[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HWTY6YR9Y5XBB0D8S9S12B":3,"skill-same:01M6HWTY6YR9Y5XBB0D8S9S12B":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},"01M6HWTY6YR9Y5XBB0D8S9S12B","python-execution-fallback",null,"Four-step recovery workflow for code execution failures when inline Python fails","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\u002Fpython-execution-fallback\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28],"python","execution","fallback","python execution fallback","workflow","code","recovery","code execution","for","inline","2026-11-10 10:12:30",false,"---\nname: python-execution-fallback\ndescription: Four-step recovery workflow for code execution failures when inline Python fails\n---\n\n# Python Execution Fallback Workflow\n\nThis skill provides a systematic debugging approach when inline Python code execution fails, particularly in heredoc or shell_agent contexts.\n\n## Pattern Overview\n\nWhen Python code execution fails, follow this recovery workflow:\n\n1. **Attempt inline execution first** - Try running Python code directly\n2. **Write script to file on failure** - Persist the code to a `.py` file\n3. **Execute the file** - Run the saved script via shell\n4. **Validate output** - Verify results are correct and complete\n\n## When to Use\n\nApply this pattern when:\n- Inline Python execution fails with syntax or runtime errors\n- Heredoc-based code execution encounters parsing issues\n- Working with complex multi-line scripts that need debugging\n- Need systematic approach to isolate execution failures\n- Spreadsheet\u002Fdata generation tasks fail in inline mode\n\n## Step-by-Step Instructions\n\n### Step 1: Attempt Inline Execution\n\nTry executing Python code inline first (using execute_code_sandbox or similar):\n\n```python\n# Example: Attempt inline execution\nimport pandas as pd\nimport openpyxl\n\ndf = pd.read_excel(\"input.xlsx\")\n# Process data...\ndf.to_excel(\"output.xlsx\", index=False)\n```\n\nIf this succeeds, proceed. If it fails, move to Step 2.\n\n### Step 2: Write Script to File (On Failure)\n\nWhen inline execution fails, write the complete script to a persistent file:\n\n```python\n# Capture the script content\nscript_content = '''\nimport pandas as pd\nimport openpyxl\nimport sys\n\ntry:\n    # Your original code here\n    df = pd.read_excel(\"input.xlsx\")\n    \n    # Processing logic\n    result_df = df.groupby(\"category\").sum()\n    \n    # Output\n    result_df.to_excel(\"output.xlsx\", index=False)\n    print(\"SUCCESS: File generated\")\n    \nexcept Exception as e:\n    print(f\"ERROR: {e}\", file=sys.stderr)\n    sys.exit(1)\n'''\n\n# Write to file\nwith open(\"script.py\", \"w\") as f:\n    f.write(script_content)\n\nprint(\"Script written to script.py\")\n```\n\n### Step 3: Execute the File\n\nRun the saved script using shell execution:\n\n```bash\npython script.py\n```\n\nOr with error capture:\n\n```bash\npython script.py 2>&1 | tee execution.log\n```\n\nThis approach:\n- Avoids heredoc parsing issues\n- Provides clearer error messages\n- Allows script inspection and modification\n- Enables re-execution without rewriting\n\n### Step 4: Validate Output\n\nVerify the results are correct:\n\n```python\n# Validation script\nimport pandas as pd\nimport os\n\n# Check file exists\nif os.path.exists(\"output.xlsx\"):\n    df = pd.read_excel(\"output.xlsx\")\n    print(f\"Rows: {len(df)}, Columns: {len(df.columns)}\")\n    print(df.head())\n    print(\"VALIDATION: PASSED\")\nelse:\n    print(\"VALIDATION: FAILED - Output file missing\")\n```\n\n## Code Example: Complete Workflow\n\n```python\n# Full fallback workflow example\ndef generate_spreadsheet_fallback(data, output_path):\n    \"\"\"Generate spreadsheet with fallback workflow\"\"\"\n    \n    # Step 1: Try inline\n    inline_script = f'''\nimport pandas as pd\ndata = {data}\ndf = pd.DataFrame(data)\ndf.to_excel(\"{output_path}\", index=False)\n'''\n    \n    try:\n        # Attempt inline execution\n        result = execute_code_sandbox(code=inline_script)\n        if \"error\" not in result.lower():\n            return \"SUCCESS_INLINE\"\n    except Exception as e:\n        pass\n    \n    # Step 2: Write to file\n    file_script = f'''\nimport pandas as pd\nimport sys\n\ntry:\n    data = {data}\n    df = pd.DataFrame(data)\n    df.to_excel(\"{output_path}\", index=False)\n    print(\"SUCCESS\")\nexcept Exception as e:\n    print(f\"ERROR: {{e}}\", file=sys.stderr)\n    sys.exit(1)\n'''\n    \n    with open(\"generate.py\", \"w\") as f:\n        f.write(file_script)\n    \n    # Step 3: Execute file\n    shell_result = run_shell(command=\"python generate.py\")\n    \n    # Step 4: Validate\n    if os.path.exists(output_path):\n        return \"SUCCESS_FILE\"\n    else:\n        return \"FAILED\"\n```\n\n## Best Practices\n\n1. **Include error handling** in file-based scripts (try\u002Fexcept with sys.stderr)\n2. **Add success indicators** (print statements) to confirm execution\n3. **Preserve original logic** when converting from inline to file\n4. **Check return codes** when executing scripts via shell\n5. **Clean up temporary files** after successful validation\n6. **Log both stdout and stderr** for debugging\n\n## Common Failure Scenarios\n\nThis pattern helps resolve:\n- Heredoc string escaping issues\n- Multi-line code formatting problems\n- Import path resolution failures\n- Environment variable access issues\n- Complex indentation in inline code\n\n## Related Patterns\n\n- Combine with `retry-with-modification` for iterative debugging\n- Use alongside `output-validation-check` for result verification\n- Pair with `error-log-analysis` for root cause identification","# Python Execution Fallback Workflow\n\nThis skill provides a systematic debugging approach when inline Python code execution fails, particularly in heredoc or shell_agent contexts.\n\n## Pattern Overview\n\nWhen Python code execution fails, follow this recovery workflow:\n\n1. **Attempt inline execution first** - Try running Python code directly\n2. **Write script to file on failure** - Persist the code to a `.py` file\n3. **Execute the file** - Run the saved script via shell\n4. **Validate output** - Verify results are correct and complete\n\n## When to Use\n\nApply this pattern when:\n- Inline Python execution fails with syntax or runtime errors\n- Heredoc-based code execution encounters parsing issues\n- Working with complex multi-line scripts that need debugging\n- Need systematic approach to isolate execution failures\n- Spreadsheet\u002Fdata generation tasks fail in inline mode\n\n## Step-by-Step Instructions\n\n### Step 1: Attempt Inline Execution\n\nTry executing Python code inline first (using execute_code_sandbox or similar):\n\n```python\n# Example: Attempt inline execution\nimport pandas as pd\nimport openpyxl\n\ndf = pd.read_excel(\"input.xlsx\")\n# Process data...\ndf.to_excel(\"output.xlsx\", index=False)\n```\n\nIf this succeeds, proceed. If it fails, move to Step 2.\n\n### Step 2: Write Script to File (On Failure)\n\nWhen inline execution fails, write the complete script to a persistent file:\n\n```python\n# Capture the script content\nscript_content = '''\nimport pandas as pd\nimport openpyxl\nimport sys\n\ntry:\n    # Your original code here\n    df = pd.read_excel(\"input.xlsx\")\n    \n    # Processing logic\n    result_df = df.groupby(\"category\").sum()\n    \n    # Output\n    result_df.to_excel(\"output.xlsx\", index=False)\n    print(\"SUCCESS: File generated\")\n    \nexcept Exception as e:\n    print(f\"ERROR: {e}\", file=sys.stderr)\n    sys.exit(1)\n'''\n\n# Write to file\nwith open(\"script.py\", \"w\") as f:\n    f.write(script_content)\n\nprint(\"Script written to script.py\")\n```\n\n### Step 3: Execute the File\n\nRun the saved script using shell execution:\n\n```bash\npython script.py\n```\n\nOr with error capture:\n\n```bash\npython script.py 2>&1 | tee execution.log\n```\n\nThis approach:\n- Avoids heredoc parsing issues\n- Provides clearer error messages\n- Allows script inspection and modification\n- Enables re-execution without rewriting\n\n### Step 4: Validate Output\n\nVerify the results are correct:\n\n```python\n# Validation script\nimport pandas as pd\nimport os\n\n# Check file exists\nif os.path.exists(\"output.xlsx\"):\n    df = pd.read_excel(\"output.xlsx\")\n    print(f\"Rows: {len(df)}, Columns: {len(df.columns)}\")\n    print(df.head())\n    print(\"VALIDATION: PASSED\")\nelse:\n    print(\"VALIDATION: FAILED - Output file missing\")\n```\n\n## Code Example: Complete Workflow\n\n```python\n# Full fallback workflow example\ndef generate_spreadsheet_fallback(data, output_path):\n    \"\"\"Generate spreadsheet with fallback workflow\"\"\"\n    \n    # Step 1: Try inline\n    inline_script = f'''\nimport pandas as pd\ndata = {data}\ndf = pd.DataFrame(data)\ndf.to_excel(\"{output_path}\", index=False)\n'''\n    \n    try:\n        # Attempt inline execution\n        result = execute_code_sandbox(code=inline_script)\n        if \"error\" not in result.lower():\n            return \"SUCCESS_INLINE\"\n    except Exception as e:\n        pass\n    \n    # Step 2: Write to file\n    file_script = f'''\nimport pandas as pd\nimport sys\n\ntry:\n    data = {data}\n    df = pd.DataFrame(data)\n    df.to_excel(\"{output_path}\", index=False)\n    print(\"SUCCESS\")\nexcept Exception as e:\n    print(f\"ERROR: {{e}}\", file=sys.stderr)\n    sys.exit(1)\n'''\n    \n    with open(\"generate.py\", \"w\") as f:\n        f.write(file_script)\n    \n    # Step 3: Execute file\n    shell_result = run_shell(command=\"python generate.py\")\n    \n    # Step 4: Validate\n    if os.path.exists(output_path):\n        return \"SUCCESS_FILE\"\n    else:\n        return \"FAILED\"\n```\n\n## Best Practices\n\n1. **Include error handling** in file-based scripts (try\u002Fexcept with sys.stderr)\n2. **Add success indicators** (print statements) to confirm execution\n3. **Preserve original logic** when converting from inline to file\n4. **Check return codes** when executing scripts via shell\n5. **Clean up temporary files** after successful validation\n6. **Log both stdout and stderr** for debugging\n\n## Common Failure Scenarios\n\nThis pattern helps resolve:\n- Heredoc string escaping issues\n- Multi-line code formatting problems\n- Import path resolution failures\n- Environment variable access issues\n- Complex indentation in inline code\n\n## Related Patterns\n\n- Combine with `retry-with-modification` for iterative debugging\n- Use alongside `output-validation-check` for result verification\n- Pair with `error-log-analysis` for root cause identification",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fpython-execution-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":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add HKUDS\u002FAgentPilot --skill python-execution-fallback",{"tool":48,"command":49},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill python-execution-fallback",{"tool":51,"command":52},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill python-execution-fallback","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fpython-execution-fallback\u002FSKILL.md",true,[56],{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},".skill_id","OTHER","其他",39,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fpython-execution-fallback\u002F.skill_id",[63,83,102,127,150,172],{"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",[],[65,70,71,72,73,74,75,76,77,78,79,80,81,82],"prepare","requests","with","missing","installation","rsi","up","use","user","work","SET","run","experiments",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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",[],[85,90,91,92,93,94,95,96,97,98,99,100,101],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":113,"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",[108],{"categoryNo":109,"categoryName":110,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[114,115,116,93,117,118,119,120,121,122,123,124,125,126],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search","Tools",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":134,"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",[133],{"categoryNo":109,"categoryName":110,"taxonomyType":111,"taxonomyTypeDesc":112},[135,136,137,93,138,139,140,141,142,116,92,77,143,144,145,27,146,147,148,149],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","tool","stack","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",[],[157,158,159,160,161,162,163,164,165,19,166,167,168,169,27,170,171],"write special chars ts check","write","check","type","files","filters","only","template","file","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",[],[179,180,158,72,27,171,181,182,183,184,185,164,165,186,187,19],"write special chars readback","readback","helper","post","via","scripts","read","verification","cleanup"]