[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HXJ1GVY61Z1ZFNBSDAK25T":3,"skill-same:01M6HXJ1GVY61Z1ZFNBSDAK25T":74},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M6HXJ1GVY61Z1ZFNBSDAK25T","excel-creation-fallback",null,"Use shell_agent as fallback when execute_code_sandbox fails for Excel file operations","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-creation-fallback\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":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40],"xlsx","fallback","creation","excel creation fallback","sandbox","code","file","shell","file operations","execute","operations","use","as","for","2026-11-10 10:12:30",false,"---\nname: excel-creation-fallback\ndescription: Use shell_agent as fallback when execute_code_sandbox fails for Excel file operations\n---\n\n# Excel File Creation Fallback\n\nWhen `execute_code_sandbox` fails for openpyxl or Excel operations, delegate to `shell_agent` which can autonomously handle dependency and environment issues.\n\n## When to Use\n\n- `execute_code_sandbox` fails with import errors for openpyxl or related libraries\n- The sandbox environment lacks required dependencies\n- You need to create or modify Excel files with complex requirements\n- Repeated sandbox execution failures for file I\u002FO operations\n\n## Steps\n\n### Step 1: Attempt with execute_code_sandbox first\n\nTry creating the Excel file using Python's openpyxl library in the code sandbox:\n\n```python\nfrom openpyxl import Workbook\n\nwb = Workbook()\nws = wb.active\nws.append(['Column1', 'Column2', 'Column3'])\nwb.save('output.xlsx')\n```\n\n### Step 2: If it fails, switch to shell_agent\n\nDelegate the task to shell_agent with a clear, comprehensive task description:\n\n```\nCreate an Excel file named 'output.xlsx' with the following structure:\n- Sheet 1: Data with columns [Date, Metric, Value]\n- Include sample data rows with realistic values\n- Apply basic formatting (bold headers, cell borders)\n- Add a summary section with totals or averages\n- Save the file in the current directory\n```\n\n### Step 3: Let shell_agent handle the environment\n\nThe shell_agent will:\n- Decide whether to use Python or Bash\n- Install dependencies if needed (e.g., `pip install openpyxl`)\n- Write and execute the code\n- Automatically retry and fix errors (up to several rounds)\n- Confirm the file was created successfully\n\n## Example Task Descriptions\n\n### Basic Excel file:\n```\nCreate an Excel file named 'sales_report.xlsx' with headers: Date, Product, Quantity, Price, Total. Add 10 sample rows of data and a formula column for Total (Quantity * Price).\n```\n\n### Complex Excel with formatting:\n```\nCreate an Excel file with multiple sheets:\n- Sheet 'Summary': Key metrics and totals\n- Sheet 'Details': Full transaction data with columns [ID, Date, Customer, Amount, Status]\n- Apply conditional formatting to highlight amounts over 1000\n- Add borders to all cells and bold headers\n```\n\n### Tiered pricing structure:\n```\nCreate an Excel file with a tiered pricing table:\n- Column A: Quantity thresholds (0, 100, 500, 1000)\n- Column B: Unit price at each tier\n- Column C: Discount percentage (e.g., 15% discount over 1000 units)\n- Include a financial summary section with projections\n```\n\n## Why This Pattern Works\n\n`shell_agent` has several advantages over `execute_code_sandbox` for file creation tasks:\n\n| Feature | execute_code_sandbox | shell_agent |\n|---------|---------------------|-------------|\n| Dependency installation | Manual\u002Fpreset only | Autonomous |\n| Error recovery | Returns error | Auto-retries and fixes |\n| Tool selection | Python only | Python, Bash, or other |\n| Filesystem access | Sandbox-limited | Full workspace access |\n| Verification | None | Can verify file creation |\n\n## Troubleshooting\n\nIf shell_agent also struggles:\n\n1. **Be more specific** - Include exact column names, data types, and formatting requirements\n2. **Provide sample data** - Include example rows to clarify expected output\n3. **Break it down** - For complex files, request creation in stages\n4. **Check permissions** - Ensure the target directory is writable\n\n## Alternative Approaches\n\nIf shell_agent is unavailable or unsuitable:\n\n- Use `run_shell` with explicit commands (if you know the exact syntax)\n- Check for alternative libraries (xlsxwriter, pandas with openpyxl engine)\n- Use CSV as intermediate format, then convert to Excel","# Excel File Creation Fallback\n\nWhen `execute_code_sandbox` fails for openpyxl or Excel operations, delegate to `shell_agent` which can autonomously handle dependency and environment issues.\n\n## When to Use\n\n- `execute_code_sandbox` fails with import errors for openpyxl or related libraries\n- The sandbox environment lacks required dependencies\n- You need to create or modify Excel files with complex requirements\n- Repeated sandbox execution failures for file I\u002FO operations\n\n## Steps\n\n### Step 1: Attempt with execute_code_sandbox first\n\nTry creating the Excel file using Python's openpyxl library in the code sandbox:\n\n```python\nfrom openpyxl import Workbook\n\nwb = Workbook()\nws = wb.active\nws.append(['Column1', 'Column2', 'Column3'])\nwb.save('output.xlsx')\n```\n\n### Step 2: If it fails, switch to shell_agent\n\nDelegate the task to shell_agent with a clear, comprehensive task description:\n\n```\nCreate an Excel file named 'output.xlsx' with the following structure:\n- Sheet 1: Data with columns [Date, Metric, Value]\n- Include sample data rows with realistic values\n- Apply basic formatting (bold headers, cell borders)\n- Add a summary section with totals or averages\n- Save the file in the current directory\n```\n\n### Step 3: Let shell_agent handle the environment\n\nThe shell_agent will:\n- Decide whether to use Python or Bash\n- Install dependencies if needed (e.g., `pip install openpyxl`)\n- Write and execute the code\n- Automatically retry and fix errors (up to several rounds)\n- Confirm the file was created successfully\n\n## Example Task Descriptions\n\n### Basic Excel file:\n```\nCreate an Excel file named 'sales_report.xlsx' with headers: Date, Product, Quantity, Price, Total. Add 10 sample rows of data and a formula column for Total (Quantity * Price).\n```\n\n### Complex Excel with formatting:\n```\nCreate an Excel file with multiple sheets:\n- Sheet 'Summary': Key metrics and totals\n- Sheet 'Details': Full transaction data with columns [ID, Date, Customer, Amount, Status]\n- Apply conditional formatting to highlight amounts over 1000\n- Add borders to all cells and bold headers\n```\n\n### Tiered pricing structure:\n```\nCreate an Excel file with a tiered pricing table:\n- Column A: Quantity thresholds (0, 100, 500, 1000)\n- Column B: Unit price at each tier\n- Column C: Discount percentage (e.g., 15% discount over 1000 units)\n- Include a financial summary section with projections\n```\n\n## Why This Pattern Works\n\n`shell_agent` has several advantages over `execute_code_sandbox` for file creation tasks:\n\n| Feature | execute_code_sandbox | shell_agent |\n|---------|---------------------|-------------|\n| Dependency installation | Manual\u002Fpreset only | Autonomous |\n| Error recovery | Returns error | Auto-retries and fixes |\n| Tool selection | Python only | Python, Bash, or other |\n| Filesystem access | Sandbox-limited | Full workspace access |\n| Verification | None | Can verify file creation |\n\n## Troubleshooting\n\nIf shell_agent also struggles:\n\n1. **Be more specific** - Include exact column names, data types, and formatting requirements\n2. **Provide sample data** - Include example rows to clarify expected output\n3. **Break it down** - For complex files, request creation in stages\n4. **Check permissions** - Ensure the target directory is writable\n\n## Alternative Approaches\n\nIf shell_agent is unavailable or unsuitable:\n\n- Use `run_shell` with explicit commands (if you know the exact syntax)\n- Check for alternative libraries (xlsxwriter, pandas with openpyxl engine)\n- Use CSV as intermediate format, then convert to Excel",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fexcel-creation-fallback",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":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add HKUDS\u002FAgentPilot --skill excel-creation-fallback",{"tool":60,"command":61},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill excel-creation-fallback",{"tool":63,"command":64},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill excel-creation-fallback","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fexcel-creation-fallback\u002FSKILL.md",true,[68],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},".skill_id","OTHER","其他",37,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fexcel-creation-fallback\u002F.skill_id",[75,94,113,134,157,179],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":41},"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",[],[77,82,83,84,85,86,87,88,38,89,90,91,92,93],"prepare","requests","with","missing","installation","rsi","up","user","work","SET","run","experiments",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":41},"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",[],[96,101,102,103,104,105,106,107,108,109,110,111,112],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":120,"publishedAt":41},"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",[119],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[121,122,123,104,124,125,126,127,128,129,130,131,132,133],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search","Tools",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":141,"publishedAt":41},"01M6HYAR811B3RB0M50RBEDGN6","delegate-task","Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and skill library. Skills auto-improve through use, reducing token consumption over time. A cloud community lets agents share and collectively evolve reusable skills.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fopenspace\u002Fhost_skills\u002Fdelegate-task\u002FSKILL.md",[140],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[142,143,144,104,145,146,147,148,149,123,103,38,150,151,152,40,153,154,155,156],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","tool","stack","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":41},"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",[],[164,165,166,167,168,169,170,171,33,172,173,174,175,176,40,177,178],"write special chars ts check","write","check","type","files","filters","only","template","python","typescript","output","Existing","type-checking","errors","script",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":185,"publishedAt":41},"01M6HYAH05HGV7SVWSVR8PJRQD","write-special-chars-readback","Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, with mandatory post-write verification via read_file and cleanup of \u002Ftmp helper scripts.","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fshowcase\u002Fskills\u002Fwrite-special-chars-readback\u002FSKILL.md",[],[186,187,165,84,40,178,188,189,190,191,192,171,33,193,194,172],"write special chars readback","readback","helper","post","via","scripts","read","verification","cleanup"]