[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HWZ4K4SCNZAASVA9EVT15W":3,"skill-same:01M6HWZ4K4SCNZAASVA9EVT15W":62},{"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":18,"publishedAt":29,"linkOnly":30,"markdownContent":31,"markdownBody":32,"frontMatter":33,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":6,"updatedAt":41,"install":42,"resources":55},"01M6HWZ4K4SCNZAASVA9EVT15W","sandbox-failure-recovery",null,"Recover from execute_code_sandbox failures by writing code to file and executing via run_shell","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\u002Fsandbox-failure-recovery\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28],"sandbox","recovery","sandbox failure recovery","writing","run","code","file","shell","execute","via","2026-11-10 10:12:30",false,"---\nname: sandbox-failure-recovery\ndescription: Recover from execute_code_sandbox failures by writing code to file and executing via run_shell\n---\n\n# Sandbox Failure Recovery Workflow\n\nWhen `execute_code_sandbox` fails (often due to infrastructure issues, timeouts, or complex dependencies), use this recovery pattern to achieve identical results by writing the code to a file and executing it directly.\n\n## When to Use This Skill\n\n- `execute_code_sandbox` returns an error or times out\n- The task involves spreadsheet generation (Excel, CSV) or file output\n- You have working Python code that needs to be executed\n- The sandbox environment appears unstable\n\n## Step-by-Step Instructions\n\n### Step 1: Preserve the Failed Code\n\nWhen `execute_code_sandbox` fails, capture the Python code that was attempted. If the code was generated but not saved, reconstruct it from the execution attempt.\n\n### Step 2: Write Code to File\n\nUse `write_file` to save the Python script to a `.py` file:\n\n```\nwrite_file with:\n- path: \"script_name.py\" (e.g., \"generate_report.py\", \"process_data.py\")\n- content: \u003Cthe full Python code>\n```\n\n**Example:**\n```python\n# Content for write_file\nimport pandas as pd\nfrom openpyxl import Workbook\n\n# Your spreadsheet generation logic here\ndf = pd.DataFrame({'Revenue': [100, 200, 300]})\ndf.to_excel('output.xlsx', index=False)\n```\n\n### Step 3: Execute via run_shell\n\nRun the saved script using `run_shell` with Python 3:\n\n```\nrun_shell with:\n- command: \"python3 script_name.py\"\n- timeout: 60 (or higher for complex operations)\n```\n\n### Step 4: Verify Output\n\nCheck that the expected output files were created:\n\n```\nlist_dir with:\n- path: \".\"\n```\n\nOr read the generated file to confirm correctness:\n\n```\nread_file with:\n- file_path: \"output.xlsx\"\n- filetype: \"xlsx\"\n```\n\n## Complete Example\n\n**Scenario:** Generate an Excel P&L report after sandbox failure.\n\n```yaml\n# Step 1: Write the Python script\nwrite_file:\n  path: \"generate_pnl_report.py\"\n  content: |\n    import pandas as pd\n    from openpyxl import Workbook\n    \n    # Create revenue data\n    data = {\n        'Tour Stop': ['London', 'Paris', 'Berlin'],\n        'Revenue': [50000, 45000, 38000],\n        'Withholding Tax': [5000, 4500, 3800],\n        'Expenses': [12000, 11000, 9500]\n    }\n    df = pd.DataFrame(data)\n    df['Net Income'] = df['Revenue'] - df['Withholding Tax'] - df['Expenses']\n    \n    # Export to Excel\n    df.to_excel('pnl_report.xlsx', index=False)\n    print(\"Report generated successfully\")\n\n# Step 2: Execute the script\nrun_shell:\n  command: \"python3 generate_pnl_report.py\"\n  timeout: 60\n\n# Step 3: Verify\nlist_dir:\n  path: \".\"\n```\n\n## Best Practices\n\n1. **Use descriptive filenames** - Name files after their purpose (e.g., `generate_report.py`, `process_spreadsheet.py`)\n\n2. **Set appropriate timeouts** - Complex operations may need 60+ seconds\n\n3. **Include error handling in your Python code** - Add try\u002Fexcept blocks to capture and report issues:\n   ```python\n   try:\n       # Your code here\n   except Exception as e:\n       print(f\"Error: {e}\")\n       raise\n   ```\n\n4. **Clean up temporary files** - After successful execution, you may remove the `.py` file if not needed\n\n5. **Check dependencies** - Ensure required packages (pandas, openpyxl, etc.) are available in the shell environment\n\n## Why This Works\n\n- `run_shell` executes in a more stable environment than the sandbox\n- File-based execution avoids sandbox memory\u002Fresource constraints\n- The Python interpreter in the shell has full access to installed packages\n- Output files are written directly to the workspace\n\n\u003CTHIS_SKILL_EVOLVED>","# Sandbox Failure Recovery Workflow\n\nWhen `execute_code_sandbox` fails (often due to infrastructure issues, timeouts, or complex dependencies), use this recovery pattern to achieve identical results by writing the code to a file and executing it directly.\n\n## When to Use This Skill\n\n- `execute_code_sandbox` returns an error or times out\n- The task involves spreadsheet generation (Excel, CSV) or file output\n- You have working Python code that needs to be executed\n- The sandbox environment appears unstable\n\n## Step-by-Step Instructions\n\n### Step 1: Preserve the Failed Code\n\nWhen `execute_code_sandbox` fails, capture the Python code that was attempted. If the code was generated but not saved, reconstruct it from the execution attempt.\n\n### Step 2: Write Code to File\n\nUse `write_file` to save the Python script to a `.py` file:\n\n```\nwrite_file with:\n- path: \"script_name.py\" (e.g., \"generate_report.py\", \"process_data.py\")\n- content: \u003Cthe full Python code>\n```\n\n**Example:**\n```python\n# Content for write_file\nimport pandas as pd\nfrom openpyxl import Workbook\n\n# Your spreadsheet generation logic here\ndf = pd.DataFrame({'Revenue': [100, 200, 300]})\ndf.to_excel('output.xlsx', index=False)\n```\n\n### Step 3: Execute via run_shell\n\nRun the saved script using `run_shell` with Python 3:\n\n```\nrun_shell with:\n- command: \"python3 script_name.py\"\n- timeout: 60 (or higher for complex operations)\n```\n\n### Step 4: Verify Output\n\nCheck that the expected output files were created:\n\n```\nlist_dir with:\n- path: \".\"\n```\n\nOr read the generated file to confirm correctness:\n\n```\nread_file with:\n- file_path: \"output.xlsx\"\n- filetype: \"xlsx\"\n```\n\n## Complete Example\n\n**Scenario:** Generate an Excel P&L report after sandbox failure.\n\n```yaml\n# Step 1: Write the Python script\nwrite_file:\n  path: \"generate_pnl_report.py\"\n  content: |\n    import pandas as pd\n    from openpyxl import Workbook\n    \n    # Create revenue data\n    data = {\n        'Tour Stop': ['London', 'Paris', 'Berlin'],\n        'Revenue': [50000, 45000, 38000],\n        'Withholding Tax': [5000, 4500, 3800],\n        'Expenses': [12000, 11000, 9500]\n    }\n    df = pd.DataFrame(data)\n    df['Net Income'] = df['Revenue'] - df['Withholding Tax'] - df['Expenses']\n    \n    # Export to Excel\n    df.to_excel('pnl_report.xlsx', index=False)\n    print(\"Report generated successfully\")\n\n# Step 2: Execute the script\nrun_shell:\n  command: \"python3 generate_pnl_report.py\"\n  timeout: 60\n\n# Step 3: Verify\nlist_dir:\n  path: \".\"\n```\n\n## Best Practices\n\n1. **Use descriptive filenames** - Name files after their purpose (e.g., `generate_report.py`, `process_spreadsheet.py`)\n\n2. **Set appropriate timeouts** - Complex operations may need 60+ seconds\n\n3. **Include error handling in your Python code** - Add try\u002Fexcept blocks to capture and report issues:\n   ```python\n   try:\n       # Your code here\n   except Exception as e:\n       print(f\"Error: {e}\")\n       raise\n   ```\n\n4. **Clean up temporary files** - After successful execution, you may remove the `.py` file if not needed\n\n5. **Check dependencies** - Ensure required packages (pandas, openpyxl, etc.) are available in the shell environment\n\n## Why This Works\n\n- `run_shell` executes in a more stable environment than the sandbox\n- File-based execution avoids sandbox memory\u002Fresource constraints\n- The Python interpreter in the shell has full access to installed packages\n- Output files are written directly to the workspace\n\n\u003CTHIS_SKILL_EVOLVED>",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fsandbox-failure-recovery",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":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add HKUDS\u002FAgentPilot --skill sandbox-failure-recovery",{"tool":48,"command":49},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill sandbox-failure-recovery",{"tool":51,"command":52},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill sandbox-failure-recovery","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fsandbox-failure-recovery\u002FSKILL.md",true,[56],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},".skill_id","OTHER","其他",38,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fsandbox-failure-recovery\u002F.skill_id",[63,82,101,126,150,172],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":29},"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",[],[65,70,71,72,73,74,75,76,77,78,79,80,23,81],"prepare","requests","with","missing","installation","rsi","up","use","user","work","SET","experiments",{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":29},"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",[],[84,89,90,91,92,93,94,95,96,97,98,99,100],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":112,"publishedAt":29},"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",[107],{"categoryNo":108,"categoryName":109,"taxonomyType":110,"taxonomyTypeDesc":111},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[113,114,115,92,116,117,118,119,120,121,122,123,124,125],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search","Tools",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":133,"publishedAt":29},"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",[132],{"categoryNo":108,"categoryName":109,"taxonomyType":110,"taxonomyTypeDesc":111},[134,135,136,92,137,138,139,140,141,115,91,77,142,143,144,145,146,147,148,149],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","tool","stack","for","share","tasks","automation","MCP",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":156,"publishedAt":29},"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",[],[157,158,159,160,161,162,163,164,25,165,166,167,168,169,145,170,171],"write special chars ts check","write","check","type","files","filters","only","template","python","typescript","output","Existing","type-checking","errors","script",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":178,"publishedAt":29},"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",[],[179,180,158,72,145,171,181,182,28,183,184,164,25,185,186,165],"write special chars readback","readback","helper","post","scripts","read","verification","cleanup"]