[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HXWJCQ7H3DWH3292E227B0":3,"skill-same:01M6HXWJCQ7H3DWH3292E227B0":74},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":6,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M6HXWJCQ7H3DWH3292E227B0","resilient-spreadsheet-workflow",null,"Resilient multi-step workflow for spreadsheet processing when execute_code_sandbox fails, using shell_agent exploration, file-based scripts, and verification steps","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\u002Fresilient-spreadsheet-workflow\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000004","电子表格","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40],"workflow","spreadsheet","resilient spreadsheet workflow","sandbox","code","verification","file","shell","execute","exploration","scripts","processing","multi","for","2026-11-10 10:12:30",false,"---\nname: resilient-spreadsheet-workflow\ndescription: Resilient multi-step workflow for spreadsheet processing when execute_code_sandbox fails, using shell_agent exploration, file-based scripts, and verification steps\n---\n\n# Resilient Spreadsheet Workflow\n\nThis skill provides a robust workflow for processing spreadsheet files (CSV, XLSX) when `execute_code_sandbox` encounters failures. It uses a combination of tools to ensure reliable execution and clear error diagnosis.\n\n## When to Use\n\n- Processing spreadsheet files when `execute_code_sandbox` returns unknown errors\n- Need to debug why spreadsheet operations fail\n- Require reliable file I\u002FO with verification at each step\n\n## Step-by-Step Workflow\n\n### Step 1: Initial Exploration with shell_agent\n\nStart by using `shell_agent` to explore the file structure and understand what files exist:\n\n```\nUse shell_agent to:\n- List files in the working directory\n- Identify spreadsheet files (CSV, XLSX)\n- Examine file sizes and basic structure\n```\n\n**Example task for shell_agent:**\n```\nExplore the current directory to find all spreadsheet files (CSV, XLSX). \nList their sizes and identify which files need processing.\n```\n\n### Step 2: Write Processing Script with write_file\n\nCreate a standalone script file rather than executing inline code:\n\n```python\n# Use write_file to create a script like \"process_sheet.py\"\ncontent = \"\"\"\nimport pandas as pd\nimport sys\n\ntry:\n    df = pd.read_csv('input.csv')  # or pd.read_excel for XLSX\n    # Perform your processing\n    result = df.describe()\n    result.to_csv('output.csv', index=False)\n    print(\"Processing complete\")\nexcept Exception as e:\n    print(f\"Error: {e}\", file=sys.stderr)\n    sys.exit(1)\n\"\"\"\n\nwrite_file(path=\"process_sheet.py\", content=content)\n```\n\n### Step 3: Execute with run_shell and Error Redirection\n\nExecute the script with stderr redirected to stdout for complete error capture:\n\n```bash\nrun_shell command=\"python process_sheet.py 2>&1\"\n```\n\nThe `2>&1` redirection ensures both stdout and stderr are captured together, making error messages visible.\n\n### Step 4: Isolate Errors with Verification Commands\n\nIf Step 3 fails, add targeted verification commands to diagnose the actual problem:\n\n```bash\n# Check if Python is available\nrun_shell command=\"which python 2>&1\"\n\n# Check if pandas is installed\nrun_shell command=\"python -c 'import pandas' 2>&1\"\n\n# Verify input file exists and is readable\nrun_shell command=\"ls -la input.csv 2>&1\"\n\n# Check file encoding\u002Fcontent\nrun_shell command=\"file input.csv 2>&1\"\nrun_shell command=\"head -5 input.csv 2>&1\"\n```\n\n### Step 5: Verify Output Before Reading\n\nBefore reading results with `read_file`, verify the output file exists:\n\n```\nlist_dir(path=\".\")\n# Confirm output file appears in the listing\n# Then proceed to read_file\n```\n\n## Complete Example\n\n```\n1. shell_agent(task=\"Find and describe all CSV\u002FXLSX files in current directory\")\n2. write_file(path=\"analyze_data.py\", content=\"\u003Cprocessing script>\")\n3. run_shell(command=\"python analyze_data.py 2>&1\")\n4. If error: run_shell(command=\"python -c 'import pandas; print(pandas.__version__)' 2>&1\")\n5. list_dir(path=\".\")  # Verify output exists\n6. read_file(filetype=\"csv\", file_path=\"output.csv\")\n```\n\n## Common Error Patterns\n\n| Symptom | Diagnostic Command | Likely Cause |\n|---------|-------------------|--------------|\n| Module not found | `python -c 'import pandas'` | Missing dependency |\n| File not found | `ls -la \u003Cfilename>` | Wrong path or name |\n| Permission denied | `ls -la \u003Cfilename>` | File permissions |\n| Encoding error | `file \u003Cfilename>` | Wrong file format |\n\n## Best Practices\n\n1. **Always use 2>&1** with run_shell for shell commands to capture full error output\n2. **Verify before reading** - use list_dir to confirm file existence before read_file\n3. **Break into small steps** - separate exploration, script writing, execution, and verification\n4. **Use shell_agent for unknowns** - when directory structure or file types are unclear\n5. **Write scripts to files** - more reliable than inline code execution for complex operations","# Resilient Spreadsheet Workflow\n\nThis skill provides a robust workflow for processing spreadsheet files (CSV, XLSX) when `execute_code_sandbox` encounters failures. It uses a combination of tools to ensure reliable execution and clear error diagnosis.\n\n## When to Use\n\n- Processing spreadsheet files when `execute_code_sandbox` returns unknown errors\n- Need to debug why spreadsheet operations fail\n- Require reliable file I\u002FO with verification at each step\n\n## Step-by-Step Workflow\n\n### Step 1: Initial Exploration with shell_agent\n\nStart by using `shell_agent` to explore the file structure and understand what files exist:\n\n```\nUse shell_agent to:\n- List files in the working directory\n- Identify spreadsheet files (CSV, XLSX)\n- Examine file sizes and basic structure\n```\n\n**Example task for shell_agent:**\n```\nExplore the current directory to find all spreadsheet files (CSV, XLSX). \nList their sizes and identify which files need processing.\n```\n\n### Step 2: Write Processing Script with write_file\n\nCreate a standalone script file rather than executing inline code:\n\n```python\n# Use write_file to create a script like \"process_sheet.py\"\ncontent = \"\"\"\nimport pandas as pd\nimport sys\n\ntry:\n    df = pd.read_csv('input.csv')  # or pd.read_excel for XLSX\n    # Perform your processing\n    result = df.describe()\n    result.to_csv('output.csv', index=False)\n    print(\"Processing complete\")\nexcept Exception as e:\n    print(f\"Error: {e}\", file=sys.stderr)\n    sys.exit(1)\n\"\"\"\n\nwrite_file(path=\"process_sheet.py\", content=content)\n```\n\n### Step 3: Execute with run_shell and Error Redirection\n\nExecute the script with stderr redirected to stdout for complete error capture:\n\n```bash\nrun_shell command=\"python process_sheet.py 2>&1\"\n```\n\nThe `2>&1` redirection ensures both stdout and stderr are captured together, making error messages visible.\n\n### Step 4: Isolate Errors with Verification Commands\n\nIf Step 3 fails, add targeted verification commands to diagnose the actual problem:\n\n```bash\n# Check if Python is available\nrun_shell command=\"which python 2>&1\"\n\n# Check if pandas is installed\nrun_shell command=\"python -c 'import pandas' 2>&1\"\n\n# Verify input file exists and is readable\nrun_shell command=\"ls -la input.csv 2>&1\"\n\n# Check file encoding\u002Fcontent\nrun_shell command=\"file input.csv 2>&1\"\nrun_shell command=\"head -5 input.csv 2>&1\"\n```\n\n### Step 5: Verify Output Before Reading\n\nBefore reading results with `read_file`, verify the output file exists:\n\n```\nlist_dir(path=\".\")\n# Confirm output file appears in the listing\n# Then proceed to read_file\n```\n\n## Complete Example\n\n```\n1. shell_agent(task=\"Find and describe all CSV\u002FXLSX files in current directory\")\n2. write_file(path=\"analyze_data.py\", content=\"\u003Cprocessing script>\")\n3. run_shell(command=\"python analyze_data.py 2>&1\")\n4. If error: run_shell(command=\"python -c 'import pandas; print(pandas.__version__)' 2>&1\")\n5. list_dir(path=\".\")  # Verify output exists\n6. read_file(filetype=\"csv\", file_path=\"output.csv\")\n```\n\n## Common Error Patterns\n\n| Symptom | Diagnostic Command | Likely Cause |\n|---------|-------------------|--------------|\n| Module not found | `python -c 'import pandas'` | Missing dependency |\n| File not found | `ls -la \u003Cfilename>` | Wrong path or name |\n| Permission denied | `ls -la \u003Cfilename>` | File permissions |\n| Encoding error | `file \u003Cfilename>` | Wrong file format |\n\n## Best Practices\n\n1. **Always use 2>&1** with run_shell for shell commands to capture full error output\n2. **Verify before reading** - use list_dir to confirm file existence before read_file\n3. **Break into small steps** - separate exploration, script writing, execution, and verification\n4. **Use shell_agent for unknowns** - when directory structure or file types are unclear\n5. **Write scripts to files** - more reliable than inline code execution for complex operations",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fresilient-spreadsheet-workflow",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":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add HKUDS\u002FAgentPilot --skill resilient-spreadsheet-workflow",{"tool":60,"command":61},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill resilient-spreadsheet-workflow",{"tool":63,"command":64},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill resilient-spreadsheet-workflow","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fresilient-spreadsheet-workflow\u002FSKILL.md",true,[68],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},".skill_id","OTHER","其他",44,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fresilient-spreadsheet-workflow\u002F.skill_id",[75,95,114,135,158,180],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":41},"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",[],[77,82,83,84,85,86,87,88,89,90,91,92,93,94],"prepare","requests","with","missing","installation","rsi","up","use","user","work","SET","run","experiments",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":41},"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",[],[97,102,103,104,105,106,107,108,109,110,111,112,113],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":121,"publishedAt":41},"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",[120],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[122,123,124,105,125,126,127,128,129,130,131,132,133,134],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search","Tools",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":142,"publishedAt":41},"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",[141],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[143,144,145,105,146,147,148,149,150,124,104,89,151,152,153,40,154,155,156,157],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","tool","stack","share","tasks","automation","MCP",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":41},"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",[],[165,166,167,168,169,170,171,172,33,173,174,175,176,177,40,178,179],"write special chars ts check","write","check","type","files","filters","only","template","python","typescript","output","Existing","type-checking","errors","script",{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":41},"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",[],[187,188,166,84,40,179,189,190,191,37,192,172,33,32,193,173],"write special chars readback","readback","helper","post","via","read","cleanup"]