitz  # PyMuPDF\n\ndoc = fitz.open(\"\u002Fpath\u002Fto\u002Ffile.pdf\")\ntext = \"\"\nfor page in doc:\n    text += page.get_text()\ndoc.close()\nprint(text)\n```\n\n**Usage in agent:**\n```bash\nrun_shell command=\"python3 -c \\\"import fitz; doc=fitz.open('file.pdf'); print(''.join(p.get_text() for p in doc))\\\"\"\n```\n\n### Method 4: Python with pdfplumber (Tables)\n\n```python\nimport pdfplumber\n\nwith pdfplumber.open(\"\u002Fpath\u002Fto\u002Ffile.pdf\") as pdf:\n    for page in pdf.pages:\n        text = page.extract_text()\n        tables = page.extract_tables()  # For tabular data\n```\n\n**Usage in agent:**\n```bash\nrun_shell command=\"python3 -c \\\"import pdfplumber; pdf=pdfplumber.open('file.pdf'); print(''.join(p.extract_text() or '' for p in pdf.pages))\\\"\"\n```\n\n## Workflow\n\n1. **Try pdftotext first** - Fastest and most reliable for plain text\n   ```bash\n   run_shell command=\"pdftotext -layout \u002Fpath\u002Fto\u002Ffile.pdf -\"\n   ```\n\n2. **If pdftotext unavailable, check for Python libraries**\n   ```bash\n   run_shell command=\"python3 -c \\\"import fitz; print('PyMuPDF available')\\\"\"\n   ```\n\n3. **For table\u002Fstructured data, use pdfplumber**\n   ```bash\n   run_shell command=\"python3 -c \\\"import pdfplumber; ...\\\"\"\n   ```\n\n4. **Verify extraction succeeded** - Check output contains readable text, not binary data\n\n## Installation Notes\n\nIf tools are not available:\n```bash\n# Ubuntu\u002FDebian\napt-get install poppler-utils  # pdftotext, pdfinfo\n\n# Install Python libraries\npip install pymupdf pdfplumber\n```\n\n## Anti-Patterns to Avoid\n\n- Do NOT rely solely on `read_file` with `filetype='pdf'` for critical text extraction\n- Do NOT assume PDF text is in any particular order - verify extracted content\n- Do NOT use image-based extraction unless the PDF is scanned (use OCR instead)\n\n## Example: Complete Extraction Pattern\n\n```bash\n# Step 1: Try pdftotext\nRESULT=$(pdftotext -layout \u002Fpath\u002Fto\u002Fform.pdf - 2>\u002Fdev\u002Fnull)\n\n# Step 2: Verify we got text, not error\nif [ -z \"$RESULT\" ]; then\n    # Fallback to Python\n    RESULT=$(python3 -c \"import fitz; doc=fitz.open('\u002Fpath\u002Fto\u002Fform.pdf'); print(''.join(p.get_text() for p in doc))\")\nfi\n\n# Step 3: Use extracted text\necho \"$RESULT\"\n```","# PDF Text Extraction (Fallback Method)\n\n## When to Use This Skill\n\nUse this skill when `read_file` with `filetype='pdf'`:\n- Returns binary image data instead of text\n- Produces errors or incomplete content\n- Fails to extract structured data reliably\n\nThe built-in PDF handler is unreliable for structured text extraction. Shell-based tools provide more robust alternatives.\n\n## Available Methods\n\n### Method 1: pdftotext (Recommended)\n\n```bash\n# Extract text from PDF to stdout\npdftotext \u002Fpath\u002Fto\u002Ffile.pdf -\n\n# Extract text to a file\npdftotext \u002Fpath\u002Fto\u002Ffile.pdf output.txt\n\n# Preserve layout (maintains spacing\u002Fstructure)\npdftotext -layout \u002Fpath\u002Fto\u002Ffile.pdf output.txt\n```\n\n**Usage in agent:**\n```bash\nrun_shell command=\"pdftotext -layout \u002Fpath\u002Fto\u002Fdocument.pdf -\"\n```\n\n### Method 2: pdfinfo (Metadata)\n\n```bash\n# Get PDF metadata (pages, author, creation date, etc.)\npdfinfo \u002Fpath\u002Fto\u002Ffile.pdf\n```\n\n**Usage in agent:**\n```bash\nrun_shell command=\"pdfinfo \u002Fpath\u002Fto\u002Fdocument.pdf\"\n```\n\n### Method 3: Python with PyMuPDF (fitz)\n\n```python\nimport fitz  # PyMuPDF\n\ndoc = fitz.open(\"\u002Fpath\u002Fto\u002Ffile.pdf\")\ntext = \"\"\nfor page in doc:\n    text += page.get_text()\ndoc.close()\nprint(text)\n```\n\n**Usage in agent:**\n```bash\nrun_shell command=\"python3 -c \\\"import fitz; doc=fitz.open('file.pdf'); print(''.join(p.get_text() for p in doc))\\\"\"\n```\n\n### Method 4: Python with pdfplumber (Tables)\n\n```python\nimport pdfplumber\n\nwith pdfplumber.open(\"\u002Fpath\u002Fto\u002Ffile.pdf\") as pdf:\n    for page in pdf.pages:\n        text = page.extract_text()\n        tables = page.extract_tables()  # For tabular data\n```\n\n**Usage in agent:**\n```bash\nrun_shell command=\"python3 -c \\\"import pdfplumber; pdf=pdfplumber.open('file.pdf'); print(''.join(p.extract_text() or '' for p in pdf.pages))\\\"\"\n```\n\n## Workflow\n\n1. **Try pdftotext first** - Fastest and most reliable for plain text\n   ```bash\n   run_shell command=\"pdftotext -layout \u002Fpath\u002Fto\u002Ffile.pdf -\"\n   ```\n\n2. **If pdftotext unavailable, check for Python libraries**\n   ```bash\n   run_shell command=\"python3 -c \\\"import fitz; print('PyMuPDF available')\\\"\"\n   ```\n\n3. **For table\u002Fstructured data, use pdfplumber**\n   ```bash\n   run_shell command=\"python3 -c \\\"import pdfplumber; ...\\\"\"\n   ```\n\n4. **Verify extraction succeeded** - Check output contains readable text, not binary data\n\n## Installation Notes\n\nIf tools are not available:\n```bash\n# Ubuntu\u002FDebian\napt-get install poppler-utils  # pdftotext, pdfinfo\n\n# Install Python libraries\npip install pymupdf pdfplumber\n```\n\n## Anti-Patterns to Avoid\n\n- Do NOT rely solely on `read_file` with `filetype='pdf'` for critical text extraction\n- Do NOT assume PDF text is in any particular order - verify extracted content\n- Do NOT use image-based extraction unless the PDF is scanned (use OCR instead)\n\n## Example: Complete Extraction Pattern\n\n```bash\n# Step 1: Try pdftotext\nRESULT=$(pdftotext -layout \u002Fpath\u002Fto\u002Fform.pdf - 2>\u002Fdev\u002Fnull)\n\n# Step 2: Verify we got text, not error\nif [ -z \"$RESULT\" ]; then\n    # Fallback to Python\n    RESULT=$(python3 -c \"import fitz; doc=fitz.open('\u002Fpath\u002Fto\u002Fform.pdf'); print(''.join(p.get_text() for p in doc))\")\nfi\n\n# Step 3: Use extracted text\necho \"$RESULT\"\n```",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fpdf-text-extraction",944,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot","https:\u002F\u002Fgithub.com\u002FHKUDS","https:\u002F\u002Fsites.google.com\u002Fview\u002Fchaoh","2026-11-12 22:26:39",{"source":8,"skillName":5,"commands":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add HKUDS\u002FAgentPilot --skill pdf-text-extraction",{"tool":52,"command":53},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill pdf-text-extraction",{"tool":55,"command":56},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill pdf-text-extraction","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fpdf-text-extraction\u002FSKILL.md",true,[60],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},".skill_id","OTHER","其他",33,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fpdf-text-extraction\u002F.skill_id",[67,87,106,128,152,174],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":33},"01M6HYB297NDABRERJRVG0K8R0","agentpilot","Set up AgentPilot and use its single entry to prepare missing inputs and run configured RSI experiments. Use when the user requests AgentPilot installation or work with AgentPilot.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fplugins\u002Fagentpilot\u002Fskills\u002Fagentpilot\u002FSKILL.md",[],[69,74,75,76,77,78,79,80,81,82,83,84,85,86],"prepare","requests","with","missing","installation","rsi","up","use","user","work","SET","run","experiments",{"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":33},"01M6HYAYWXTTE1J7DJM0MFNQ4H","remember","Review auto-memory entries and propose promotions to OPENSPACE.md, OPENSPACE.local.md, or retained auto-memory topics; detect duplicates, stale facts, conflicts, and ambiguous entries before making changes.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fskills\u002Fremember\u002FSKILL.md",[],[89,94,95,96,97,98,99,100,101,102,103,104,105],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":115,"publishedAt":33},"01M6HYAVMPM4SBDV60R2B5HPV8","skill-discovery","Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fhost_skills\u002Fskill-discovery\u002FSKILL.md",[112],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[116,117,118,97,119,120,121,122,123,124,125,126,127,29],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":135,"publishedAt":33},"01M6HYAR811B3RB0M50RBEDGN6","delegate-task","Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and skill library. Skills auto-improve through use, reducing token consumption over time. A cloud community lets agents share and collectively evolve reusable skills.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fhost_skills\u002Fdelegate-task\u002FSKILL.md",[134],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},[136,137,138,97,139,140,141,142,143,118,96,81,144,145,146,147,148,149,150,151],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","tool","stack","for","share","tasks","automation","MCP",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":33},"01M6HYAM9FSGV6E52AYENDQXYH","write-special-chars-ts-check","Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, plus a reliable TypeScript type-checking step that filters output to only the newly-written files to avoid being misled by pre-existing errors.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fshowcase\u002Fskills\u002Fwrite-special-chars-ts-check\u002FSKILL.md",[],[159,160,161,162,163,164,165,166,28,167,168,169,170,171,147,172,173],"write special chars ts check","write","check","type","files","filters","only","template","python","typescript","output","Existing","type-checking","errors","script",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":33},"01M6HYAH05HGV7SVWSVR8PJRQD","write-special-chars-readback","Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, with mandatory post-write verification via read_file and cleanup of \u002Ftmp helper scripts.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fshowcase\u002Fskills\u002Fwrite-special-chars-readback\u002FSKILL.md",[],[181,182,160,76,147,173,183,184,185,186,31,166,28,187,188,167],"write special chars readback","readback","helper","post","via","scripts","verification","cleanup"]