[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HXKASG8B17F6JM7DW09D5G":3,"skill-same:01M6HXKASG8B17F6JM7DW09D5G":68},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M6HXKASG8B17F6JM7DW09D5G","fallback-script-execution",null,"Two-step script execution workflow for debugging when shell_agent and execute_code_sandbox consistently fail","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\u002Ffallback-script-execution\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34],"execution","fallback","script","fallback script execution","sandbox","workflow","debugging","code","shell","execute","for","2026-11-10 10:12:30",false,"---\nname: fallback-script-execution\ndescription: Two-step script execution workflow for debugging when shell_agent and execute_code_sandbox consistently fail\n---\n\n# Fallback Script Execution with write_file + run_shell\n\n## When to Use This Skill\n\nUse this pattern when:\n- `shell_agent` fails repeatedly with unclear error messages\n- `execute_code_sandbox` consistently errors or times out\n- You need better visibility into what's happening during execution\n- Debugging inline code or delegated agents proves difficult\n\n## Core Pattern\n\nInstead of delegating execution to an agent or running inline code, use this two-step approach:\n\n1. **Write script to file** using `write_file`\n2. **Execute script** using `run_shell` with `python script.py`\n\nThis provides:\n- Clearer error messages (full stack traces visible in run_shell output)\n- Easier debugging (script persists for inspection)\n- Better control over execution environment\n- Ability to modify and re-run without rewriting code\n\n## Step-by-Step Instructions\n\n### Step 1: Write the Script File\n\nUse `write_file` to create a self-contained Python script:\n\n```\nwrite_file with:\n  path: \"path\u002Fto\u002Fscript_name.py\"\n  content: |\n    #!\u002Fusr\u002Fbin\u002Fenv python3\n    # Your complete script here\n    # Include imports, logic, and error handling\n```\n\n**Best Practices:**\n- Include descriptive comments\n- Add try\u002Fexcept blocks for error handling\n- Print intermediate results for debugging\n- Use absolute or clear relative paths\n\n### Step 2: Execute the Script\n\nUse `run_shell` to execute the script:\n\n```\nrun_shell with:\n  command: \"python path\u002Fto\u002Fscript_name.py\"\n```\n\n**Best Practices:**\n- Capture and examine full output\n- If errors occur, the script file is still available for inspection\n- You can re-run with modifications without starting over\n\n## Example: Data Processing Task\n\n### ❌ Problematic Approach (shell_agent fails repeatedly)\n\n```\nshell_agent with:\n  task: \"Load Excel file, calculate correlations, save results\"\n```\n\n*Result: Agent struggles with path handling, unclear errors*\n\n### ✅ Recommended Approach (write_file + run_shell)\n\n```\n# Step 1: Write script\nwrite_file with:\n  path: \"correlation_analysis.py\"\n  content: |\n    import pandas as pd\n    import sys\n    \n    try:\n        # Load data\n        df = pd.read_excel('data.xlsx', sheet_name='Returns')\n        print(f\"Loaded {len(df)} rows\")\n        \n        # Calculate correlation\n        corr = df.corr()\n        print(f\"Correlation matrix shape: {corr.shape}\")\n        \n        # Save results\n        with pd.ExcelWriter('output.xlsx') as writer:\n            df.to_excel(writer, sheet_name='Returns')\n            corr.to_excel(writer, sheet_name='Correlation')\n        \n        print(\"SUCCESS: output.xlsx created\")\n    except Exception as e:\n        print(f\"ERROR: {type(e).__name__}: {e}\", file=sys.stderr)\n        sys.exit(1)\n\n# Step 2: Execute script\nrun_shell with:\n  command: \"python correlation_analysis.py\"\n```\n\n## Debugging Tips\n\n1. **Add print statements** at key points to trace execution\n2. **Check file paths** - use `run_shell` with `ls -la path\u002F` to verify files exist\n3. **Inspect errors** - run_shell output shows full Python stack traces\n4. **Modify and re-run** - edit the script file and execute again without rewriting\n\n## When to Escalate\n\nIf this pattern also fails:\n- Verify Python is available: `run_shell` with `which python` or `python --version`\n- Check file permissions: `run_shell` with `ls -la script.py`\n- Try explicit Python path: `run_shell` with `\u002Fusr\u002Fbin\u002Fpython script.py`\n- Consider task complexity - may need to break into smaller scripts","# Fallback Script Execution with write_file + run_shell\n\n## When to Use This Skill\n\nUse this pattern when:\n- `shell_agent` fails repeatedly with unclear error messages\n- `execute_code_sandbox` consistently errors or times out\n- You need better visibility into what's happening during execution\n- Debugging inline code or delegated agents proves difficult\n\n## Core Pattern\n\nInstead of delegating execution to an agent or running inline code, use this two-step approach:\n\n1. **Write script to file** using `write_file`\n2. **Execute script** using `run_shell` with `python script.py`\n\nThis provides:\n- Clearer error messages (full stack traces visible in run_shell output)\n- Easier debugging (script persists for inspection)\n- Better control over execution environment\n- Ability to modify and re-run without rewriting code\n\n## Step-by-Step Instructions\n\n### Step 1: Write the Script File\n\nUse `write_file` to create a self-contained Python script:\n\n```\nwrite_file with:\n  path: \"path\u002Fto\u002Fscript_name.py\"\n  content: |\n    #!\u002Fusr\u002Fbin\u002Fenv python3\n    # Your complete script here\n    # Include imports, logic, and error handling\n```\n\n**Best Practices:**\n- Include descriptive comments\n- Add try\u002Fexcept blocks for error handling\n- Print intermediate results for debugging\n- Use absolute or clear relative paths\n\n### Step 2: Execute the Script\n\nUse `run_shell` to execute the script:\n\n```\nrun_shell with:\n  command: \"python path\u002Fto\u002Fscript_name.py\"\n```\n\n**Best Practices:**\n- Capture and examine full output\n- If errors occur, the script file is still available for inspection\n- You can re-run with modifications without starting over\n\n## Example: Data Processing Task\n\n### ❌ Problematic Approach (shell_agent fails repeatedly)\n\n```\nshell_agent with:\n  task: \"Load Excel file, calculate correlations, save results\"\n```\n\n*Result: Agent struggles with path handling, unclear errors*\n\n### ✅ Recommended Approach (write_file + run_shell)\n\n```\n# Step 1: Write script\nwrite_file with:\n  path: \"correlation_analysis.py\"\n  content: |\n    import pandas as pd\n    import sys\n    \n    try:\n        # Load data\n        df = pd.read_excel('data.xlsx', sheet_name='Returns')\n        print(f\"Loaded {len(df)} rows\")\n        \n        # Calculate correlation\n        corr = df.corr()\n        print(f\"Correlation matrix shape: {corr.shape}\")\n        \n        # Save results\n        with pd.ExcelWriter('output.xlsx') as writer:\n            df.to_excel(writer, sheet_name='Returns')\n            corr.to_excel(writer, sheet_name='Correlation')\n        \n        print(\"SUCCESS: output.xlsx created\")\n    except Exception as e:\n        print(f\"ERROR: {type(e).__name__}: {e}\", file=sys.stderr)\n        sys.exit(1)\n\n# Step 2: Execute script\nrun_shell with:\n  command: \"python correlation_analysis.py\"\n```\n\n## Debugging Tips\n\n1. **Add print statements** at key points to trace execution\n2. **Check file paths** - use `run_shell` with `ls -la path\u002F` to verify files exist\n3. **Inspect errors** - run_shell output shows full Python stack traces\n4. **Modify and re-run** - edit the script file and execute again without rewriting\n\n## When to Escalate\n\nIf this pattern also fails:\n- Verify Python is available: `run_shell` with `which python` or `python --version`\n- Check file permissions: `run_shell` with `ls -la script.py`\n- Try explicit Python path: `run_shell` with `\u002Fusr\u002Fbin\u002Fpython script.py`\n- Consider task complexity - may need to break into smaller scripts",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Ffallback-script-execution",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":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add HKUDS\u002FAgentPilot --skill fallback-script-execution",{"tool":54,"command":55},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill fallback-script-execution",{"tool":57,"command":58},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill fallback-script-execution","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Ffallback-script-execution\u002FSKILL.md",true,[62],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},".skill_id","OTHER","其他",39,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Ffallback-script-execution\u002F.skill_id",[69,89,108,129,152,174],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":35},"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",[],[71,76,77,78,79,80,81,82,83,84,85,86,87,88],"prepare","requests","with","missing","installation","rsi","up","use","user","work","SET","run","experiments",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":35},"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",[],[91,96,97,98,99,100,101,102,103,104,105,106,107],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"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":115,"publishedAt":35},"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",[114],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[116,117,118,99,119,120,121,122,123,124,125,126,127,128],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search","Tools",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":136,"publishedAt":35},"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",[135],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[137,138,139,99,140,141,142,143,144,118,98,83,145,146,147,34,148,149,150,151],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","tool","stack","share","tasks","automation","MCP",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":35},"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",[],[159,160,161,162,163,164,165,166,167,168,169,170,171,172,34,173,26],"write special chars ts check","write","check","type","files","filters","only","template","file","python","typescript","output","Existing","type-checking","errors",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":180,"publishedAt":35},"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",[],[181,182,160,78,34,26,183,184,185,186,187,166,167,188,189,168],"write special chars readback","readback","helper","post","via","scripts","read","verification","cleanup"]