[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HXK7Q3AATA616A97YRXMH3":3,"skill-same:01M6HXK7Q3AATA616A97YRXMH3":72},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":44,"commitSha":45,"skillDirectory":46,"forksCount":47,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":50,"ownerDescription":6,"updatedAt":51,"install":52,"resources":65},"01M6HXK7Q3AATA616A97YRXMH3","fallback-python-shell",null,"Use run_shell with Python heredoc when execute_code_sandbox or read_file 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-python-shell\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000004","电子表格",[27,28,29,30,31,32,33,34,35,36,37,38],"python","shell","fallback","fallback python shell","sandbox","run","code","file","read","execute","use","with","2026-11-10 10:12:30",false,"---\nname: fallback-python-shell\ndescription: Use run_shell with Python heredoc when execute_code_sandbox or read_file fail\n---\n\n# Shell-Based Python Fallback\n\n## When to Use\n\nUse this fallback pattern when:\n- `execute_code_sandbox` returns 'unknown error'\n- `read_file` returns 'unknown error' for supported formats\n- You need to process documents, analyze data, or read files programmatically\n\n## Core Technique\n\nRun Python code through `run_shell` using a heredoc. This bypasses sandbox execution issues while maintaining Python's full capabilities for file I\u002FO and data processing.\n\n### Basic Pattern\n\n```bash\npython3 \u003C\u003C 'EOF'\n# Your Python code here\nimport json\nimport os\n\n# Example: Read and process a file\nwith open('\u002Fpath\u002Fto\u002Ffile.txt', 'r') as f:\n    content = f.read()\n    print(content)\nEOF\n```\n\n### Key Syntax Points\n\n1. Use `python3 \u003C\u003C 'EOF'` (quoted EOF prevents variable expansion in the heredoc)\n2. Indent Python code starting from column 0 (no extra indentation from shell)\n3. End with `EOF` on its own line with no leading\u002Ftrailing whitespace\n4. Print results to stdout to capture them in the tool response\n\n## Common Use Cases\n\n### Reading Files (Fallback for read_file)\n\n```bash\npython3 \u003C\u003C 'EOF'\nimport json\n\n# Read text file\nwith open('document.txt', 'r') as f:\n    content = f.read()\n    print(content)\n\n# Read JSON file\nwith open('data.json', 'r') as f:\n    data = json.load(f)\n    print(json.dumps(data, indent=2))\nEOF\n```\n\n### Processing Excel\u002FCSV Files\n\n```bash\npython3 \u003C\u003C 'EOF'\nimport pandas as pd\n\n# Read Excel file\ndf = pd.read_excel('data.xlsx', sheet_name='Sheet1')\nprint(df.to_string())\nprint(f\"Shape: {df.shape}\")\n\n# Read CSV\ndf = pd.read_csv('data.csv')\nprint(df.head(10))\nEOF\n```\n\n### Reading PDF Files\n\n```bash\npython3 \u003C\u003C 'EOF'\nimport fitz  # PyMuPDF\n\ndoc = fitz.open('document.pdf')\nfor page_num in range(len(doc)):\n    page = doc[page_num]\n    text = page.get_text()\n    print(f\"=== Page {page_num + 1} ===\")\n    print(text)\ndoc.close()\nEOF\n```\n\n### Reading Word Documents\n\n```bash\npython3 \u003C\u003C 'EOF'\nfrom docx import Document\n\ndoc = Document('document.docx')\nfor para in doc.paragraphs:\n    print(para.text)\nEOF\n```\n\n### Data Analysis\n\n```bash\npython3 \u003C\u003C 'EOF'\nimport pandas as pd\nimport numpy as np\n\ndf = pd.read_csv('data.csv')\n\n# Basic statistics\nprint(f\"Shape: {df.shape}\")\nprint(f\"Columns: {list(df.columns)}\")\nprint(df.describe())\n\n# Filter and aggregate\nresult = df.groupby('category').agg({'value': 'sum'})\nprint(result)\nEOF\n```\n\n## Best Practices\n\n1. **Error Handling**: Wrap file operations in try\u002Fexcept blocks\n   ```bash\n   python3 \u003C\u003C 'EOF'\n   try:\n       with open('file.txt', 'r') as f:\n           content = f.read()\n           print(content)\n   except FileNotFoundError:\n       print(\"ERROR: File not found\")\n   except Exception as e:\n       print(f\"ERROR: {e}\")\n   EOF\n   ```\n\n2. **Large Output**: For large files, process in chunks or print summaries\n   ```bash\n   python3 \u003C\u003C 'EOF'\n   with open('large_file.csv', 'r') as f:\n       for i, line in enumerate(f):\n           if i \u003C 10:\n               print(line.strip())\n           else:\n               print(\"... truncated ...\")\n               break\n   EOF\n   ```\n\n3. **Working Directory**: Remember run_shell executes in the current working directory. Use absolute paths or ensure you're in the right directory.\n\n4. **Multiple Steps**: Chain related operations in a single heredoc rather than multiple calls\n   ```bash\n   python3 \u003C\u003C 'EOF'\n   # Do all related work in one call\n   with open('input.json') as f:\n       data = json.load(f)\n   \n   processed = [transform(x) for x in data]\n   \n   with open('output.json', 'w') as f:\n       json.dump(processed, f)\n   \n   print(\"Processing complete\")\n   EOF\n   ```\n\n## Troubleshooting\n\n- **Module not found**: Some packages may not be available. Stick to standard library or commonly pre-installed packages (pandas, numpy are often available).\n- **Permission errors**: Ensure files aren't in protected directories.\n- **Character encoding**: Specify encoding explicitly: `open('file.txt', 'r', encoding='utf-8')`\n- **Very long code**: Split into multiple heredocs or write to a temporary .py file first.","# Shell-Based Python Fallback\n\n## When to Use\n\nUse this fallback pattern when:\n- `execute_code_sandbox` returns 'unknown error'\n- `read_file` returns 'unknown error' for supported formats\n- You need to process documents, analyze data, or read files programmatically\n\n## Core Technique\n\nRun Python code through `run_shell` using a heredoc. This bypasses sandbox execution issues while maintaining Python's full capabilities for file I\u002FO and data processing.\n\n### Basic Pattern\n\n```bash\npython3 \u003C\u003C 'EOF'\n# Your Python code here\nimport json\nimport os\n\n# Example: Read and process a file\nwith open('\u002Fpath\u002Fto\u002Ffile.txt', 'r') as f:\n    content = f.read()\n    print(content)\nEOF\n```\n\n### Key Syntax Points\n\n1. Use `python3 \u003C\u003C 'EOF'` (quoted EOF prevents variable expansion in the heredoc)\n2. Indent Python code starting from column 0 (no extra indentation from shell)\n3. End with `EOF` on its own line with no leading\u002Ftrailing whitespace\n4. Print results to stdout to capture them in the tool response\n\n## Common Use Cases\n\n### Reading Files (Fallback for read_file)\n\n```bash\npython3 \u003C\u003C 'EOF'\nimport json\n\n# Read text file\nwith open('document.txt', 'r') as f:\n    content = f.read()\n    print(content)\n\n# Read JSON file\nwith open('data.json', 'r') as f:\n    data = json.load(f)\n    print(json.dumps(data, indent=2))\nEOF\n```\n\n### Processing Excel\u002FCSV Files\n\n```bash\npython3 \u003C\u003C 'EOF'\nimport pandas as pd\n\n# Read Excel file\ndf = pd.read_excel('data.xlsx', sheet_name='Sheet1')\nprint(df.to_string())\nprint(f\"Shape: {df.shape}\")\n\n# Read CSV\ndf = pd.read_csv('data.csv')\nprint(df.head(10))\nEOF\n```\n\n### Reading PDF Files\n\n```bash\npython3 \u003C\u003C 'EOF'\nimport fitz  # PyMuPDF\n\ndoc = fitz.open('document.pdf')\nfor page_num in range(len(doc)):\n    page = doc[page_num]\n    text = page.get_text()\n    print(f\"=== Page {page_num + 1} ===\")\n    print(text)\ndoc.close()\nEOF\n```\n\n### Reading Word Documents\n\n```bash\npython3 \u003C\u003C 'EOF'\nfrom docx import Document\n\ndoc = Document('document.docx')\nfor para in doc.paragraphs:\n    print(para.text)\nEOF\n```\n\n### Data Analysis\n\n```bash\npython3 \u003C\u003C 'EOF'\nimport pandas as pd\nimport numpy as np\n\ndf = pd.read_csv('data.csv')\n\n# Basic statistics\nprint(f\"Shape: {df.shape}\")\nprint(f\"Columns: {list(df.columns)}\")\nprint(df.describe())\n\n# Filter and aggregate\nresult = df.groupby('category').agg({'value': 'sum'})\nprint(result)\nEOF\n```\n\n## Best Practices\n\n1. **Error Handling**: Wrap file operations in try\u002Fexcept blocks\n   ```bash\n   python3 \u003C\u003C 'EOF'\n   try:\n       with open('file.txt', 'r') as f:\n           content = f.read()\n           print(content)\n   except FileNotFoundError:\n       print(\"ERROR: File not found\")\n   except Exception as e:\n       print(f\"ERROR: {e}\")\n   EOF\n   ```\n\n2. **Large Output**: For large files, process in chunks or print summaries\n   ```bash\n   python3 \u003C\u003C 'EOF'\n   with open('large_file.csv', 'r') as f:\n       for i, line in enumerate(f):\n           if i \u003C 10:\n               print(line.strip())\n           else:\n               print(\"... truncated ...\")\n               break\n   EOF\n   ```\n\n3. **Working Directory**: Remember run_shell executes in the current working directory. Use absolute paths or ensure you're in the right directory.\n\n4. **Multiple Steps**: Chain related operations in a single heredoc rather than multiple calls\n   ```bash\n   python3 \u003C\u003C 'EOF'\n   # Do all related work in one call\n   with open('input.json') as f:\n       data = json.load(f)\n   \n   processed = [transform(x) for x in data]\n   \n   with open('output.json', 'w') as f:\n       json.dump(processed, f)\n   \n   print(\"Processing complete\")\n   EOF\n   ```\n\n## Troubleshooting\n\n- **Module not found**: Some packages may not be available. Stick to standard library or commonly pre-installed packages (pandas, numpy are often available).\n- **Permission errors**: Ensure files aren't in protected directories.\n- **Character encoding**: Specify encoding explicitly: `open('file.txt', 'r', encoding='utf-8')`\n- **Very long code**: Split into multiple heredocs or write to a temporary .py file first.",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Ffallback-python-shell",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":53,"prompt":63,"zipAvailable":64},[54,57,60],{"tool":55,"command":56},"npx","npx skills add HKUDS\u002FAgentPilot --skill fallback-python-shell",{"tool":58,"command":59},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill fallback-python-shell",{"tool":61,"command":62},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill fallback-python-shell","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Ffallback-python-shell\u002FSKILL.md",true,[66],{"path":67,"resourceType":68,"resourceTypeDesc":69,"sizeBytes":70,"sourceHtmlUrl":71},".skill_id","OTHER","其他",35,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Ffallback-python-shell\u002F.skill_id",[73,90,109,132,156,177],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":39},"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",[],[75,80,81,38,82,83,84,85,37,86,87,88,32,89],"prepare","requests","missing","installation","rsi","up","user","work","SET","experiments",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":39},"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",[],[92,97,98,99,100,101,102,103,104,105,106,107,108],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":118,"publishedAt":39},"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",[115],{"categoryNo":116,"categoryName":117,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[119,120,121,100,122,123,124,125,126,127,128,129,130,131],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search","Tools",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":139,"publishedAt":39},"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",[138],{"categoryNo":116,"categoryName":117,"taxonomyType":21,"taxonomyTypeDesc":22},[140,141,142,100,143,144,145,146,147,121,99,37,148,149,150,151,152,153,154,155],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","tool","stack","for","share","tasks","automation","MCP",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":39},"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",[],[163,164,165,166,167,168,169,170,34,27,171,172,173,174,151,175,176],"write special chars ts check","write","check","type","files","filters","only","template","typescript","output","Existing","type-checking","errors","script",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":39},"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",[],[184,185,164,38,151,176,186,187,188,189,35,170,34,190,191,27],"write special chars readback","readback","helper","post","via","scripts","verification","cleanup"]