[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KFJJ04SYT5GP9RTVBN1BRC":3,"skill-same:01M6KFJJ04SYT5GP9RTVBN1BRC":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":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":49,"updatedAt":50,"install":51,"resources":64},"01M6KFJJ04SYT5GP9RTVBN1BRC","irregular-excel-parsing",null,"Handle Excel files with irregular headers, merged cells, and unknown header row positions using pattern-matching and index-based extraction.","xyliu-cs\u002FOpenSpace-GDPval","xyliu-cs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F89236536?v=4","01M6KF8Z1V4TXS86CKSH48BY8T","xy","01M6KF8Z67443W0SHXM85JEF0B",0,"MIT","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Firregular-excel-parsing\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000004","电子表格","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37],"xlsx","parsing","excel parsing","irregular excel parsing","index","extraction","pattern-matching","files","pattern","positions","matching","with","headers","unknown","2026-11-10 10:12:30",false,"---\nname: irregular-excel-parsing\ndescription: Handle Excel files with irregular headers, merged cells, and unknown header row positions using pattern-matching and index-based extraction.\n---\n\n# Irregular Excel File Parsing\n\nUse this skill when you encounter Excel files where standard `pandas.read_excel()` fails due to:\n- Headers not in row 0 (6-9+ header rows common)\n- Merged cells in header area\n- Unknown or inconsistent header row positions\n- Multiple title\u002Fmetadata rows before actual data\n\n## Step-by-Step Instructions\n\n### Step 1: Read Excel Without Headers\n\nFirst, read the entire sheet with `header=None` to get raw data:\n\n```python\nimport pandas as pd\n\n# Read all data without assuming header position\ndf_raw = pd.read_excel('filename.xlsx', sheet_name='Sheet1', header=None)\n```\n\n### Step 2: Scan Rows to Find Header Pattern\n\nSearch for the actual header row by looking for distinctive patterns:\n\n```python\ndef find_header_row(df):\n    \"\"\"Find header row by pattern-matching common column identifiers.\"\"\"\n    header_patterns = [\n        r'Store ID',\n        r'ID\\d{4}',  # ID followed by 4 digits\n        r'Week \\d+',\n        r'Date',\n        r'Store',\n        r'Product',\n        r'ID'\n    ]\n    \n    for row_idx in range(len(df)):\n        row_values = df.iloc[row_idx].astype(str).str.lower()\n        for pattern in header_patterns:\n            if row_values.str.contains(pattern, case=False, regex=True).any():\n                return row_idx\n    \n    # Fallback: return first non-empty row\n    for row_idx in range(len(df)):\n        if df.iloc[row_idx].notna().sum() > 0:\n            return row_idx\n    \n    return 0\n\nheader_row = find_header_row(df_raw)\n```\n\n### Step 3: Extract and Clean Headers\n\nExtract the header row and clean column names:\n\n```python\n# Extract header row\nheaders = df_raw.iloc[header_row].tolist()\n\n# Clean headers: convert to string, strip whitespace, handle NaN\nclean_headers = []\nfor h in headers:\n    if pd.isna(h) or str(h).strip() == '':\n        clean_headers.append(f'col_{len(clean_headers)}')\n    else:\n        clean_headers.append(str(h).strip())\n\n# Handle duplicate headers by adding suffix\nfrom collections import Counter\nheader_counts = Counter(clean_headers)\nfinal_headers = []\nfor h in clean_headers:\n    if header_counts[h] > 1:\n        final_headers.append(f\"{h}_{header_counts[h]}\")\n        header_counts[h] -= 1\n    else:\n        final_headers.append(h)\n```\n\n### Step 4: Extract Data Rows\n\nExtract data starting from the row after headers:\n\n```python\n# Get data rows (everything after header)\ndata_df = df_raw.iloc[header_row + 1:].copy()\ndata_df.columns = final_headers\n\n# Reset index\ndata_df = data_df.reset_index(drop=True)\n\n# Remove completely empty rows\ndata_df = data_df.dropna(how='all')\n```\n\n### Step 5: Validate and Clean Data\n\nPerform basic validation and type conversion:\n\n```python\n# Identify ID columns and preserve as string\nfor col in data_df.columns:\n    if 'id' in col.lower() or 'code' in col.lower():\n        data_df[col] = data_df[col].astype(str).str.strip()\n\n# Convert numeric columns\nnumeric_cols = data_df.select_dtypes(include=['float64', 'int64']).columns\nfor col in numeric_cols:\n    data_df[col] = pd.to_numeric(data_df[col], errors='coerce')\n\n# Remove rows with invalid critical data\nif 'Store ID' in data_df.columns:\n    data_df = data_df[data_df['Store ID'].notna() & (data_df['Store ID'] != '')]\n```\n\n## Complete Example Function\n\n```python\ndef parse_irregular_excel(filepath, sheet_name=0):\n    \"\"\"Parse Excel file with unknown\u002Firregular header structure.\"\"\"\n    import pandas as pd\n    import re\n    from collections import Counter\n    \n    # Step 1: Read raw\n    df_raw = pd.read_excel(filepath, sheet_name=sheet_name, header=None)\n    \n    # Step 2: Find header row\n    patterns = [r'Store ID', r'ID\\d{4}', r'Week', r'Date', r'Store']\n    header_row = 0\n    for idx in range(min(15, len(df_raw))):  # Check first 15 rows\n        row_str = ' '.join(df_raw.iloc[idx].astype(str))\n        for pattern in patterns:\n            if re.search(pattern, row_str, re.IGNORECASE):\n                header_row = idx\n                break\n    \n    # Step 3: Extract headers\n    headers = [str(h).strip() if pd.notna(h) else f'col_{i}' \n               for i, h in enumerate(df_raw.iloc[header_row])]\n    \n    # Handle duplicates\n    counts = Counter(headers)\n    final_headers = []\n    for h in headers:\n        if counts[h] > 1:\n            final_headers.append(f\"{h}_{counts[h]}\")\n            counts[h] -= 1\n        else:\n            final_headers.append(h)\n    \n    # Step 4: Extract data\n    data_df = df_raw.iloc[header_row + 1:].copy()\n    data_df.columns = final_headers\n    data_df = data_df.dropna(how='all').reset_index(drop=True)\n    \n    return data_df\n```\n\n## When to Use This Pattern\n\n- ✅ Excel files with 6-9+ title\u002Fmetadata rows before data\n- ✅ Merged cells in header area causing misalignment\n- ✅ Headers not in predictable positions\n- ✅ Multiple sheets with inconsistent structures\n\n## When NOT to Use\n\n- ❌ Standard Excel files with headers in row 0 (use `read_excel()` directly)\n- ❌ Files with consistent, known structure (use explicit `header=` parameter)\n- ❌ When you know exact header row position (specify it directly)\n\n## Tips\n\n1. **Always inspect first**: Use `df_raw.head(20)` to visualize structure before parsing\n2. **Pattern flexibility**: Adjust regex patterns based on your specific column naming conventions\n3. **Handle merged cells**: Merged cells often result in NaN values - fill strategically if needed\n4. **Save for reuse**: Once you determine the correct header row for a file type, cache this for future runs","# Irregular Excel File Parsing\n\nUse this skill when you encounter Excel files where standard `pandas.read_excel()` fails due to:\n- Headers not in row 0 (6-9+ header rows common)\n- Merged cells in header area\n- Unknown or inconsistent header row positions\n- Multiple title\u002Fmetadata rows before actual data\n\n## Step-by-Step Instructions\n\n### Step 1: Read Excel Without Headers\n\nFirst, read the entire sheet with `header=None` to get raw data:\n\n```python\nimport pandas as pd\n\n# Read all data without assuming header position\ndf_raw = pd.read_excel('filename.xlsx', sheet_name='Sheet1', header=None)\n```\n\n### Step 2: Scan Rows to Find Header Pattern\n\nSearch for the actual header row by looking for distinctive patterns:\n\n```python\ndef find_header_row(df):\n    \"\"\"Find header row by pattern-matching common column identifiers.\"\"\"\n    header_patterns = [\n        r'Store ID',\n        r'ID\\d{4}',  # ID followed by 4 digits\n        r'Week \\d+',\n        r'Date',\n        r'Store',\n        r'Product',\n        r'ID'\n    ]\n    \n    for row_idx in range(len(df)):\n        row_values = df.iloc[row_idx].astype(str).str.lower()\n        for pattern in header_patterns:\n            if row_values.str.contains(pattern, case=False, regex=True).any():\n                return row_idx\n    \n    # Fallback: return first non-empty row\n    for row_idx in range(len(df)):\n        if df.iloc[row_idx].notna().sum() > 0:\n            return row_idx\n    \n    return 0\n\nheader_row = find_header_row(df_raw)\n```\n\n### Step 3: Extract and Clean Headers\n\nExtract the header row and clean column names:\n\n```python\n# Extract header row\nheaders = df_raw.iloc[header_row].tolist()\n\n# Clean headers: convert to string, strip whitespace, handle NaN\nclean_headers = []\nfor h in headers:\n    if pd.isna(h) or str(h).strip() == '':\n        clean_headers.append(f'col_{len(clean_headers)}')\n    else:\n        clean_headers.append(str(h).strip())\n\n# Handle duplicate headers by adding suffix\nfrom collections import Counter\nheader_counts = Counter(clean_headers)\nfinal_headers = []\nfor h in clean_headers:\n    if header_counts[h] > 1:\n        final_headers.append(f\"{h}_{header_counts[h]}\")\n        header_counts[h] -= 1\n    else:\n        final_headers.append(h)\n```\n\n### Step 4: Extract Data Rows\n\nExtract data starting from the row after headers:\n\n```python\n# Get data rows (everything after header)\ndata_df = df_raw.iloc[header_row + 1:].copy()\ndata_df.columns = final_headers\n\n# Reset index\ndata_df = data_df.reset_index(drop=True)\n\n# Remove completely empty rows\ndata_df = data_df.dropna(how='all')\n```\n\n### Step 5: Validate and Clean Data\n\nPerform basic validation and type conversion:\n\n```python\n# Identify ID columns and preserve as string\nfor col in data_df.columns:\n    if 'id' in col.lower() or 'code' in col.lower():\n        data_df[col] = data_df[col].astype(str).str.strip()\n\n# Convert numeric columns\nnumeric_cols = data_df.select_dtypes(include=['float64', 'int64']).columns\nfor col in numeric_cols:\n    data_df[col] = pd.to_numeric(data_df[col], errors='coerce')\n\n# Remove rows with invalid critical data\nif 'Store ID' in data_df.columns:\n    data_df = data_df[data_df['Store ID'].notna() & (data_df['Store ID'] != '')]\n```\n\n## Complete Example Function\n\n```python\ndef parse_irregular_excel(filepath, sheet_name=0):\n    \"\"\"Parse Excel file with unknown\u002Firregular header structure.\"\"\"\n    import pandas as pd\n    import re\n    from collections import Counter\n    \n    # Step 1: Read raw\n    df_raw = pd.read_excel(filepath, sheet_name=sheet_name, header=None)\n    \n    # Step 2: Find header row\n    patterns = [r'Store ID', r'ID\\d{4}', r'Week', r'Date', r'Store']\n    header_row = 0\n    for idx in range(min(15, len(df_raw))):  # Check first 15 rows\n        row_str = ' '.join(df_raw.iloc[idx].astype(str))\n        for pattern in patterns:\n            if re.search(pattern, row_str, re.IGNORECASE):\n                header_row = idx\n                break\n    \n    # Step 3: Extract headers\n    headers = [str(h).strip() if pd.notna(h) else f'col_{i}' \n               for i, h in enumerate(df_raw.iloc[header_row])]\n    \n    # Handle duplicates\n    counts = Counter(headers)\n    final_headers = []\n    for h in headers:\n        if counts[h] > 1:\n            final_headers.append(f\"{h}_{counts[h]}\")\n            counts[h] -= 1\n        else:\n            final_headers.append(h)\n    \n    # Step 4: Extract data\n    data_df = df_raw.iloc[header_row + 1:].copy()\n    data_df.columns = final_headers\n    data_df = data_df.dropna(how='all').reset_index(drop=True)\n    \n    return data_df\n```\n\n## When to Use This Pattern\n\n- ✅ Excel files with 6-9+ title\u002Fmetadata rows before data\n- ✅ Merged cells in header area causing misalignment\n- ✅ Headers not in predictable positions\n- ✅ Multiple sheets with inconsistent structures\n\n## When NOT to Use\n\n- ❌ Standard Excel files with headers in row 0 (use `read_excel()` directly)\n- ❌ Files with consistent, known structure (use explicit `header=` parameter)\n- ❌ When you know exact header row position (specify it directly)\n\n## Tips\n\n1. **Always inspect first**: Use `df_raw.head(20)` to visualize structure before parsing\n2. **Pattern flexibility**: Adjust regex patterns based on your specific column naming conventions\n3. **Handle merged cells**: Merged cells often result in NaN values - fill strategically if needed\n4. **Save for reuse**: Once you determine the correct header row for a file type, cache this for future runs",{"name":5,"description":7},"main","af1b40a42167d09c30b3a63000aa14ace4c1e229","gdpval_bench\u002Fskills\u002Firregular-excel-parsing","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval","https:\u002F\u002Fgithub.com\u002Fxyliu-cs","https:\u002F\u002Fxyliu-cs.github.io","PhD Student in CS, CUHK-Shenzhen.","2026-04-06 20:32:15",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add xyliu-cs\u002FOpenSpace-GDPval --skill irregular-excel-parsing",{"tool":57,"command":58},"bunx","bunx skills add xyliu-cs\u002FOpenSpace-GDPval --skill irregular-excel-parsing",{"tool":60,"command":61},"pnpm","pnpm dlx skills add xyliu-cs\u002FOpenSpace-GDPval --skill irregular-excel-parsing","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Firregular-excel-parsing\u002FSKILL.md",true,[65],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},".skill_id","OTHER","其他",37,"https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Firregular-excel-parsing\u002F.skill_id",[72,85,93,108,134,154],{"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},"01M6KG8MF1S664SWBDENYRSCK8","zip-export-deliverable","Ensures codebase deliverables are properly exported as ZIP archives through a dedicated finalization step","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fzip-export-deliverable\u002FSKILL.md",[],[79,80,81,82,83,84],"zip export deliverable","zip","export","deliverables","codebase","as",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":38},"01M6KG8GAZWHHEK7VNJDW0ME21","zip-deliverable-finalization","Ensure codebase deliverables are properly packaged as ZIP exports in a dedicated final step","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fzip-deliverable-finalization\u002FSKILL.md",[],[92,80,82,83,84],"zip deliverable finalization",{"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":38},"01M6KG8CMQQ1PYMNTSRZ9VS1MD","zero-iteration-failure-analysis","Identify and handle agent failures with 0 iterations as pre-execution system issues","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fzero-iteration-failure-analysis\u002FSKILL.md",[],[100,101,102,103,104,35,105,106,84,107],"failure analysis","ZeRO","analysis","iteration","zero iteration failure analysis","issues","execution","system",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":119,"publishedAt":38},"01M6KG86W3PA07FT9W58YHHERM","write-file-fallback-report","Generate professional documents using write_file when primary data sources fail, leveraging embedded domain knowledge instead of external retrieval","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fwrite-file-fallback-report\u002FSKILL.md",[114],{"categoryNo":115,"categoryName":116,"taxonomyType":117,"taxonomyTypeDesc":118},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[120,121,122,123,124,125,126,127,128,129,130,131,132,133],"fallback","write","file","report","write file fallback report","domain","professional","sources","retrieval","generate","embedded","documents","data","knowledge",{"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":143,"publishedAt":38},"01M6KG82GAEY3GG77CMGCK1C2T","fallback-doc-with-delegation","Generate professional documents after tool failures using shell_agent for complex formats or write_file for simple text\u002Fmarkdown","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fwrite-file-fallback-report-enhanced\u002FSKILL.md",[140],{"categoryNo":141,"categoryName":142,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[144,35,120,145,146,147,131,129,122,148,149,150,121,151,126,152,153],"fallback doc with delegation","doc","delegation","shell","markdown","tool","text","simple","formats","for",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":161,"publishedAt":38},"01M6KG7WT7GX5NYCGEFHW22NV7","context-anchored-fallback-report","Generate documents with write_file when retrieval tools fail, with explicit guardrails against task context drift","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fwrite-file-fallback-report-enhanced-4bc5c2\u002FSKILL.md",[160],{"categoryNo":115,"categoryName":116,"taxonomyType":117,"taxonomyTypeDesc":118},[120,123,162,163,129,122,164,165,121,166,167,128,35,168,131],"context","context anchored fallback report","Guardrails","Tools","task","drift","context drift"]