[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HX30TH3WYTD1PB25ECQTDA":3,"skill-same:01M6HX30TH3WYTD1PB25ECQTDA":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":26,"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},"01M6HX30TH3WYTD1PB25ECQTDA","document-direct-python",null,"Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports","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\u002Fspreadsheet-direct-python-merged\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":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000004","电子表格",[27,28,29,30,31,32,33,34,35,36,37],"python","direct","document","document direct python","spreadsheets","execution","use","reports","structured","creation","for","2026-11-10 10:12:30",false,"---\nname: document-direct-python\ndescription: Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports\n---\n\n# Direct Python Execution for Document Generation Tasks\n\n## When to Use This Skill\n\nUse direct `run_shell` with Python scripts for document operations when:\n\n- Reading or writing complex Excel files with multiple sheets\n- Generating PDF documents, checklists, or reports\n- Applying formulas, formatting, or data transformations\n- Working with `openpyxl`, `pandas`, `reportlab`, `FPDF`, or similar libraries\n- The operation involves multiple steps that could exceed agent step limits\n- You need precise control over error handling and debugging\n- Complex scripts benefit from file-based execution for better reliability\n\n## Why Direct Execution?\n\nThe `shell_agent` tool can:\n\n- Hit maximum step limits on complex multi-step operations\n- Produce unexplained errors on formatting operations\n- Fail on intricate document reads\u002Fwrites due to iterative parsing\n- Fail to parse heredoc syntax correctly, causing 'unknown error' failures\n\nDirect `run_shell` with Python is more reliable because it:\n\n- Executes in a single step with no iteration limits\n- Provides clearer, immediate error messages\n- Handles complex operations without step constraints\n- Gives full control over library imports and execution flow\n- Writing scripts to `.py` files first avoids shell_agent parsing issues with heredocs\n\n## How to Use\n\n\n### Handling Web Research Failures\n\nWhen web research tools (`search_web`, `read_webpage`) fail or return 'unknown error':\n\n1. **Assess what you need**: Determine if the information is from well-documented regulatory frameworks, standards, or common knowledge that you can provide from internal knowledge.\n2. **Proceed with available knowledge**: For pharmacy compliance, OSHA standards, GDPR requirements, and similar well-established frameworks, generate documents using your training knowledge rather than waiting for web access.\n3. **Document assumptions**: Clearly note that materials were generated based on standard practices when source verification was unavailable.\n4. **Use direct Python execution**: Continue with the recommended `run_shell` pattern to generate documents even without web-sourced content.\n\n**Example contingency workflow for pharmacy compliance:**\n\n```python\n# When web research fails, proceed with established regulatory knowledge\nfrom reportlab.lib.pagesizes import letter\nfrom reportlab.pdfgen import canvas\n\nchecklist_items = [\n    \"Verify pharmacist license is current and displayed\",\n    \"Maintain controlled substance inventory logs\",\n    \"Ensure proper storage temperatures for medications\",\n    \"Keep patient counseling records for controlled substances\",\n    \"Display required pharmacy signage and notices\"\n]\n# Generate PDF using these standard compliance items\n```\n\nThis approach was successfully used in task 045aba2e-4093-42aa-ab7f-159cc538278c_phase2 where all web tools failed but pharmacy compliance PDFs were still created successfully.\n\n### Recommended Pattern: Write Script to File First\n\nFor complex multi-line scripts, especially when using shell_agent as executor:\n\n```bash\n# Step 1: Write the Python script to a file\ncat > generate_document.py \u003C\u003C 'EOF'\nimport openpyxl\nfrom openpyxl import Workbook\n\n# Your document code here\nwb = openpyxl.load_workbook('file.xlsx')\n# ... operations ...\nwb.save('output.xlsx')\nprint('Success')\nEOF\n\n# Step 2: Execute the script\npython3 generate_document.py\n```\n\n### Alternative Pattern: Inline Heredoc (Simple Scripts Only)\n\nFor short, simple scripts when NOT using shell_agent as the executor:\n\n```bash\npython3 \u003C\u003C 'EOF'\nimport pandas as pd\ndf = pd.read_excel('input.xlsx')\ndf.to_excel('output.xlsx', index=False)\nprint('Done')\nEOF\n```\n\n## Spreadsheet Examples\n\n### Example 1: Read and Transform Excel Data\n\n**Write to file first, then execute:**\n\n```python\nimport pandas as pd\n\n# Load data from specific sheet\ndf = pd.read_excel('input.xlsx', sheet_name='Revenue')\n\n# Apply transformations\ndf['Net_Revenue'] = df['Gross_Revenue'] * (1 - df['Tax_Rate'])\n\n# Save results\ndf.to_excel('output.xlsx', index=False, sheet_name='Processed')\n```\n\n### Example 2: Multi-Sheet Operations with openpyxl\n\n```python\nfrom openpyxl import load_workbook\n\nwb = load_workbook('tour_data.xlsx')\n\n# Iterate through sheets\nfor sheet_name in wb.sheetnames:\n    ws = wb[sheet_name]\n    # Apply formatting or calculations\n    for row in ws.iter_rows(min_row=2, max_col=5):\n        # Process cells\n        pass\n\nwb.save('tour_data_processed.xlsx')\n```\n\n## PDF Generation Examples\n\n### Example 3: Generate PDF Checklist with reportlab\n\n**Write to file first, then execute:**\n\n```python\nfrom reportlab.lib.pagesizes import letter\nfrom reportlab.pdfgen import canvas\nfrom reportlab.lib.units import inch\n\ndef create_checklist(filename, items):\n    c = canvas.Canvas(filename, pagesize=letter)\n    width, height = letter\n    \n    # Title\n    c.setFont(\"Helvetica-Bold\", 20)\n    c.drawString(1*inch, height - 1*inch, \"Task Checklist\")\n    \n    # Items\n    c.setFont(\"Helvetica\", 14)\n    y_position = height - 1.5*inch\n    for i, item in enumerate(items, 1):\n        checkbox = \"☐\"  # Empty checkbox\n        c.drawString(1*inch, y_position, f\"{checkbox} {item}\")\n        y_position -= 0.3*inch\n    \n    c.save()\n    print(f\"Created {filename} with {len(items)} items\")\n\n# Usage\nitems = [\"Review requirements\", \"Complete analysis\", \"Submit report\", \"Follow up\"]\ncreate_checklist(\"checklist.pdf\", items)\n```\n\n### Example 4: Generate PDF Report with FPDF\n\n```python\nfrom fpdf import FPDF\n\nclass PDF(FPDF):\n    def header(self):\n        self.set_font('Arial', 'B', 15)\n        self.cell(0, 10, 'Monthly Report', 0, 1, 'C')\n        self.ln(10)\n    \n    def footer(self):\n        self.set_y(-15)\n        self.set_font('Arial', 'I', 8)\n        self.cell(0, 10, f'Page {self.page_no()}', 0, 0, 'C')\n\ndef create_report(filename, data):\n    pdf = PDF()\n    pdf.add_page()\n    pdf.set_font('Arial', '', 12)\n    \n    # Add content\n    for section, content in data.items():\n        pdf.set_font('Arial', 'B', 12)\n        pdf.cell(0, 10, section, 0, 1)\n        pdf.set_font('Arial', '', 12)\n        pdf.multi_cell(0, 8, content)\n        pdf.ln(5)\n    \n    pdf.output(filename)\n    print(f\"Report saved to {filename}\")\n\n# Usage\ndata = {\n    \"Executive Summary\": \"This report covers Q4 performance metrics.\",\n    \"Key Findings\": \"Revenue increased by 15% compared to Q3.\",\n    \"Recommendations\": \"Continue current strategy with minor adjustments.\"\n}\ncreate_report(\"report.pdf\", data)\n```\n\n### Example 5: Combined Spreadsheet to PDF Workflow\n\n```python\nimport pandas as pd\nfrom reportlab.lib.pagesizes import letter\nfrom reportlab.pdfgen import canvas\nfrom reportlab.platypus import SimpleDocTemplate, Table, TableStyle\nfrom reportlab.lib import colors\n\n# Step 1: Process spreadsheet data\ndf = pd.read_excel('sales_data.xlsx')\nsummary = df.groupby('Region')['Revenue'].sum().reset_index()\n\n# Step 2: Generate PDF report\ndoc = SimpleDocTemplate(\"sales_report.pdf\", pagesize=letter)\nelements = []\n\n# Create table from data\ndata = [['Region', 'Revenue']]\nfor _, row in summary.iterrows():\n    data.append([row['Region'], f\"${row['Revenue']:,.2f}\"])\n\ntable = Table(data)\ntable.setStyle(TableStyle([\n    ('BACKGROUND', (0, 0), (-1, 0), colors.grey),\n    ('TEXTCOLOR', (0, 0), (-1, 0), colors.whitesmoke),\n    ('ALIGN', (0, 0), (-1, -1), 'CENTER'),\n    ('GRID', (0, 0), (-1, -1), 1, colors.black),\n]))\n\nelements.append(table)\ndoc.build(elements)\nprint(\"PDF report generated successfully\")\n```\n\n## Error Handling Pattern\n\n**Write to file first, then execute:**\n\n```python\nimport sys\nfrom openpyxl import load_workbook\n\ntry:\n    wb = load_workbook('data.xlsx')\n    ws = wb.active\n    \n    # Your operations here\n    value = ws['A1'].value\n    \n    wb.save('output.xlsx')\n    print(f\"Success: Processed {ws.max_row} rows\")\n    \nexcept Exception as e:\n    print(f\"Error: {str(e)}\", file=sys.stderr)\n    sys.exit(1)\n```\n\n## Best Practices\n\n1. **Prefer file-based execution** for complex scripts: write to `.py` file first, then execute via `run_shell`\n2. **Import only needed libraries** to reduce execution time\n3. **Print clear success\u002Ferror messages** for debugging\n4. **Save intermediate results** for complex multi-step transformations\n5. **Test with small data** before scaling to large documents\n6. **Use pandas for data manipulation** and openpyxl for spreadsheet formatting\n7. **Use reportlab for professional PDF layouts** and FPDF for simple PDFs\n8. **Clean up temporary script files** after execution if they won't be reused\n\n## When NOT to Use This Skill\n\n- Simple single-cell reads\u002Fwrites (use shell_agent or basic commands)\n- Operations that require interactive user input\n- Tasks where you need the agent to iteratively refine the approach\n- Basic text file operations (use shell commands directly)\n\n## Common Libraries\n\n### Spreadsheets\n| Library | Best For |\n|---------|----------|\n| `openpyxl` | Reading\u002Fwriting .xlsx files, formatting, formulas |\n| `pandas` | Data manipulation, analysis, merging datasets |\n| `xlrd` | Reading older .xls files (read-only) |\n| `xlsxwriter` | Creating new .xlsx files with advanced formatting |\n\n### PDF Generation\n| Library | Best For |\n|---------|----------|\n| `reportlab` | Professional PDF reports with complex layouts |\n| `FPDF` | Simple PDF generation with basic formatting |\n| `PyPDF2` \u002F `pypdf` | Reading, merging, splitting existing PDFs |\n| `pdfplumber` | Extracting text and tables from PDFs |\n\n## Troubleshooting\n\n**Issue**: Heredoc syntax fails with 'unknown error' when using shell_agent\n- **Solution**: Write the Python script to a `.py` file first, then execute it with `python3 script.py`. This pattern is significantly more reliable than inline heredoc execution when shell_agent is the executor.\n\n**Issue**: FileNotFoundError\n- **Solution**: Verify the file path is absolute or relative to the working directory. Use `os.getcwd()` to check current directory if needed.\n\n**Issue**: PermissionError\n- **Solution**: Ensure the file is not open in another application. Close Excel\u002FPDF readers before writing.\n\n**Issue**: MemoryError on large files\n- **Solution**: Process data in chunks using pandas `chunksize` parameter. For PDFs, generate in sections and merge.\n\n**Issue**: Formatting not applying\n- **Solution**: Ensure you're modifying cell styles before saving, and use `.copy()` for style objects in openpyxl.\n\n**Issue**: PDF text rendering issues\n- **Solution**: For non-ASCII characters, use appropriate fonts (e.g., `DejaVuSans` for Unicode support in reportlab).\n\n**Issue**: Agent fails before first iteration (0 steps)\n- **Solution**: Ensure the skill is properly loaded and the task description clearly indicates document generation needs. Complex initialization may require explicit Python script patterns.\n","# Direct Python Execution for Document Generation Tasks\n\n## When to Use This Skill\n\nUse direct `run_shell` with Python scripts for document operations when:\n\n- Reading or writing complex Excel files with multiple sheets\n- Generating PDF documents, checklists, or reports\n- Applying formulas, formatting, or data transformations\n- Working with `openpyxl`, `pandas`, `reportlab`, `FPDF`, or similar libraries\n- The operation involves multiple steps that could exceed agent step limits\n- You need precise control over error handling and debugging\n- Complex scripts benefit from file-based execution for better reliability\n\n## Why Direct Execution?\n\nThe `shell_agent` tool can:\n\n- Hit maximum step limits on complex multi-step operations\n- Produce unexplained errors on formatting operations\n- Fail on intricate document reads\u002Fwrites due to iterative parsing\n- Fail to parse heredoc syntax correctly, causing 'unknown error' failures\n\nDirect `run_shell` with Python is more reliable because it:\n\n- Executes in a single step with no iteration limits\n- Provides clearer, immediate error messages\n- Handles complex operations without step constraints\n- Gives full control over library imports and execution flow\n- Writing scripts to `.py` files first avoids shell_agent parsing issues with heredocs\n\n## How to Use\n\n\n### Handling Web Research Failures\n\nWhen web research tools (`search_web`, `read_webpage`) fail or return 'unknown error':\n\n1. **Assess what you need**: Determine if the information is from well-documented regulatory frameworks, standards, or common knowledge that you can provide from internal knowledge.\n2. **Proceed with available knowledge**: For pharmacy compliance, OSHA standards, GDPR requirements, and similar well-established frameworks, generate documents using your training knowledge rather than waiting for web access.\n3. **Document assumptions**: Clearly note that materials were generated based on standard practices when source verification was unavailable.\n4. **Use direct Python execution**: Continue with the recommended `run_shell` pattern to generate documents even without web-sourced content.\n\n**Example contingency workflow for pharmacy compliance:**\n\n```python\n# When web research fails, proceed with established regulatory knowledge\nfrom reportlab.lib.pagesizes import letter\nfrom reportlab.pdfgen import canvas\n\nchecklist_items = [\n    \"Verify pharmacist license is current and displayed\",\n    \"Maintain controlled substance inventory logs\",\n    \"Ensure proper storage temperatures for medications\",\n    \"Keep patient counseling records for controlled substances\",\n    \"Display required pharmacy signage and notices\"\n]\n# Generate PDF using these standard compliance items\n```\n\nThis approach was successfully used in task 045aba2e-4093-42aa-ab7f-159cc538278c_phase2 where all web tools failed but pharmacy compliance PDFs were still created successfully.\n\n### Recommended Pattern: Write Script to File First\n\nFor complex multi-line scripts, especially when using shell_agent as executor:\n\n```bash\n# Step 1: Write the Python script to a file\ncat > generate_document.py \u003C\u003C 'EOF'\nimport openpyxl\nfrom openpyxl import Workbook\n\n# Your document code here\nwb = openpyxl.load_workbook('file.xlsx')\n# ... operations ...\nwb.save('output.xlsx')\nprint('Success')\nEOF\n\n# Step 2: Execute the script\npython3 generate_document.py\n```\n\n### Alternative Pattern: Inline Heredoc (Simple Scripts Only)\n\nFor short, simple scripts when NOT using shell_agent as the executor:\n\n```bash\npython3 \u003C\u003C 'EOF'\nimport pandas as pd\ndf = pd.read_excel('input.xlsx')\ndf.to_excel('output.xlsx', index=False)\nprint('Done')\nEOF\n```\n\n## Spreadsheet Examples\n\n### Example 1: Read and Transform Excel Data\n\n**Write to file first, then execute:**\n\n```python\nimport pandas as pd\n\n# Load data from specific sheet\ndf = pd.read_excel('input.xlsx', sheet_name='Revenue')\n\n# Apply transformations\ndf['Net_Revenue'] = df['Gross_Revenue'] * (1 - df['Tax_Rate'])\n\n# Save results\ndf.to_excel('output.xlsx', index=False, sheet_name='Processed')\n```\n\n### Example 2: Multi-Sheet Operations with openpyxl\n\n```python\nfrom openpyxl import load_workbook\n\nwb = load_workbook('tour_data.xlsx')\n\n# Iterate through sheets\nfor sheet_name in wb.sheetnames:\n    ws = wb[sheet_name]\n    # Apply formatting or calculations\n    for row in ws.iter_rows(min_row=2, max_col=5):\n        # Process cells\n        pass\n\nwb.save('tour_data_processed.xlsx')\n```\n\n## PDF Generation Examples\n\n### Example 3: Generate PDF Checklist with reportlab\n\n**Write to file first, then execute:**\n\n```python\nfrom reportlab.lib.pagesizes import letter\nfrom reportlab.pdfgen import canvas\nfrom reportlab.lib.units import inch\n\ndef create_checklist(filename, items):\n    c = canvas.Canvas(filename, pagesize=letter)\n    width, height = letter\n    \n    # Title\n    c.setFont(\"Helvetica-Bold\", 20)\n    c.drawString(1*inch, height - 1*inch, \"Task Checklist\")\n    \n    # Items\n    c.setFont(\"Helvetica\", 14)\n    y_position = height - 1.5*inch\n    for i, item in enumerate(items, 1):\n        checkbox = \"☐\"  # Empty checkbox\n        c.drawString(1*inch, y_position, f\"{checkbox} {item}\")\n        y_position -= 0.3*inch\n    \n    c.save()\n    print(f\"Created {filename} with {len(items)} items\")\n\n# Usage\nitems = [\"Review requirements\", \"Complete analysis\", \"Submit report\", \"Follow up\"]\ncreate_checklist(\"checklist.pdf\", items)\n```\n\n### Example 4: Generate PDF Report with FPDF\n\n```python\nfrom fpdf import FPDF\n\nclass PDF(FPDF):\n    def header(self):\n        self.set_font('Arial', 'B', 15)\n        self.cell(0, 10, 'Monthly Report', 0, 1, 'C')\n        self.ln(10)\n    \n    def footer(self):\n        self.set_y(-15)\n        self.set_font('Arial', 'I', 8)\n        self.cell(0, 10, f'Page {self.page_no()}', 0, 0, 'C')\n\ndef create_report(filename, data):\n    pdf = PDF()\n    pdf.add_page()\n    pdf.set_font('Arial', '', 12)\n    \n    # Add content\n    for section, content in data.items():\n        pdf.set_font('Arial', 'B', 12)\n        pdf.cell(0, 10, section, 0, 1)\n        pdf.set_font('Arial', '', 12)\n        pdf.multi_cell(0, 8, content)\n        pdf.ln(5)\n    \n    pdf.output(filename)\n    print(f\"Report saved to {filename}\")\n\n# Usage\ndata = {\n    \"Executive Summary\": \"This report covers Q4 performance metrics.\",\n    \"Key Findings\": \"Revenue increased by 15% compared to Q3.\",\n    \"Recommendations\": \"Continue current strategy with minor adjustments.\"\n}\ncreate_report(\"report.pdf\", data)\n```\n\n### Example 5: Combined Spreadsheet to PDF Workflow\n\n```python\nimport pandas as pd\nfrom reportlab.lib.pagesizes import letter\nfrom reportlab.pdfgen import canvas\nfrom reportlab.platypus import SimpleDocTemplate, Table, TableStyle\nfrom reportlab.lib import colors\n\n# Step 1: Process spreadsheet data\ndf = pd.read_excel('sales_data.xlsx')\nsummary = df.groupby('Region')['Revenue'].sum().reset_index()\n\n# Step 2: Generate PDF report\ndoc = SimpleDocTemplate(\"sales_report.pdf\", pagesize=letter)\nelements = []\n\n# Create table from data\ndata = [['Region', 'Revenue']]\nfor _, row in summary.iterrows():\n    data.append([row['Region'], f\"${row['Revenue']:,.2f}\"])\n\ntable = Table(data)\ntable.setStyle(TableStyle([\n    ('BACKGROUND', (0, 0), (-1, 0), colors.grey),\n    ('TEXTCOLOR', (0, 0), (-1, 0), colors.whitesmoke),\n    ('ALIGN', (0, 0), (-1, -1), 'CENTER'),\n    ('GRID', (0, 0), (-1, -1), 1, colors.black),\n]))\n\nelements.append(table)\ndoc.build(elements)\nprint(\"PDF report generated successfully\")\n```\n\n## Error Handling Pattern\n\n**Write to file first, then execute:**\n\n```python\nimport sys\nfrom openpyxl import load_workbook\n\ntry:\n    wb = load_workbook('data.xlsx')\n    ws = wb.active\n    \n    # Your operations here\n    value = ws['A1'].value\n    \n    wb.save('output.xlsx')\n    print(f\"Success: Processed {ws.max_row} rows\")\n    \nexcept Exception as e:\n    print(f\"Error: {str(e)}\", file=sys.stderr)\n    sys.exit(1)\n```\n\n## Best Practices\n\n1. **Prefer file-based execution** for complex scripts: write to `.py` file first, then execute via `run_shell`\n2. **Import only needed libraries** to reduce execution time\n3. **Print clear success\u002Ferror messages** for debugging\n4. **Save intermediate results** for complex multi-step transformations\n5. **Test with small data** before scaling to large documents\n6. **Use pandas for data manipulation** and openpyxl for spreadsheet formatting\n7. **Use reportlab for professional PDF layouts** and FPDF for simple PDFs\n8. **Clean up temporary script files** after execution if they won't be reused\n\n## When NOT to Use This Skill\n\n- Simple single-cell reads\u002Fwrites (use shell_agent or basic commands)\n- Operations that require interactive user input\n- Tasks where you need the agent to iteratively refine the approach\n- Basic text file operations (use shell commands directly)\n\n## Common Libraries\n\n### Spreadsheets\n| Library | Best For |\n|---------|----------|\n| `openpyxl` | Reading\u002Fwriting .xlsx files, formatting, formulas |\n| `pandas` | Data manipulation, analysis, merging datasets |\n| `xlrd` | Reading older .xls files (read-only) |\n| `xlsxwriter` | Creating new .xlsx files with advanced formatting |\n\n### PDF Generation\n| Library | Best For |\n|---------|----------|\n| `reportlab` | Professional PDF reports with complex layouts |\n| `FPDF` | Simple PDF generation with basic formatting |\n| `PyPDF2` \u002F `pypdf` | Reading, merging, splitting existing PDFs |\n| `pdfplumber` | Extracting text and tables from PDFs |\n\n## Troubleshooting\n\n**Issue**: Heredoc syntax fails with 'unknown error' when using shell_agent\n- **Solution**: Write the Python script to a `.py` file first, then execute it with `python3 script.py`. This pattern is significantly more reliable than inline heredoc execution when shell_agent is the executor.\n\n**Issue**: FileNotFoundError\n- **Solution**: Verify the file path is absolute or relative to the working directory. Use `os.getcwd()` to check current directory if needed.\n\n**Issue**: PermissionError\n- **Solution**: Ensure the file is not open in another application. Close Excel\u002FPDF readers before writing.\n\n**Issue**: MemoryError on large files\n- **Solution**: Process data in chunks using pandas `chunksize` parameter. For PDFs, generate in sections and merge.\n\n**Issue**: Formatting not applying\n- **Solution**: Ensure you're modifying cell styles before saving, and use `.copy()` for style objects in openpyxl.\n\n**Issue**: PDF text rendering issues\n- **Solution**: For non-ASCII characters, use appropriate fonts (e.g., `DejaVuSans` for Unicode support in reportlab).\n\n**Issue**: Agent fails before first iteration (0 steps)\n- **Solution**: Ensure the skill is properly loaded and the task description clearly indicates document generation needs. Complex initialization may require explicit Python script patterns.\n",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fspreadsheet-direct-python-merged",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 document-direct-python",{"tool":57,"command":58},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill document-direct-python",{"tool":60,"command":61},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill document-direct-python","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fspreadsheet-direct-python-merged\u002FSKILL.md",true,[65],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},".skill_id","OTHER","其他",46,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fspreadsheet-direct-python-merged\u002F.skill_id",[72,91,110,133,156,178],{"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",[],[74,79,80,81,82,83,84,85,33,86,87,88,89,90],"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},[141,142,143,101,144,145,146,147,148,122,100,33,149,150,151,37,152,153,154,155],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","tool","stack","share","tasks","automation","MCP",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"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",[],[163,164,165,166,167,168,169,170,171,27,172,173,174,175,37,176,177],"write special chars ts check","write","check","type","files","filters","only","template","file","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",[],[185,186,164,81,37,177,187,188,189,190,191,170,171,192,193,27],"write special chars readback","readback","helper","post","via","scripts","read","verification","cleanup"]