[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HXX34H0H7NGKAHA90YF5YV":3,"skill-same:01M6HXX34H0H7NGKAHA90YF5YV":66},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":44,"ownerDescription":6,"updatedAt":45,"install":46,"resources":59},"01M6HXX34H0H7NGKAHA90YF5YV","run-shell-fallback",null,"Use run_shell with inline Python as a reliable fallback 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\u002Frun-shell-fallback\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32],"run","shell","fallback","run shell fallback","python","sandbox","code","file","read","execute","use","as","with","inline","2026-11-10 10:12:30",false,"---\nname: run-shell-fallback\ndescription: Use run_shell with inline Python as a reliable fallback when execute_code_sandbox or read_file fail\n---\n\n# Run Shell Fallback Pattern\n\nThis skill provides a reliable workaround when `execute_code_sandbox` or `read_file` fail with 'unknown error' by switching to `run_shell` with inline Python code.\n\n## When to Use\n\nApply this pattern when you encounter:\n- `execute_code_sandbox` fails with \"unknown error\" or timeout\n- `read_file` fails to read accessible files with \"unknown error\"\n- Sandbox environment is unreliable for your specific task\n\n## How to Implement\n\n### 1. File Reading Fallback\n\nWhen `read_file` fails, use `run_shell` with Python or `cat`:\n\n**For text files:**\n```bash\nrun_shell(command=\"cat \u002Fpath\u002Fto\u002Ffile.txt\")\n```\n\n**For structured parsing (Python one-liner):**\n```bash\nrun_shell(command=\"python3 -c \\\"import json; print(json.load(open('\u002Fpath\u002Fto\u002Ffile.json')))\\\"\")\n```\n\n**For multi-line Python processing:**\n```bash\nrun_shell(command=\"python3 \u003C\u003C 'EOF'\nwith open('\u002Fpath\u002Fto\u002Ffile.txt', 'r') as f:\n    content = f.read()\n    # Process content here\n    print(content.upper())\nEOF\")\n```\n\n### 2. Code Execution Fallback\n\nWhen `execute_code_sandbox` fails, use `run_shell` with inline Python:\n\n**Simple one-liners:**\n```bash\nrun_shell(command=\"python3 -c \\\"print('Hello'); import os; print(os.getcwd())\\\"\")\n```\n\n**Multi-line scripts (heredoc):**\n```bash\nrun_shell(command=\"python3 \u003C\u003C 'EOF'\nimport os\nimport json\n\ndef process_data(data):\n    return {k: v.upper() if isinstance(v, str) else v for k, v in data.items()}\n\nwith open('input.json') as f:\n    data = json.load(f)\n    \nresult = process_data(data)\nprint(json.dumps(result, indent=2))\nEOF\")\n```\n\n**With inline file write:**\n```bash\nrun_shell(command=\"python3 \u003C\u003C 'EOF'\nresult = {'status': 'success', 'count': 42}\nwith open('output.json', 'w') as f:\n    json.dump(result, f, indent=2)\nprint('File written successfully')\nEOF\")\n```\n\n### 3. Decision Flow\n\n```\n1. Attempt execute_code_sandbox or read_file\n2. If failure with 'unknown error':\n   a. Determine task type (code execution vs file reading)\n   b. Choose inline Python approach (-c for simple, heredoc for complex)\n   c. Execute via run_shell\n   d. Parse output as needed\n3. Continue with task using results from run_shell\n```\n\n## Best Practices\n\n1. **Escape quotes properly** in `-c` commands: Use `\\\"` for double quotes inside the command string\n\n2. **Use heredoc for complex scripts**: When code exceeds 2-3 lines or needs multiple imports, use `\u003C\u003C 'EOF'` syntax\n\n3. **Quote EOF marker**: Use `\u003C\u003C 'EOF'` (with quotes) to prevent variable expansion in the heredoc\n\n4. **Capture stdout**: Design your inline Python to print results to stdout for easy capture\n\n5. **Error handling**: Add try\u002Fexcept blocks in your inline Python to catch and report errors clearly\n\n6. **File paths**: Use absolute paths when possible, or ensure working directory is correct\n\n## Examples\n\n### Example 1: Read and parse JSON after read_file failure\n```bash\nrun_shell(command=\"python3 -c \\\"import json; data=json.load(open('config.json')); print(data['key'])\\\"\")\n```\n\n### Example 2: Process CSV data after execute_code_sandbox failure\n```bash\nrun_shell(command=\"python3 \u003C\u003C 'EOF'\nimport csv\nwith open('data.csv', 'r') as f:\n    reader = csv.DictReader(f)\n    rows = list(reader)\n    print(f\\\"Total rows: {len(rows)}\\\")\n    for row in rows[:5]:\n        print(row)\nEOF\")\n```\n\n### Example 3: Transform and write output file\n```bash\nrun_shell(command=\"python3 \u003C\u003C 'EOF'\nimport json\nwith open('input.json') as f:\n    data = json.load(f)\ntransformed = [item.upper() if isinstance(item, str) else item for item in data]\nwith open('output.json', 'w') as f:\n    json.dump(transformed, f, indent=2)\nprint('Transformation complete')\nEOF\")\n```\n\n## Limitations\n\n- run_shell executes in the shell environment, not the sandbox - ensure paths and dependencies are available\n- Output is limited to stdout\u002Fstderr - use file writes for large data\n- Complex multi-file projects may require creating temporary script files first","# Run Shell Fallback Pattern\n\nThis skill provides a reliable workaround when `execute_code_sandbox` or `read_file` fail with 'unknown error' by switching to `run_shell` with inline Python code.\n\n## When to Use\n\nApply this pattern when you encounter:\n- `execute_code_sandbox` fails with \"unknown error\" or timeout\n- `read_file` fails to read accessible files with \"unknown error\"\n- Sandbox environment is unreliable for your specific task\n\n## How to Implement\n\n### 1. File Reading Fallback\n\nWhen `read_file` fails, use `run_shell` with Python or `cat`:\n\n**For text files:**\n```bash\nrun_shell(command=\"cat \u002Fpath\u002Fto\u002Ffile.txt\")\n```\n\n**For structured parsing (Python one-liner):**\n```bash\nrun_shell(command=\"python3 -c \\\"import json; print(json.load(open('\u002Fpath\u002Fto\u002Ffile.json')))\\\"\")\n```\n\n**For multi-line Python processing:**\n```bash\nrun_shell(command=\"python3 \u003C\u003C 'EOF'\nwith open('\u002Fpath\u002Fto\u002Ffile.txt', 'r') as f:\n    content = f.read()\n    # Process content here\n    print(content.upper())\nEOF\")\n```\n\n### 2. Code Execution Fallback\n\nWhen `execute_code_sandbox` fails, use `run_shell` with inline Python:\n\n**Simple one-liners:**\n```bash\nrun_shell(command=\"python3 -c \\\"print('Hello'); import os; print(os.getcwd())\\\"\")\n```\n\n**Multi-line scripts (heredoc):**\n```bash\nrun_shell(command=\"python3 \u003C\u003C 'EOF'\nimport os\nimport json\n\ndef process_data(data):\n    return {k: v.upper() if isinstance(v, str) else v for k, v in data.items()}\n\nwith open('input.json') as f:\n    data = json.load(f)\n    \nresult = process_data(data)\nprint(json.dumps(result, indent=2))\nEOF\")\n```\n\n**With inline file write:**\n```bash\nrun_shell(command=\"python3 \u003C\u003C 'EOF'\nresult = {'status': 'success', 'count': 42}\nwith open('output.json', 'w') as f:\n    json.dump(result, f, indent=2)\nprint('File written successfully')\nEOF\")\n```\n\n### 3. Decision Flow\n\n```\n1. Attempt execute_code_sandbox or read_file\n2. If failure with 'unknown error':\n   a. Determine task type (code execution vs file reading)\n   b. Choose inline Python approach (-c for simple, heredoc for complex)\n   c. Execute via run_shell\n   d. Parse output as needed\n3. Continue with task using results from run_shell\n```\n\n## Best Practices\n\n1. **Escape quotes properly** in `-c` commands: Use `\\\"` for double quotes inside the command string\n\n2. **Use heredoc for complex scripts**: When code exceeds 2-3 lines or needs multiple imports, use `\u003C\u003C 'EOF'` syntax\n\n3. **Quote EOF marker**: Use `\u003C\u003C 'EOF'` (with quotes) to prevent variable expansion in the heredoc\n\n4. **Capture stdout**: Design your inline Python to print results to stdout for easy capture\n\n5. **Error handling**: Add try\u002Fexcept blocks in your inline Python to catch and report errors clearly\n\n6. **File paths**: Use absolute paths when possible, or ensure working directory is correct\n\n## Examples\n\n### Example 1: Read and parse JSON after read_file failure\n```bash\nrun_shell(command=\"python3 -c \\\"import json; data=json.load(open('config.json')); print(data['key'])\\\"\")\n```\n\n### Example 2: Process CSV data after execute_code_sandbox failure\n```bash\nrun_shell(command=\"python3 \u003C\u003C 'EOF'\nimport csv\nwith open('data.csv', 'r') as f:\n    reader = csv.DictReader(f)\n    rows = list(reader)\n    print(f\\\"Total rows: {len(rows)}\\\")\n    for row in rows[:5]:\n        print(row)\nEOF\")\n```\n\n### Example 3: Transform and write output file\n```bash\nrun_shell(command=\"python3 \u003C\u003C 'EOF'\nimport json\nwith open('input.json') as f:\n    data = json.load(f)\ntransformed = [item.upper() if isinstance(item, str) else item for item in data]\nwith open('output.json', 'w') as f:\n    json.dump(transformed, f, indent=2)\nprint('Transformation complete')\nEOF\")\n```\n\n## Limitations\n\n- run_shell executes in the shell environment, not the sandbox - ensure paths and dependencies are available\n- Output is limited to stdout\u002Fstderr - use file writes for large data\n- Complex multi-file projects may require creating temporary script files first",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Frun-shell-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":47,"prompt":57,"zipAvailable":58},[48,51,54],{"tool":49,"command":50},"npx","npx skills add HKUDS\u002FAgentPilot --skill run-shell-fallback",{"tool":52,"command":53},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill run-shell-fallback",{"tool":55,"command":56},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill run-shell-fallback","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Frun-shell-fallback\u002FSKILL.md",true,[60],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},".skill_id","OTHER","其他",32,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Frun-shell-fallback\u002F.skill_id",[67,84,103,128,152,173],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":33},"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",[],[69,74,75,31,76,77,78,79,29,80,81,82,19,83],"prepare","requests","missing","installation","rsi","up","user","work","SET","experiments",{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":33},"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",[],[86,91,92,93,94,95,96,97,98,99,100,101,102],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":114,"publishedAt":33},"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",[109],{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[115,116,117,94,118,119,120,121,122,123,124,125,126,127],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search","Tools",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":135,"publishedAt":33},"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",[134],{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},[136,137,138,94,139,140,141,142,143,117,93,29,144,145,146,147,148,149,150,151],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","tool","stack","for","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":33},"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",[],[159,160,161,162,163,164,165,166,26,23,167,168,169,170,147,171,172],"write special chars ts check","write","check","type","files","filters","only","template","typescript","output","Existing","type-checking","errors","script",{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":33},"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",[],[180,181,160,31,147,172,182,183,184,185,27,166,26,186,187,23],"write special chars readback","readback","helper","post","via","scripts","verification","cleanup"]