[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HXJ55FAHNAEB2V4CD21QP6":3,"skill-same:01M6HXJ55FAHNAEB2V4CD21QP6":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":28,"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},"01M6HXJ55FAHNAEB2V4CD21QP6","excel-debug-extraction",null,"Iteratively debug Excel structure with exploratory scripts before writing extraction logic","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\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fexcel-debug-extraction\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000004","电子表格","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37],"xlsx","debug","extraction","excel debug extraction","writing","structure","logic","scripts","with","2026-11-10 10:12:30",false,"---\nname: excel-debug-extraction\ndescription: Iteratively debug Excel structure with exploratory scripts before writing extraction logic\n---\n\n# Excel Debug-First Extraction Workflow\n\nWhen working with poorly-structured, complex, or unfamiliar Excel files, use this iterative debugging approach to map the data layout before writing your final extraction logic.\n\n## When to Use This Skill\n\n- Excel files with inconsistent formatting or merged cells\n- Files received from external sources with unknown structure\n- Complex workbooks with multiple sheets and interdependencies\n- When initial parsing attempts fail or produce unexpected results\n\n## Workflow Steps\n\n### Step 1: Initial Structure Reconnaissance\n\nBefore writing extraction logic, create a debug script to explore the file structure:\n\n```python\n# debug_structure.py\nfrom openpyxl import load_workbook\n\nwb = load_workbook('file.xlsx')\nprint(f\"Sheets: {wb.sheetnames}\")\n\nfor sheet_name in wb.sheetnames:\n    ws = wb[sheet_name]\n    print(f\"\\n=== Sheet: {sheet_name} ===\")\n    print(f\"Dimensions: {ws.dimensions}\")\n    \n    # Print first 10 rows to understand header structure\n    for row in ws.iter_rows(min_row=1, max_row=10, values_only=True):\n        print([str(cell)[:50] for cell in row])\n```\n\n### Step 2: Map Column Positions\n\nIdentify where key data fields are located:\n\n```python\n# debug_columns.py\nfrom openpyxl import load_workbook\n\nwb = load_workbook('file.xlsx')\nws = wb['Sheet1']\n\n# Examine header row to find column indices\nheader_row = 1\ncolumn_map = {}\n\nfor col in ws.iter_cols(min_row=header_row, max_row=header_row):\n    for cell in col:\n        if cell.value:\n            column_map[str(cell.value)] = cell.column_letter\n\nprint(\"Column mapping:\", column_map)\n\n# Sample data rows to verify structure\nfor row_num in range(2, min(6, ws.max_row + 1)):\n    row_data = [ws.cell(row=row_num, column=col).value \n                for col in range(1, ws.max_column + 1)]\n    print(f\"Row {row_num}: {row_data}\")\n```\n\n### Step 3: Identify Row Patterns\n\nUnderstand how data rows are structured (e.g., summary rows, detail rows, blank separators):\n\n```python\n# debug_rows.py\nfrom openpyxl import load_workbook\n\nwb = load_workbook('file.xlsx')\nws = wb['Sheet1']\n\nrow_types = []\nfor row_num in range(1, min(30, ws.max_row + 1)):\n    row_values = [ws.cell(row=row_num, column=col).value \n                  for col in range(1, ws.max_column + 1)]\n    \n    non_empty = sum(1 for v in row_values if v is not None and str(v).strip())\n    \n    # Classify row type\n    if non_empty == 0:\n        row_type = \"blank\"\n    elif non_empty == 1:\n        row_type = \"summary\u002Flabel\"\n    elif non_empty == ws.max_column:\n        row_type = \"full_data\"\n    else:\n        row_type = \"partial\"\n    \n    row_types.append((row_num, row_type, row_values[:5]))\n\nfor rt in row_types:\n    print(f\"Row {rt[0]} ({rt[1]}): {rt[2]}\")\n```\n\n### Step 4: Document Findings\n\nBefore writing extraction logic, summarize:\n- Sheet names and their purposes\n- Header row location and column mappings\n- Data row patterns (which rows contain actual data vs. headers\u002Fsummaries)\n- Any special formatting (merged cells, blank separators, grouping rows)\n\n### Step 5: Write Extraction Logic\n\nIncorporate findings into your final processing script:\n\n```python\n# extract_data.py\nfrom openpyxl import load_workbook\nimport pandas as pd\n\nwb = load_workbook('file.xlsx')\nws = wb['Sheet1']\n\n# Use column mappings from debug phase\nSTORE_COL = 'B'  # Column 2\nWEEK1_COL = 'D'  # Column 4\nWEEK2_COL = 'E'  # Column 5\n\n# Skip header rows and summary rows based on debug findings\ndata_rows = []\nfor row_num in range(5, ws.max_row + 1):  # Start after header based on debug\n    # Skip summary\u002Fblank rows\n    if ws.cell(row=row_num, column=2).value is None:\n        continue\n    if 'TOTAL' in str(ws.cell(row=row_num, column=2).value).upper():\n        continue\n    \n    row_data = {\n        'store': ws.cell(row=row_num, column=2).value,\n        'week1': ws.cell(row=row_num, column=4).value,\n        'week2': ws.cell(row=row_num, column=5).value,\n    }\n    data_rows.append(row_data)\n\ndf = pd.DataFrame(data_rows)\nprint(df.head())\n```\n\n## Best Practices\n\n1. **Always start with exploration** - Never assume Excel structure matches expectations\n2. **Save debug scripts** - Keep them in your project for future reference and debugging\n3. **Print generously** - Use verbose output during exploration to catch edge cases\n4. **Verify row-by-row** - Don't assume all data rows follow the same pattern\n5. **Handle merged cells** - Check for merged cells that span multiple rows\u002Fcolumns\n\n## Common Pitfalls to Avoid\n\n- Assuming header is always row 1\n- Assuming all rows between first and last contain data\n- Not checking for hidden sheets or protected ranges\n- Ignoring cell formatting that indicates row type (bold, indentation)\n- Not handling None values or empty strings consistently\n\n## File Naming Convention\n\nUse descriptive names for debug scripts:\n- `debug_structure.py` - Overall file\u002Fsheet structure\n- `debug_columns.py` - Column positions and headers\n- `debug_rows.py` - Row patterns and data boundaries\n- `debug_values.py` - Value patterns and edge cases\n\nKeep debug scripts alongside your extraction script for maintainability.","# Excel Debug-First Extraction Workflow\n\nWhen working with poorly-structured, complex, or unfamiliar Excel files, use this iterative debugging approach to map the data layout before writing your final extraction logic.\n\n## When to Use This Skill\n\n- Excel files with inconsistent formatting or merged cells\n- Files received from external sources with unknown structure\n- Complex workbooks with multiple sheets and interdependencies\n- When initial parsing attempts fail or produce unexpected results\n\n## Workflow Steps\n\n### Step 1: Initial Structure Reconnaissance\n\nBefore writing extraction logic, create a debug script to explore the file structure:\n\n```python\n# debug_structure.py\nfrom openpyxl import load_workbook\n\nwb = load_workbook('file.xlsx')\nprint(f\"Sheets: {wb.sheetnames}\")\n\nfor sheet_name in wb.sheetnames:\n    ws = wb[sheet_name]\n    print(f\"\\n=== Sheet: {sheet_name} ===\")\n    print(f\"Dimensions: {ws.dimensions}\")\n    \n    # Print first 10 rows to understand header structure\n    for row in ws.iter_rows(min_row=1, max_row=10, values_only=True):\n        print([str(cell)[:50] for cell in row])\n```\n\n### Step 2: Map Column Positions\n\nIdentify where key data fields are located:\n\n```python\n# debug_columns.py\nfrom openpyxl import load_workbook\n\nwb = load_workbook('file.xlsx')\nws = wb['Sheet1']\n\n# Examine header row to find column indices\nheader_row = 1\ncolumn_map = {}\n\nfor col in ws.iter_cols(min_row=header_row, max_row=header_row):\n    for cell in col:\n        if cell.value:\n            column_map[str(cell.value)] = cell.column_letter\n\nprint(\"Column mapping:\", column_map)\n\n# Sample data rows to verify structure\nfor row_num in range(2, min(6, ws.max_row + 1)):\n    row_data = [ws.cell(row=row_num, column=col).value \n                for col in range(1, ws.max_column + 1)]\n    print(f\"Row {row_num}: {row_data}\")\n```\n\n### Step 3: Identify Row Patterns\n\nUnderstand how data rows are structured (e.g., summary rows, detail rows, blank separators):\n\n```python\n# debug_rows.py\nfrom openpyxl import load_workbook\n\nwb = load_workbook('file.xlsx')\nws = wb['Sheet1']\n\nrow_types = []\nfor row_num in range(1, min(30, ws.max_row + 1)):\n    row_values = [ws.cell(row=row_num, column=col).value \n                  for col in range(1, ws.max_column + 1)]\n    \n    non_empty = sum(1 for v in row_values if v is not None and str(v).strip())\n    \n    # Classify row type\n    if non_empty == 0:\n        row_type = \"blank\"\n    elif non_empty == 1:\n        row_type = \"summary\u002Flabel\"\n    elif non_empty == ws.max_column:\n        row_type = \"full_data\"\n    else:\n        row_type = \"partial\"\n    \n    row_types.append((row_num, row_type, row_values[:5]))\n\nfor rt in row_types:\n    print(f\"Row {rt[0]} ({rt[1]}): {rt[2]}\")\n```\n\n### Step 4: Document Findings\n\nBefore writing extraction logic, summarize:\n- Sheet names and their purposes\n- Header row location and column mappings\n- Data row patterns (which rows contain actual data vs. headers\u002Fsummaries)\n- Any special formatting (merged cells, blank separators, grouping rows)\n\n### Step 5: Write Extraction Logic\n\nIncorporate findings into your final processing script:\n\n```python\n# extract_data.py\nfrom openpyxl import load_workbook\nimport pandas as pd\n\nwb = load_workbook('file.xlsx')\nws = wb['Sheet1']\n\n# Use column mappings from debug phase\nSTORE_COL = 'B'  # Column 2\nWEEK1_COL = 'D'  # Column 4\nWEEK2_COL = 'E'  # Column 5\n\n# Skip header rows and summary rows based on debug findings\ndata_rows = []\nfor row_num in range(5, ws.max_row + 1):  # Start after header based on debug\n    # Skip summary\u002Fblank rows\n    if ws.cell(row=row_num, column=2).value is None:\n        continue\n    if 'TOTAL' in str(ws.cell(row=row_num, column=2).value).upper():\n        continue\n    \n    row_data = {\n        'store': ws.cell(row=row_num, column=2).value,\n        'week1': ws.cell(row=row_num, column=4).value,\n        'week2': ws.cell(row=row_num, column=5).value,\n    }\n    data_rows.append(row_data)\n\ndf = pd.DataFrame(data_rows)\nprint(df.head())\n```\n\n## Best Practices\n\n1. **Always start with exploration** - Never assume Excel structure matches expectations\n2. **Save debug scripts** - Keep them in your project for future reference and debugging\n3. **Print generously** - Use verbose output during exploration to catch edge cases\n4. **Verify row-by-row** - Don't assume all data rows follow the same pattern\n5. **Handle merged cells** - Check for merged cells that span multiple rows\u002Fcolumns\n\n## Common Pitfalls to Avoid\n\n- Assuming header is always row 1\n- Assuming all rows between first and last contain data\n- Not checking for hidden sheets or protected ranges\n- Ignoring cell formatting that indicates row type (bold, indentation)\n- Not handling None values or empty strings consistently\n\n## File Naming Convention\n\nUse descriptive names for debug scripts:\n- `debug_structure.py` - Overall file\u002Fsheet structure\n- `debug_columns.py` - Column positions and headers\n- `debug_rows.py` - Row patterns and data boundaries\n- `debug_values.py` - Value patterns and edge cases\n\nKeep debug scripts alongside your extraction script for maintainability.",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fexcel-debug-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 excel-debug-extraction",{"tool":57,"command":58},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill excel-debug-extraction",{"tool":60,"command":61},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill excel-debug-extraction","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fexcel-debug-extraction\u002FSKILL.md",true,[65],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},".skill_id","OTHER","其他",36,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fexcel-debug-extraction\u002F.skill_id",[72,91,110,133,157,180],{"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",[],[74,79,80,37,81,82,83,84,85,86,87,88,89,90],"prepare","requests","missing","installation","rsi","up","use","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},[141,142,143,101,144,145,146,147,148,122,100,85,149,150,151,152,153,154,155,156],"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",[],[164,165,166,167,168,169,170,171,172,173,174,175,176,177,152,178,179],"write special chars ts check","write","check","type","files","filters","only","template","file","python","typescript","output","Existing","type-checking","errors","script",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"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",[],[187,188,165,37,152,179,189,190,191,36,192,171,172,193,194,173],"write special chars readback","readback","helper","post","via","read","verification","cleanup"]