[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KM1X5KCJPF0F7CVSRPK584":3,"skill-same:01M6KM1X5KCJPF0F7CVSRPK584":64},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":27,"publishedAt":37,"linkOnly":38,"markdownContent":39,"markdownBody":40,"frontMatter":41,"refName":42,"commitSha":43,"skillDirectory":44,"forksCount":45,"repositoryHtmlUrl":46,"repositoryHomepageUrl":47,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M6KM1X5KCJPF0F7CVSRPK584","docx",null,"Word document manipulation with python-docx - handling split placeholders, headers\u002Ffooters, nested tables","cxcscmu\u002FSkillLearnBench","cxcscmu","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F142838272?v=4","01M6KCQDFQWPDSN0MKZY96MSQP","01M6KCQDM7G70TKJ28NTSQC0RZ",93,"MIT","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Foffer-letter-generator\u002Fdocx\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[5,28,29,30,31,32,33,34,35,36],"python","Word","nested","document","with","headers","tables","python-docx","split","2026-11-10 10:12:30",false,"---\nname: docx\ndescription: Word document manipulation with python-docx - handling split placeholders, headers\u002Ffooters, nested tables\n---\n\n# Word Document Manipulation with python-docx\n\n## Critical: Split Placeholder Problem\n\n**The #1 issue with Word templates**: Word often splits placeholder text across multiple XML runs. For example, `{{CANDIDATE_NAME}}` might be stored as:\n- Run 1: `{{CANDI`\n- Run 2: `DATE_NAME}}`\n\nThis happens due to spell-check, formatting changes, or Word's internal XML structure.\n\n### Naive Approach (FAILS on split placeholders)\n\n```python\n# DON'T DO THIS - won't find split placeholders\nfor para in doc.paragraphs:\n    for run in para.runs:\n        if '{{NAME}}' in run.text:  # Won't match if split!\n            run.text = run.text.replace('{{NAME}}', value)\n```\n\n### Correct Approach: Paragraph-Level Search and Rebuild\n\n```python\nimport re\n\ndef replace_placeholder_robust(paragraph, placeholder, value):\n    \"\"\"Replace placeholder that may be split across runs.\"\"\"\n    full_text = paragraph.text\n    if placeholder not in full_text:\n        return False\n\n    # Find all runs and their positions\n    runs = paragraph.runs\n    if not runs:\n        return False\n\n    # Build mapping of character positions to runs\n    char_to_run = []\n    for run in runs:\n        for char in run.text:\n            char_to_run.append(run)\n\n    # Find placeholder position\n    start_idx = full_text.find(placeholder)\n    end_idx = start_idx + len(placeholder)\n\n    # Get runs that contain the placeholder\n    if start_idx >= len(char_to_run):\n        return False\n\n    start_run = char_to_run[start_idx]\n\n    # Clear all runs and rebuild with replacement\n    new_text = full_text.replace(placeholder, str(value))\n\n    # Preserve first run's formatting, clear others\n    for i, run in enumerate(runs):\n        if i == 0:\n            run.text = new_text\n        else:\n            run.text = ''\n\n    return True\n```\n\n### Best Practice: Regex-Based Full Replacement\n\n```python\nimport re\nfrom docx import Document\n\ndef replace_all_placeholders(doc, data):\n    \"\"\"Replace all {{KEY}} placeholders with values from data dict.\"\"\"\n\n    def replace_in_paragraph(para):\n        \"\"\"Replace placeholders in a single paragraph.\"\"\"\n        text = para.text\n        # Find all placeholders\n        pattern = r'\\{\\{([A-Z_]+)\\}\\}'\n        matches = re.findall(pattern, text)\n\n        if not matches:\n            return\n\n        # Build new text with replacements\n        new_text = text\n        for key in matches:\n            placeholder = '{{' + key + '}}'\n            if key in data:\n                new_text = new_text.replace(placeholder, str(data[key]))\n\n        # If text changed, rebuild paragraph\n        if new_text != text:\n            # Clear all runs, put new text in first run\n            runs = para.runs\n            if runs:\n                runs[0].text = new_text\n                for run in runs[1:]:\n                    run.text = ''\n\n    # Process all paragraphs\n    for para in doc.paragraphs:\n        replace_in_paragraph(para)\n\n    # Process tables (including nested)\n    for table in doc.tables:\n        for row in table.rows:\n            for cell in row.cells:\n                for para in cell.paragraphs:\n                    replace_in_paragraph(para)\n                # Handle nested tables\n                for nested_table in cell.tables:\n                    for nested_row in nested_table.rows:\n                        for nested_cell in nested_row.cells:\n                            for para in nested_cell.paragraphs:\n                                replace_in_paragraph(para)\n\n    # Process headers and footers\n    for section in doc.sections:\n        for para in section.header.paragraphs:\n            replace_in_paragraph(para)\n        for para in section.footer.paragraphs:\n            replace_in_paragraph(para)\n```\n\n## Headers and Footers\n\nHeaders\u002Ffooters are separate from main document body:\n\n```python\nfrom docx import Document\n\ndoc = Document('template.docx')\n\n# Access headers\u002Ffooters through sections\nfor section in doc.sections:\n    # Header\n    header = section.header\n    for para in header.paragraphs:\n        # Process paragraphs\n        pass\n\n    # Footer\n    footer = section.footer\n    for para in footer.paragraphs:\n        # Process paragraphs\n        pass\n```\n\n## Nested Tables\n\nTables can contain other tables. Must recurse:\n\n```python\ndef process_table(table, data):\n    \"\"\"Process table including nested tables.\"\"\"\n    for row in table.rows:\n        for cell in row.cells:\n            # Process paragraphs in cell\n            for para in cell.paragraphs:\n                replace_in_paragraph(para, data)\n\n            # Recurse into nested tables\n            for nested_table in cell.tables:\n                process_table(nested_table, data)\n```\n\n## Conditional Sections\n\nFor `{{IF_CONDITION}}...{{END_IF_CONDITION}}` patterns:\n\n```python\ndef handle_conditional(doc, condition_key, should_include, data):\n    \"\"\"Remove or keep conditional sections.\"\"\"\n    start_marker = '{{IF_' + condition_key + '}}'\n    end_marker = '{{END_IF_' + condition_key + '}}'\n\n    for para in doc.paragraphs:\n        text = para.text\n        if start_marker in text and end_marker in text:\n            if should_include:\n                # Remove just the markers\n                new_text = text.replace(start_marker, '').replace(end_marker, '')\n                # Also replace any placeholders inside\n                for key, val in data.items():\n                    new_text = new_text.replace('{{' + key + '}}', str(val))\n            else:\n                # Remove entire content between markers\n                new_text = ''\n\n            # Apply to first run\n            if para.runs:\n                para.runs[0].text = new_text\n                for run in para.runs[1:]:\n                    run.text = ''\n```\n\n## Complete Solution Pattern\n\n```python\nfrom docx import Document\nimport json\nimport re\n\ndef fill_template(template_path, data_path, output_path):\n    \"\"\"Fill Word template handling all edge cases.\"\"\"\n\n    # Load data\n    with open(data_path) as f:\n        data = json.load(f)\n\n    # Load template\n    doc = Document(template_path)\n\n    def replace_in_para(para):\n        text = para.text\n        pattern = r'\\{\\{([A-Z_]+)\\}\\}'\n        if not re.search(pattern, text):\n            return\n\n        new_text = text\n        for match in re.finditer(pattern, text):\n            key = match.group(1)\n            placeholder = match.group(0)\n            if key in data:\n                new_text = new_text.replace(placeholder, str(data[key]))\n\n        if new_text != text and para.runs:\n            para.runs[0].text = new_text\n            for run in para.runs[1:]:\n                run.text = ''\n\n    # Main document\n    for para in doc.paragraphs:\n        replace_in_para(para)\n\n    # Tables (with nesting)\n    def process_table(table):\n        for row in table.rows:\n            for cell in row.cells:\n                for para in cell.paragraphs:\n                    replace_in_para(para)\n                for nested in cell.tables:\n                    process_table(nested)\n\n    for table in doc.tables:\n        process_table(table)\n\n    # Headers\u002FFooters\n    for section in doc.sections:\n        for para in section.header.paragraphs:\n            replace_in_para(para)\n        for para in section.footer.paragraphs:\n            replace_in_para(para)\n\n    doc.save(output_path)\n\n# Usage\nfill_template('template.docx', 'data.json', 'output.docx')\n```\n\n## Common Pitfalls\n\n1. **Forgetting headers\u002Ffooters** - They're not in `doc.paragraphs`\n2. **Missing nested tables** - Must recurse into `cell.tables`\n3. **Split placeholders** - Always work at paragraph level, not run level\n4. **Losing formatting** - Keep first run's formatting when rebuilding\n5. **Conditional markers left behind** - Remove `{{IF_...}}` markers after processing\n","# Word Document Manipulation with python-docx\n\n## Critical: Split Placeholder Problem\n\n**The #1 issue with Word templates**: Word often splits placeholder text across multiple XML runs. For example, `{{CANDIDATE_NAME}}` might be stored as:\n- Run 1: `{{CANDI`\n- Run 2: `DATE_NAME}}`\n\nThis happens due to spell-check, formatting changes, or Word's internal XML structure.\n\n### Naive Approach (FAILS on split placeholders)\n\n```python\n# DON'T DO THIS - won't find split placeholders\nfor para in doc.paragraphs:\n    for run in para.runs:\n        if '{{NAME}}' in run.text:  # Won't match if split!\n            run.text = run.text.replace('{{NAME}}', value)\n```\n\n### Correct Approach: Paragraph-Level Search and Rebuild\n\n```python\nimport re\n\ndef replace_placeholder_robust(paragraph, placeholder, value):\n    \"\"\"Replace placeholder that may be split across runs.\"\"\"\n    full_text = paragraph.text\n    if placeholder not in full_text:\n        return False\n\n    # Find all runs and their positions\n    runs = paragraph.runs\n    if not runs:\n        return False\n\n    # Build mapping of character positions to runs\n    char_to_run = []\n    for run in runs:\n        for char in run.text:\n            char_to_run.append(run)\n\n    # Find placeholder position\n    start_idx = full_text.find(placeholder)\n    end_idx = start_idx + len(placeholder)\n\n    # Get runs that contain the placeholder\n    if start_idx >= len(char_to_run):\n        return False\n\n    start_run = char_to_run[start_idx]\n\n    # Clear all runs and rebuild with replacement\n    new_text = full_text.replace(placeholder, str(value))\n\n    # Preserve first run's formatting, clear others\n    for i, run in enumerate(runs):\n        if i == 0:\n            run.text = new_text\n        else:\n            run.text = ''\n\n    return True\n```\n\n### Best Practice: Regex-Based Full Replacement\n\n```python\nimport re\nfrom docx import Document\n\ndef replace_all_placeholders(doc, data):\n    \"\"\"Replace all {{KEY}} placeholders with values from data dict.\"\"\"\n\n    def replace_in_paragraph(para):\n        \"\"\"Replace placeholders in a single paragraph.\"\"\"\n        text = para.text\n        # Find all placeholders\n        pattern = r'\\{\\{([A-Z_]+)\\}\\}'\n        matches = re.findall(pattern, text)\n\n        if not matches:\n            return\n\n        # Build new text with replacements\n        new_text = text\n        for key in matches:\n            placeholder = '{{' + key + '}}'\n            if key in data:\n                new_text = new_text.replace(placeholder, str(data[key]))\n\n        # If text changed, rebuild paragraph\n        if new_text != text:\n            # Clear all runs, put new text in first run\n            runs = para.runs\n            if runs:\n                runs[0].text = new_text\n                for run in runs[1:]:\n                    run.text = ''\n\n    # Process all paragraphs\n    for para in doc.paragraphs:\n        replace_in_paragraph(para)\n\n    # Process tables (including nested)\n    for table in doc.tables:\n        for row in table.rows:\n            for cell in row.cells:\n                for para in cell.paragraphs:\n                    replace_in_paragraph(para)\n                # Handle nested tables\n                for nested_table in cell.tables:\n                    for nested_row in nested_table.rows:\n                        for nested_cell in nested_row.cells:\n                            for para in nested_cell.paragraphs:\n                                replace_in_paragraph(para)\n\n    # Process headers and footers\n    for section in doc.sections:\n        for para in section.header.paragraphs:\n            replace_in_paragraph(para)\n        for para in section.footer.paragraphs:\n            replace_in_paragraph(para)\n```\n\n## Headers and Footers\n\nHeaders\u002Ffooters are separate from main document body:\n\n```python\nfrom docx import Document\n\ndoc = Document('template.docx')\n\n# Access headers\u002Ffooters through sections\nfor section in doc.sections:\n    # Header\n    header = section.header\n    for para in header.paragraphs:\n        # Process paragraphs\n        pass\n\n    # Footer\n    footer = section.footer\n    for para in footer.paragraphs:\n        # Process paragraphs\n        pass\n```\n\n## Nested Tables\n\nTables can contain other tables. Must recurse:\n\n```python\ndef process_table(table, data):\n    \"\"\"Process table including nested tables.\"\"\"\n    for row in table.rows:\n        for cell in row.cells:\n            # Process paragraphs in cell\n            for para in cell.paragraphs:\n                replace_in_paragraph(para, data)\n\n            # Recurse into nested tables\n            for nested_table in cell.tables:\n                process_table(nested_table, data)\n```\n\n## Conditional Sections\n\nFor `{{IF_CONDITION}}...{{END_IF_CONDITION}}` patterns:\n\n```python\ndef handle_conditional(doc, condition_key, should_include, data):\n    \"\"\"Remove or keep conditional sections.\"\"\"\n    start_marker = '{{IF_' + condition_key + '}}'\n    end_marker = '{{END_IF_' + condition_key + '}}'\n\n    for para in doc.paragraphs:\n        text = para.text\n        if start_marker in text and end_marker in text:\n            if should_include:\n                # Remove just the markers\n                new_text = text.replace(start_marker, '').replace(end_marker, '')\n                # Also replace any placeholders inside\n                for key, val in data.items():\n                    new_text = new_text.replace('{{' + key + '}}', str(val))\n            else:\n                # Remove entire content between markers\n                new_text = ''\n\n            # Apply to first run\n            if para.runs:\n                para.runs[0].text = new_text\n                for run in para.runs[1:]:\n                    run.text = ''\n```\n\n## Complete Solution Pattern\n\n```python\nfrom docx import Document\nimport json\nimport re\n\ndef fill_template(template_path, data_path, output_path):\n    \"\"\"Fill Word template handling all edge cases.\"\"\"\n\n    # Load data\n    with open(data_path) as f:\n        data = json.load(f)\n\n    # Load template\n    doc = Document(template_path)\n\n    def replace_in_para(para):\n        text = para.text\n        pattern = r'\\{\\{([A-Z_]+)\\}\\}'\n        if not re.search(pattern, text):\n            return\n\n        new_text = text\n        for match in re.finditer(pattern, text):\n            key = match.group(1)\n            placeholder = match.group(0)\n            if key in data:\n                new_text = new_text.replace(placeholder, str(data[key]))\n\n        if new_text != text and para.runs:\n            para.runs[0].text = new_text\n            for run in para.runs[1:]:\n                run.text = ''\n\n    # Main document\n    for para in doc.paragraphs:\n        replace_in_para(para)\n\n    # Tables (with nesting)\n    def process_table(table):\n        for row in table.rows:\n            for cell in row.cells:\n                for para in cell.paragraphs:\n                    replace_in_para(para)\n                for nested in cell.tables:\n                    process_table(nested)\n\n    for table in doc.tables:\n        process_table(table)\n\n    # Headers\u002FFooters\n    for section in doc.sections:\n        for para in section.header.paragraphs:\n            replace_in_para(para)\n        for para in section.footer.paragraphs:\n            replace_in_para(para)\n\n    doc.save(output_path)\n\n# Usage\nfill_template('template.docx', 'data.json', 'output.docx')\n```\n\n## Common Pitfalls\n\n1. **Forgetting headers\u002Ffooters** - They're not in `doc.paragraphs`\n2. **Missing nested tables** - Must recurse into `cell.tables`\n3. **Split placeholders** - Always work at paragraph level, not run level\n4. **Losing formatting** - Keep first run's formatting when rebuilding\n5. **Conditional markers left behind** - Remove `{{IF_...}}` markers after processing\n",{"name":5,"description":7},"main","726e1f79b96b0cb3d729d0e55a1c847e0b5353ae","skills\u002Fhuman_authored\u002Foffer-letter-generator\u002Fdocx",8,"https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench","https:\u002F\u002Fcxcscmu.github.io\u002FSkillLearnBench","https:\u002F\u002Fgithub.com\u002Fcxcscmu","2026-10-02 22:55:36",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add cxcscmu\u002FSkillLearnBench --skill docx",{"tool":56,"command":57},"bunx","bunx skills add cxcscmu\u002FSkillLearnBench --skill docx",{"tool":59,"command":60},"pnpm","pnpm dlx skills add cxcscmu\u002FSkillLearnBench --skill docx","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Foffer-letter-generator\u002Fdocx\u002FSKILL.md",true,[],[65,81,106,124,144,156],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":74,"publishedAt":37},"01M6KM5KH175P5ABP5JMX2SBDQ","object_counter","Count occurrences of an object in the image using computer vision algorithm.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Fvideo-object-counting\u002Fobject_counter\u002FSKILL.md",[71],{"categoryNo":72,"categoryName":73,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",[75,76,77,78,79,80],"object counter","object","vision","computer","Computer Vision","image",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":90,"publishedAt":37},"01M6KM51TMVXG79MMPCS6Y8G86","travel-planning-workflow","Invoke this skill when performing travel planning. It defines a structured workflow for generating itineraries. Following this workflow is essential to ensure the final plan satisfies user requirements.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftravel-planning\u002Ftravel-planning-workflow\u002FSKILL.md",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[91,92,93,94,95,96,97,98,99,100,101,102,103,104,105],"workflow","planning","planning workflow","travel","travel planning","travel planning workflow","structured","performing","plan","for","user","it","requirements","essential","itineraries",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":37},"01M6KM4DY820XHS9YTSK5QP5HD","bundled-dataset-search-tool","invoke this skill when you need to perform database search for travel planning. This skill provides some useful pre-packaged tools to look up accommodations, attractions, cities, driving distance, flights, and restaurants from the bundled dataset.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftravel-planning\u002Fbundled-dataset-search-tool\u002FSKILL.md",[],[113,114,115,116,117,118,119,94,120,121,95,122,100,123,92],"search","tool","dataset","bundled dataset search tool","restaurants","Tools","up","look","flights","you","database",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":37},"01M6KM465BB9PQ0B548HQSVAWZ","glm-output","Output-processing guidance for GLM tasks. Especially useful after glm-basics and glm-calibration when you need verifier-matching metrics from output.nc and a final \u002Froot\u002Fmetrics.json.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-output\u002FSKILL.md",[],[131,132,133,100,134,135,136,137,138,139,140,141,122,142,143],"glm output","output","glm","tasks","metrics","json","basics","guidance","matching","verifier","processing","root","calibration",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":151,"publishedAt":37},"01M6KM40KY3QWDW5W97S39R2BC","glm-calibration","Calibration guidance for GLM tasks. Often most effective after glm-basics has clarified the setup; glm-output is the companion skill for exact final metric computation.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-calibration\u002FSKILL.md",[150],{"categoryNo":88,"categoryName":89,"taxonomyType":20,"taxonomyTypeDesc":21},[152,143,133,132,138,137,134,153,154,100,155],"glm calibration","setup","companion","metric",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":37},"01M6KM3VHHVSGMGHJQB3PPT6YG","glm-basics","A good starting point for GLM calibration tasks. Use to inspect glm3.nml, confirm how GLM runs, and identify the relevant files before moving on to calibration and output evaluation.","https:\u002F\u002Fgithub.com\u002Fcxcscmu\u002FSkillLearnBench\u002Fblob\u002Fmain\u002Fskills\u002Fhuman_authored\u002Ftemperature-simulation\u002Fglm-basics\u002FSKILL.md",[],[163,133,137,164,152,143,100,132,165,166,167,168,169,170,134],"glm basics","inspect","relevant","files","good","use","how","Evaluation"]