[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HWW9058RN7621EBAC1ZBG2":3,"skill-same:01M6HWW9058RN7621EBAC1ZBG2":71},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":6,"updatedAt":50,"install":51,"resources":64},"01M6HWW9058RN7621EBAC1ZBG2","reliable-pdf-extraction",null,"Use shell commands or Python libraries to extract PDF text when read_file PDF handler 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\u002Freliable-pdf-extraction\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37],"PDF","extraction","pdf extraction","reliable pdf extraction","python","libraries","file","shell","text","read","extract","use","commands","extract pdf","2026-11-10 10:12:30",false,"---\nname: reliable-pdf-extraction\ndescription: Use shell commands or Python libraries to extract PDF text when read_file PDF handler fails\n---\n\n# Reliable PDF Text Extraction\n\n## Problem\n\nThe `read_file` tool with `filetype='pdf'` often returns binary image data, errors, or unusable output when attempting to extract text from PDF documents. This makes it unreliable for structured data extraction tasks.\n\n## Solution\n\nUse `run_shell` with command-line tools (`pdftotext`, `pdfinfo`) or `execute_code_sandbox` with Python libraries (PyMuPDF, pdfplumber) to extract PDF text content reliably.\n\n## Methods\n\n### Method 1: pdftotext (Recommended for simple extraction)\n\n```bash\n# Extract all text to stdout\npdftotext input.pdf -\n\n# Or extract to file\npdftotext input.pdf output.txt\ncat output.txt\n```\n\n### Method 2: pdfinfo (For metadata)\n\n```bash\npdfinfo input.pdf\n```\n\n### Method 3: Python with PyMuPDF (fitz)\n\n```python\nimport fitz  # PyMuPDF\n\ndoc = fitz.open(\"input.pdf\")\ntext = \"\"\nfor page in doc:\n    text += page.get_text()\nprint(text)\ndoc.close()\n```\n\n### Method 4: Python with pdfplumber (Better for tables\u002Fstructured data)\n\n```python\nimport pdfplumber\n\nwith pdfplumber.open(\"input.pdf\") as pdf:\n    for page in pdf.pages:\n        text = page.extract_text()\n        print(text)\n        # For tables:\n        # tables = page.extract_tables()\n```\n\n## Workflow\n\n1. **Attempt** `read_file` with `filetype='pdf'` first (in case it works)\n\n2. **Check output** - If you receive:\n   - Binary\u002Fgarbage data\n   - Error messages\n   - Empty or truncated content\n   - Image data instead of text\n\n3. **Fall back** to one of the extraction methods above:\n   - Use `pdftotext` via `run_shell` for quick text extraction\n   - Use `pdfplumber` via `execute_code_sandbox` for structured data\u002Ftables\n   - Use `PyMuPDF` for complex layouts or when you need more control\n\n4. **Process** the extracted text for your task\n\n## Example Usage\n\n```python\n# Via run_shell\nresult = run_shell(command=\"pdftotext document.pdf -\")\npdf_text = result.stdout\n\n# Via execute_code_sandbox\ncode = \"\"\"\nimport pdfplumber\nwith pdfplumber.open(\"\u002Fpath\u002Fto\u002Fdocument.pdf\") as pdf:\n    for page in pdf.pages:\n        print(page.extract_text())\n\"\"\"\nresult = execute_code_sandbox(code=code)\npdf_text = result.stdout\n```\n\n## Tips\n\n- **pdftotext** is fastest and most reliable for plain text extraction\n- **pdfplumber** excels at extracting tables and preserving layout\n- **PyMuPDF** offers the most control for complex PDF structures\n- Always check if the PDF is scanned\u002Fimage-based (may need OCR tools like `tesseract`)\n- Some PDFs have copy protection that may prevent text extraction","# Reliable PDF Text Extraction\n\n## Problem\n\nThe `read_file` tool with `filetype='pdf'` often returns binary image data, errors, or unusable output when attempting to extract text from PDF documents. This makes it unreliable for structured data extraction tasks.\n\n## Solution\n\nUse `run_shell` with command-line tools (`pdftotext`, `pdfinfo`) or `execute_code_sandbox` with Python libraries (PyMuPDF, pdfplumber) to extract PDF text content reliably.\n\n## Methods\n\n### Method 1: pdftotext (Recommended for simple extraction)\n\n```bash\n# Extract all text to stdout\npdftotext input.pdf -\n\n# Or extract to file\npdftotext input.pdf output.txt\ncat output.txt\n```\n\n### Method 2: pdfinfo (For metadata)\n\n```bash\npdfinfo input.pdf\n```\n\n### Method 3: Python with PyMuPDF (fitz)\n\n```python\nimport fitz  # PyMuPDF\n\ndoc = fitz.open(\"input.pdf\")\ntext = \"\"\nfor page in doc:\n    text += page.get_text()\nprint(text)\ndoc.close()\n```\n\n### Method 4: Python with pdfplumber (Better for tables\u002Fstructured data)\n\n```python\nimport pdfplumber\n\nwith pdfplumber.open(\"input.pdf\") as pdf:\n    for page in pdf.pages:\n        text = page.extract_text()\n        print(text)\n        # For tables:\n        # tables = page.extract_tables()\n```\n\n## Workflow\n\n1. **Attempt** `read_file` with `filetype='pdf'` first (in case it works)\n\n2. **Check output** - If you receive:\n   - Binary\u002Fgarbage data\n   - Error messages\n   - Empty or truncated content\n   - Image data instead of text\n\n3. **Fall back** to one of the extraction methods above:\n   - Use `pdftotext` via `run_shell` for quick text extraction\n   - Use `pdfplumber` via `execute_code_sandbox` for structured data\u002Ftables\n   - Use `PyMuPDF` for complex layouts or when you need more control\n\n4. **Process** the extracted text for your task\n\n## Example Usage\n\n```python\n# Via run_shell\nresult = run_shell(command=\"pdftotext document.pdf -\")\npdf_text = result.stdout\n\n# Via execute_code_sandbox\ncode = \"\"\"\nimport pdfplumber\nwith pdfplumber.open(\"\u002Fpath\u002Fto\u002Fdocument.pdf\") as pdf:\n    for page in pdf.pages:\n        print(page.extract_text())\n\"\"\"\nresult = execute_code_sandbox(code=code)\npdf_text = result.stdout\n```\n\n## Tips\n\n- **pdftotext** is fastest and most reliable for plain text extraction\n- **pdfplumber** excels at extracting tables and preserving layout\n- **PyMuPDF** offers the most control for complex PDF structures\n- Always check if the PDF is scanned\u002Fimage-based (may need OCR tools like `tesseract`)\n- Some PDFs have copy protection that may prevent text extraction",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Freliable-pdf-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":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add HKUDS\u002FAgentPilot --skill reliable-pdf-extraction",{"tool":57,"command":58},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill reliable-pdf-extraction",{"tool":60,"command":61},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill reliable-pdf-extraction","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Freliable-pdf-extraction\u002FSKILL.md",true,[65],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},".skill_id","OTHER","其他",37,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Freliable-pdf-extraction\u002F.skill_id",[72,91,110,133,157,178],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":38},"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",[],[74,79,80,81,82,83,84,85,35,86,87,88,89,90],"prepare","requests","with","missing","installation","rsi","up","user","work","SET","run","experiments",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":38},"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",[],[93,98,99,100,101,102,103,104,105,106,107,108,109],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":119,"publishedAt":38},"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",[116],{"categoryNo":117,"categoryName":118,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[120,121,122,101,123,124,125,126,127,128,129,130,131,132],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search","Tools",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":140,"publishedAt":38},"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",[139],{"categoryNo":117,"categoryName":118,"taxonomyType":21,"taxonomyTypeDesc":22},[141,142,143,101,144,145,146,147,148,122,100,35,149,150,151,152,153,154,155,156],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","tool","stack","for","share","tasks","automation","MCP",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":38},"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",[],[164,165,166,167,168,169,170,171,30,28,172,173,174,175,152,176,177],"write special chars ts check","write","check","type","files","filters","only","template","typescript","output","Existing","type-checking","errors","script",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":38},"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",[],[185,186,165,81,152,177,187,188,189,190,33,171,30,191,192,28],"write special chars readback","readback","helper","post","via","scripts","verification","cleanup"]