[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HWE8HM62CD885860MJ6CXG":3,"skill-same:01M6HWE8HM62CD885860MJ6CXG":73},{"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":28,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":6,"ownerHtmlUrl":50,"ownerBlogUrl":51,"ownerDescription":6,"updatedAt":52,"install":53,"resources":66},"01M6HWE8HM62CD885860MJ6CXG","docx-shell-workaround",null,"Handle docx files using shell-based XML extraction and python-docx via run_shell when standard tools fail","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\u002Fdocx-shell-workaround\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39],"docx","shell","docx shell workaround","python","run","extraction","xml","Tools","files","via","python-docx","2026-11-10 10:12:30",false,"---\nname: docx-shell-workaround\ndescription: Handle docx files using shell-based XML extraction and python-docx via run_shell when standard tools fail\n---\n\n# DOCX Shell Workaround\n\n## When to Use\n\nUse this skill when:\n- `read_file` cannot extract content from .docx files\n- `execute_code_sandbox` encounters failures when creating or modifying docx files\n- You need a reliable fallback for docx file manipulation\n\n## Reading DOCX Files\n\n### Step 1: Extract document.xml using unzip\n\nUse `run_shell` to unzip the .docx file (which is a ZIP archive) and extract the main document XML:\n\n```bash\nunzip -p input.docx word\u002Fdocument.xml > document.xml\n```\n\n### Step 2: Parse XML with ElementTree via run_shell\n\nExtract text content by parsing the XML. Use `run_shell` to execute Python code:\n\n```bash\npython3 \u003C\u003C 'EOF'\nimport xml.etree.ElementTree as ET\n\ntree = ET.parse('document.xml')\nroot = tree.getroot()\nnamespace = {'w': 'http:\u002F\u002Fschemas.openxmlformats.org\u002Fwordprocessingml\u002F2006\u002Fmain'}\n\ntext_content = []\nfor elem in root.iter():\n    if elem.tag.endswith('t'):\n        if elem.text:\n            text_content.append(elem.text)\n\ntext = ''.join(text_content)\nprint(text)\nEOF\n```\n\n### Step 3: Optional - More robust XML parsing\n\nFor better text extraction that handles paragraphs:\n\n```bash\npython3 \u003C\u003C 'EOF'\nimport xml.etree.ElementTree as ET\n\ntree = ET.parse('document.xml')\nroot = tree.getroot()\nns = {'w': 'http:\u002F\u002Fschemas.openxmlformats.org\u002Fwordprocessingml\u002F2006\u002Fmain'}\n\nparagraphs = []\nfor p in root.findall('.\u002F\u002Fw:p', ns):\n    para_text = []\n    for t in p.findall('.\u002F\u002Fw:t', ns):\n        if t.text:\n            para_text.append(t.text)\n    if para_text:\n        paragraphs.append(''.join(para_text))\n\nfor para in paragraphs:\n    print(para)\nEOF\n```\n\n## Creating DOCX Files\n\n### Use python-docx via run_shell (NOT execute_code_sandbox)\n\nWhen `execute_code_sandbox` fails for docx operations, use `run_shell` instead:\n\n```bash\npython3 \u003C\u003C 'EOF'\nfrom docx import Document\nfrom docx.shared import Inches, Pt\nfrom docx.enum.text import WD_ALIGN_PARAGRAPH\n\ndoc = Document()\n\n# Add heading\ndoc.add_heading('Document Title', 0)\n\n# Add paragraph\ndoc.add_paragraph('Your content here.')\n\n# Add section with heading\ndoc.add_heading('Section Title', level=1)\ndoc.add_paragraph('Section content with multiple paragraphs.')\n\n# Add table if needed\ntable = doc.add_table(rows=3, cols=3)\ntable.style = 'Table Grid'\n\n# Save document\ndoc.save('output.docx')\nprint(\"Document created successfully\")\nEOF\n```\n\n### Example: Creating a structured business document\n\n```bash\npython3 \u003C\u003C 'EOF'\nfrom docx import Document\nfrom docx.shared import Pt\n\ndoc = Document()\n\n# Title\ntitle = doc.add_heading('Business Strategy Memo', 0)\ntitle.alignment = 1  # Center\n\n# Executive Summary\ndoc.add_heading('Executive Summary', level=1)\ndoc.add_paragraph('Brief overview of key points and recommendations.')\n\n# Market Overview\ndoc.add_heading('Market Overview', level=1)\ndoc.add_paragraph('Analysis of current market conditions and trends.')\n\n# Recommendations\ndoc.add_heading('Recommendations', level=1)\ndoc.add_paragraph('Actionable recommendations based on analysis.')\n\ndoc.save('Strategy_Memo.docx')\nEOF\n```\n\n## Full Workflow Example\n\nComplete example showing extraction and creation:\n\n```bash\n# Step 1: Extract content from existing docx\nunzip -p existing.docx word\u002Fdocument.xml > doc.xml\n\n# Step 2: Parse and transform content\npython3 \u003C\u003C 'EOF'\nimport xml.etree.ElementTree as ET\n\ntree = ET.parse('doc.xml')\nroot = tree.getroot()\nns = {'w': 'http:\u002F\u002Fschemas.openxmlformats.org\u002Fwordprocessingml\u002F2006\u002Fmain'}\n\ncontent = []\nfor p in root.findall('.\u002F\u002Fw:p', ns):\n    para_text = []\n    for t in p.findall('.\u002F\u002Fw:t', ns):\n        if t.text:\n            para_text.append(t.text)\n    if para_text:\n        content.append(''.join(para_text))\n\n# Write extracted content to file for reference\nwith open('extracted.txt', 'w') as f:\n    for line in content:\n        f.write(line + '\\n')\nEOF\n\n# Step 3: Create new docx with modified content\npython3 \u003C\u003C 'EOF'\nfrom docx import Document\n\ndoc = Document()\ndoc.add_heading('Updated Document', 0)\n\nwith open('extracted.txt', 'r') as f:\n    for line in f:\n        if line.strip():\n            doc.add_paragraph(line.strip())\n\ndoc.save('updated.docx')\nEOF\n```\n\n## Key Points\n\n1. **Always use `run_shell`** - Not `execute_code_sandbox` for docx operations\n2. **DOCX is a ZIP archive** - Contains XML files including word\u002Fdocument.xml\n3. **Use `unzip -p`** - The `-p` flag outputs to stdout, useful for piping\n4. **Handle XML namespaces** - Word XML uses the `w:` namespace prefix\n5. **Install python-docx if needed** - Run `pip install python-docx` in the shell if not available\n\n## Troubleshooting\n\nIf python-docx is not installed:\n```bash\npip install python-docx\n```\n\nIf unzip is not available:\n```bash\n# Use Python's zipfile module instead\npython3 -c \"import zipfile; z=zipfile.ZipFile('file.docx'); print(z.read('word\u002Fdocument.xml').decode('utf-8', errors='ignore'))\"\n```\n\nIf XML parsing fails:\n- Check the namespace URI matches your document version\n- Use `.endswith('t')` instead of full namespace matching for flexibility\n- Handle encoding issues with `errors='ignore'` parameter","# DOCX Shell Workaround\n\n## When to Use\n\nUse this skill when:\n- `read_file` cannot extract content from .docx files\n- `execute_code_sandbox` encounters failures when creating or modifying docx files\n- You need a reliable fallback for docx file manipulation\n\n## Reading DOCX Files\n\n### Step 1: Extract document.xml using unzip\n\nUse `run_shell` to unzip the .docx file (which is a ZIP archive) and extract the main document XML:\n\n```bash\nunzip -p input.docx word\u002Fdocument.xml > document.xml\n```\n\n### Step 2: Parse XML with ElementTree via run_shell\n\nExtract text content by parsing the XML. Use `run_shell` to execute Python code:\n\n```bash\npython3 \u003C\u003C 'EOF'\nimport xml.etree.ElementTree as ET\n\ntree = ET.parse('document.xml')\nroot = tree.getroot()\nnamespace = {'w': 'http:\u002F\u002Fschemas.openxmlformats.org\u002Fwordprocessingml\u002F2006\u002Fmain'}\n\ntext_content = []\nfor elem in root.iter():\n    if elem.tag.endswith('t'):\n        if elem.text:\n            text_content.append(elem.text)\n\ntext = ''.join(text_content)\nprint(text)\nEOF\n```\n\n### Step 3: Optional - More robust XML parsing\n\nFor better text extraction that handles paragraphs:\n\n```bash\npython3 \u003C\u003C 'EOF'\nimport xml.etree.ElementTree as ET\n\ntree = ET.parse('document.xml')\nroot = tree.getroot()\nns = {'w': 'http:\u002F\u002Fschemas.openxmlformats.org\u002Fwordprocessingml\u002F2006\u002Fmain'}\n\nparagraphs = []\nfor p in root.findall('.\u002F\u002Fw:p', ns):\n    para_text = []\n    for t in p.findall('.\u002F\u002Fw:t', ns):\n        if t.text:\n            para_text.append(t.text)\n    if para_text:\n        paragraphs.append(''.join(para_text))\n\nfor para in paragraphs:\n    print(para)\nEOF\n```\n\n## Creating DOCX Files\n\n### Use python-docx via run_shell (NOT execute_code_sandbox)\n\nWhen `execute_code_sandbox` fails for docx operations, use `run_shell` instead:\n\n```bash\npython3 \u003C\u003C 'EOF'\nfrom docx import Document\nfrom docx.shared import Inches, Pt\nfrom docx.enum.text import WD_ALIGN_PARAGRAPH\n\ndoc = Document()\n\n# Add heading\ndoc.add_heading('Document Title', 0)\n\n# Add paragraph\ndoc.add_paragraph('Your content here.')\n\n# Add section with heading\ndoc.add_heading('Section Title', level=1)\ndoc.add_paragraph('Section content with multiple paragraphs.')\n\n# Add table if needed\ntable = doc.add_table(rows=3, cols=3)\ntable.style = 'Table Grid'\n\n# Save document\ndoc.save('output.docx')\nprint(\"Document created successfully\")\nEOF\n```\n\n### Example: Creating a structured business document\n\n```bash\npython3 \u003C\u003C 'EOF'\nfrom docx import Document\nfrom docx.shared import Pt\n\ndoc = Document()\n\n# Title\ntitle = doc.add_heading('Business Strategy Memo', 0)\ntitle.alignment = 1  # Center\n\n# Executive Summary\ndoc.add_heading('Executive Summary', level=1)\ndoc.add_paragraph('Brief overview of key points and recommendations.')\n\n# Market Overview\ndoc.add_heading('Market Overview', level=1)\ndoc.add_paragraph('Analysis of current market conditions and trends.')\n\n# Recommendations\ndoc.add_heading('Recommendations', level=1)\ndoc.add_paragraph('Actionable recommendations based on analysis.')\n\ndoc.save('Strategy_Memo.docx')\nEOF\n```\n\n## Full Workflow Example\n\nComplete example showing extraction and creation:\n\n```bash\n# Step 1: Extract content from existing docx\nunzip -p existing.docx word\u002Fdocument.xml > doc.xml\n\n# Step 2: Parse and transform content\npython3 \u003C\u003C 'EOF'\nimport xml.etree.ElementTree as ET\n\ntree = ET.parse('doc.xml')\nroot = tree.getroot()\nns = {'w': 'http:\u002F\u002Fschemas.openxmlformats.org\u002Fwordprocessingml\u002F2006\u002Fmain'}\n\ncontent = []\nfor p in root.findall('.\u002F\u002Fw:p', ns):\n    para_text = []\n    for t in p.findall('.\u002F\u002Fw:t', ns):\n        if t.text:\n            para_text.append(t.text)\n    if para_text:\n        content.append(''.join(para_text))\n\n# Write extracted content to file for reference\nwith open('extracted.txt', 'w') as f:\n    for line in content:\n        f.write(line + '\\n')\nEOF\n\n# Step 3: Create new docx with modified content\npython3 \u003C\u003C 'EOF'\nfrom docx import Document\n\ndoc = Document()\ndoc.add_heading('Updated Document', 0)\n\nwith open('extracted.txt', 'r') as f:\n    for line in f:\n        if line.strip():\n            doc.add_paragraph(line.strip())\n\ndoc.save('updated.docx')\nEOF\n```\n\n## Key Points\n\n1. **Always use `run_shell`** - Not `execute_code_sandbox` for docx operations\n2. **DOCX is a ZIP archive** - Contains XML files including word\u002Fdocument.xml\n3. **Use `unzip -p`** - The `-p` flag outputs to stdout, useful for piping\n4. **Handle XML namespaces** - Word XML uses the `w:` namespace prefix\n5. **Install python-docx if needed** - Run `pip install python-docx` in the shell if not available\n\n## Troubleshooting\n\nIf python-docx is not installed:\n```bash\npip install python-docx\n```\n\nIf unzip is not available:\n```bash\n# Use Python's zipfile module instead\npython3 -c \"import zipfile; z=zipfile.ZipFile('file.docx'); print(z.read('word\u002Fdocument.xml').decode('utf-8', errors='ignore'))\"\n```\n\nIf XML parsing fails:\n- Check the namespace URI matches your document version\n- Use `.endswith('t')` instead of full namespace matching for flexibility\n- Handle encoding issues with `errors='ignore'` parameter",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fdocx-shell-workaround",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":54,"prompt":64,"zipAvailable":65},[55,58,61],{"tool":56,"command":57},"npx","npx skills add HKUDS\u002FAgentPilot --skill docx-shell-workaround",{"tool":59,"command":60},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill docx-shell-workaround",{"tool":62,"command":63},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill docx-shell-workaround","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fdocx-shell-workaround\u002FSKILL.md",true,[67],{"path":68,"resourceType":69,"resourceTypeDesc":70,"sizeBytes":71,"sourceHtmlUrl":72},".skill_id","OTHER","其他",35,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fdocx-shell-workaround\u002F.skill_id",[74,93,112,134,158,179],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":40},"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",[],[76,81,82,83,84,85,86,87,88,89,90,91,33,92],"prepare","requests","with","missing","installation","rsi","up","use","user","work","SET","experiments",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":40},"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",[],[95,100,101,102,103,104,105,106,107,108,109,110,111],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":121,"publishedAt":40},"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",[118],{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[122,123,124,103,125,126,127,128,129,130,131,132,133,36],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":141,"publishedAt":40},"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",[140],{"categoryNo":119,"categoryName":120,"taxonomyType":21,"taxonomyTypeDesc":22},[142,143,144,103,145,146,147,148,149,124,102,88,150,151,152,153,154,155,156,157],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","tool","stack","for","share","tasks","automation","MCP",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":40},"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",[],[165,166,167,168,37,169,170,171,172,32,173,174,175,176,153,177,178],"write special chars ts check","write","check","type","filters","only","template","file","typescript","output","Existing","type-checking","errors","script",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":185,"publishedAt":40},"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",[],[186,187,166,83,153,178,188,189,38,190,191,171,172,192,193,32],"write special chars readback","readback","helper","post","scripts","read","verification","cleanup"]