[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HXJX29V5H7DARZBCAS9X2W":3,"skill-same:01M6HXJX29V5H7DARZBCAS9X2W":67},{"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":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":6,"updatedAt":46,"install":47,"resources":60},"01M6HXJX29V5H7DARZBCAS9X2W","fallback-file-creation",null,"Fallback pattern for reliable file creation when code execution tools 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-file-creation\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33],"file","fallback","creation","fallback file creation","code","Tools","execution","pattern","code execution","for","2026-11-10 10:12:30",false,"---\nname: fallback-file-creation\ndescription: Fallback pattern for reliable file creation when code execution tools fail\n---\n\n# Fallback File Creation Workflow\n\nUse this skill when `execute_code_sandbox` or `shell_agent` fails repeatedly for file creation tasks. This pattern provides a manual but reliable approach to create and verify files.\n\n## When to Use\n\n- Code execution tools fail after multiple retries\n- You need to create specific file formats (PDF, DOCX, etc.)\n- Direct shell commands are more reliable than generated scripts\n- You need explicit verification of file outputs\n\n## Step-by-Step Instructions\n\n### Step 1: Verify Working Directory\n\nBefore any file operations, confirm your current location:\n\n```bash\npwd\nls -la\n```\n\nThis ensures you're creating files in the correct workspace directory.\n\n### Step 2: Create Scripts via Heredoc\n\nUse shell heredocs to create scripts with properly escaped syntax:\n\n```bash\ncat > \u002Fpath\u002Fto\u002Fscript.sh \u003C\u003C 'EOF'\n#!\u002Fbin\u002Fbash\n# Your script content here\n# Variables are NOT expanded inside 'EOF' (quoted)\necho \"Creating file...\"\n# Commands to generate output\nEOF\n```\n\n**Key escaping rules:**\n- Use `'EOF'` (quoted) to prevent variable expansion inside the heredoc\n- Use `EOF` (unquoted) if you want shell variables to expand\n- Escape any `$`, backticks, or special characters if using unquoted EOF\n\n### Step 3: Execute with Explicit Path\n\nAlways run scripts with their full or explicit relative path:\n\n```bash\nchmod +x \u002Fpath\u002Fto\u002Fscript.sh\n\u002Fpath\u002Fto\u002Fscript.sh\n# or\nbash \u002Fpath\u002Fto\u002Fscript.sh\n```\n\nAvoid relying on `.` or implicit paths.\n\n### Step 4: Verify Output\n\nAfter execution, verify files were created correctly:\n\n```bash\n# Check file exists and size\nls -lh \u002Fpath\u002Fto\u002Foutput.file\n\n# For PDFs: inspect metadata\npdfinfo \u002Fpath\u002Fto\u002Foutput.pdf\n\n# For DOCX: check structure\nunzip -l \u002Fpath\u002Fto\u002Foutput.docx | head -20\n\n# For any file: check content preview\nfile \u002Fpath\u002Fto\u002Foutput.file\nhead -c 500 \u002Fpath\u002Fto\u002Foutput.file\n```\n\n### Step 5: Iterative Debugging\n\nIf verification fails:\n\n1. Check error messages from script execution\n2. Verify all dependencies are available (`which command`)\n3. Test individual commands from the script manually\n4. Re-run with verbose output (`bash -x script.sh`)\n\n## Example: Creating a PDF Document\n\n```bash\n# Step 1: Verify directory\npwd\nls -la\n\n# Step 2: Create conversion script\ncat > \u002Fworkspace\u002Fcreate_pdf.sh \u003C\u003C 'EOF'\n#!\u002Fbin\u002Fbash\ncd \u002Fworkspace\nlibreoffice --headless --convert-to pdf checklist.odt --outdir .\nEOF\n\n# Step 3: Execute\nchmod +x \u002Fworkspace\u002Fcreate_pdf.sh\n\u002Fworkspace\u002Fcreate_pdf.sh\n\n# Step 4: Verify\nls -lh \u002Fworkspace\u002Fchecklist.pdf\npdfinfo \u002Fworkspace\u002Fchecklist.pdf\n```\n\n## Example: Creating a DOCX Document\n\n```bash\n# Step 1: Verify directory\npwd\nls -la\n\n# Step 2: Create document script\ncat > \u002Fworkspace\u002Fcreate_docx.sh \u003C\u003C 'EOF'\n#!\u002Fbin\u002Fbash\ncd \u002Fworkspace\npandoc -f markdown -t docx action_tracker.md -o action_tracker.docx\nEOF\n\n# Step 3: Execute\nchmod +x \u002Fworkspace\u002Fcreate_docx.sh\n\u002Fworkspace\u002Fcreate_docx.sh\n\n# Step 4: Verify\nls -lh \u002Fworkspace\u002Faction_tracker.docx\nunzip -l \u002Fworkspace\u002Faction_tracker.docx | head -20\n```\n\n## Best Practices\n\n1. **Always verify before and after** - Check directory state before starting and after completion\n2. **Use absolute or explicit paths** - Avoid ambiguity in file locations\n3. **Quote heredoc delimiters** - Use `'EOF'` to prevent unwanted variable expansion\n4. **Make scripts executable** - Always `chmod +x` before running\n5. **Inspect file metadata** - Use format-specific tools (pdfinfo, unzip -l, file) to verify content\n6. **Keep scripts simple** - Each script should do one thing well\n7. **Clean up temporary files** - Remove intermediate files after successful completion\n\n## Troubleshooting\n\n| Issue | Solution |\n|-------|----------|\n| Script not found | Use full path: `\u002Fworkspace\u002Fscript.sh` |\n| Permission denied | Run `chmod +x script.sh` |\n| File not created | Check script output, verify working directory in script |\n| Wrong file format | Verify conversion tool supports target format |\n| Corrupted output | Re-run with verbose mode, check intermediate files |","# Fallback File Creation Workflow\n\nUse this skill when `execute_code_sandbox` or `shell_agent` fails repeatedly for file creation tasks. This pattern provides a manual but reliable approach to create and verify files.\n\n## When to Use\n\n- Code execution tools fail after multiple retries\n- You need to create specific file formats (PDF, DOCX, etc.)\n- Direct shell commands are more reliable than generated scripts\n- You need explicit verification of file outputs\n\n## Step-by-Step Instructions\n\n### Step 1: Verify Working Directory\n\nBefore any file operations, confirm your current location:\n\n```bash\npwd\nls -la\n```\n\nThis ensures you're creating files in the correct workspace directory.\n\n### Step 2: Create Scripts via Heredoc\n\nUse shell heredocs to create scripts with properly escaped syntax:\n\n```bash\ncat > \u002Fpath\u002Fto\u002Fscript.sh \u003C\u003C 'EOF'\n#!\u002Fbin\u002Fbash\n# Your script content here\n# Variables are NOT expanded inside 'EOF' (quoted)\necho \"Creating file...\"\n# Commands to generate output\nEOF\n```\n\n**Key escaping rules:**\n- Use `'EOF'` (quoted) to prevent variable expansion inside the heredoc\n- Use `EOF` (unquoted) if you want shell variables to expand\n- Escape any `$`, backticks, or special characters if using unquoted EOF\n\n### Step 3: Execute with Explicit Path\n\nAlways run scripts with their full or explicit relative path:\n\n```bash\nchmod +x \u002Fpath\u002Fto\u002Fscript.sh\n\u002Fpath\u002Fto\u002Fscript.sh\n# or\nbash \u002Fpath\u002Fto\u002Fscript.sh\n```\n\nAvoid relying on `.` or implicit paths.\n\n### Step 4: Verify Output\n\nAfter execution, verify files were created correctly:\n\n```bash\n# Check file exists and size\nls -lh \u002Fpath\u002Fto\u002Foutput.file\n\n# For PDFs: inspect metadata\npdfinfo \u002Fpath\u002Fto\u002Foutput.pdf\n\n# For DOCX: check structure\nunzip -l \u002Fpath\u002Fto\u002Foutput.docx | head -20\n\n# For any file: check content preview\nfile \u002Fpath\u002Fto\u002Foutput.file\nhead -c 500 \u002Fpath\u002Fto\u002Foutput.file\n```\n\n### Step 5: Iterative Debugging\n\nIf verification fails:\n\n1. Check error messages from script execution\n2. Verify all dependencies are available (`which command`)\n3. Test individual commands from the script manually\n4. Re-run with verbose output (`bash -x script.sh`)\n\n## Example: Creating a PDF Document\n\n```bash\n# Step 1: Verify directory\npwd\nls -la\n\n# Step 2: Create conversion script\ncat > \u002Fworkspace\u002Fcreate_pdf.sh \u003C\u003C 'EOF'\n#!\u002Fbin\u002Fbash\ncd \u002Fworkspace\nlibreoffice --headless --convert-to pdf checklist.odt --outdir .\nEOF\n\n# Step 3: Execute\nchmod +x \u002Fworkspace\u002Fcreate_pdf.sh\n\u002Fworkspace\u002Fcreate_pdf.sh\n\n# Step 4: Verify\nls -lh \u002Fworkspace\u002Fchecklist.pdf\npdfinfo \u002Fworkspace\u002Fchecklist.pdf\n```\n\n## Example: Creating a DOCX Document\n\n```bash\n# Step 1: Verify directory\npwd\nls -la\n\n# Step 2: Create document script\ncat > \u002Fworkspace\u002Fcreate_docx.sh \u003C\u003C 'EOF'\n#!\u002Fbin\u002Fbash\ncd \u002Fworkspace\npandoc -f markdown -t docx action_tracker.md -o action_tracker.docx\nEOF\n\n# Step 3: Execute\nchmod +x \u002Fworkspace\u002Fcreate_docx.sh\n\u002Fworkspace\u002Fcreate_docx.sh\n\n# Step 4: Verify\nls -lh \u002Fworkspace\u002Faction_tracker.docx\nunzip -l \u002Fworkspace\u002Faction_tracker.docx | head -20\n```\n\n## Best Practices\n\n1. **Always verify before and after** - Check directory state before starting and after completion\n2. **Use absolute or explicit paths** - Avoid ambiguity in file locations\n3. **Quote heredoc delimiters** - Use `'EOF'` to prevent unwanted variable expansion\n4. **Make scripts executable** - Always `chmod +x` before running\n5. **Inspect file metadata** - Use format-specific tools (pdfinfo, unzip -l, file) to verify content\n6. **Keep scripts simple** - Each script should do one thing well\n7. **Clean up temporary files** - Remove intermediate files after successful completion\n\n## Troubleshooting\n\n| Issue | Solution |\n|-------|----------|\n| Script not found | Use full path: `\u002Fworkspace\u002Fscript.sh` |\n| Permission denied | Run `chmod +x script.sh` |\n| File not created | Check script output, verify working directory in script |\n| Wrong file format | Verify conversion tool supports target format |\n| Corrupted output | Re-run with verbose mode, check intermediate files |",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Ffallback-file-creation",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":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add HKUDS\u002FAgentPilot --skill fallback-file-creation",{"tool":53,"command":54},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill fallback-file-creation",{"tool":56,"command":57},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill fallback-file-creation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Ffallback-file-creation\u002FSKILL.md",true,[61],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},".skill_id","OTHER","其他",36,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Ffallback-file-creation\u002F.skill_id",[68,88,107,129,152,174],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":34},"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",[],[70,75,76,77,78,79,80,81,82,83,84,85,86,87],"prepare","requests","with","missing","installation","rsi","up","use","user","work","SET","run","experiments",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":34},"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",[],[90,95,96,97,98,99,100,101,102,103,104,105,106],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":116,"publishedAt":34},"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",[113],{"categoryNo":114,"categoryName":115,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[117,118,119,98,120,121,122,123,124,125,126,127,128,29],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search",{"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":34},"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":114,"categoryName":115,"taxonomyType":21,"taxonomyTypeDesc":22},[137,138,139,98,140,141,142,143,144,119,97,82,145,146,147,33,148,149,150,151],"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":34},"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",[],[159,160,161,162,163,164,165,166,24,167,168,169,170,171,33,172,173],"write special chars ts check","write","check","type","files","filters","only","template","python","typescript","output","Existing","type-checking","errors","script",{"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":34},"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",[],[181,182,160,77,33,173,183,184,185,186,187,166,24,188,189,167],"write special chars readback","readback","helper","post","via","scripts","read","verification","cleanup"]