[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HXYTJSS1PHPX49ZA5YEPEB":3,"skill-same:01M6HXYTJSS1PHPX49ZA5YEPEB":71},{"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":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":49,"ownerDescription":6,"updatedAt":50,"install":51,"resources":64},"01M6HXYTJSS1PHPX49ZA5YEPEB","shell-agent-delegation",null,"Delegate complex tasks to shell_agent when direct tool execution fails, leveraging autonomous error recovery and library selection","HKUDS\u002FAgentPilot","HKUDS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F118165258?v=4","01M6HW8VRNZP64G0P4MVJW2KKQ","✨Data Intelligence Lab@HKU✨","01M6HW8VWZVHBRHYH3T330PFWV",8024,"MIT","https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fshell-agent-delegation\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37],"delegation","shell","shell agent delegation","error recovery","tasks","library","execution","recovery","tool","direct","delegate","autonomous","selection","error","2026-11-10 10:12:30",false,"---\nname: shell-agent-delegation\ndescription: Delegate complex tasks to shell_agent when direct tool execution fails, leveraging autonomous error recovery and library selection\n---\n\n# Shell Agent Delegation for Resilient Workflow Execution\n\n## When to Use This Skill\n\nApply this pattern when:\n- Direct tool execution (execute_code_sandbox, read_webpage, search_web) fails with 'unknown error'\n- Multiple tool attempts have failed in sequence\n- The task requires complex document generation or data processing\n- You need a tool that can autonomously select libraries and handle multi-step workflows\n\n## Why This Works\n\nThe `shell_agent` tool differs from direct execution tools in key ways:\n- **Autonomous tool selection**: Decides whether to use Python or Bash based on the task\n- **Built-in error recovery**: Automatically retries and fixes errors (up to several rounds)\n- **Iterative execution**: Writes code, executes, inspects output, and adapts\n- **Full workflow ownership**: Handles the entire task end-to-end without manual intervention\n\n## Step-by-Step Instructions\n\n### Step 1: Recognize the Failure Pattern\n\nIdentify when to pivot to shell_agent:\n```\n- execute_code_sandbox returned 'unknown error'\n- read_webpage\u002Fsearch_web failed multiple times\n- Direct approaches are struggling with the task complexity\n```\n\n### Step 2: Formulate the Delegation Task\n\nCreate a clear, self-contained task description for shell_agent:\n\n**Good task description:**\n```\nCreate a 1-page SBAR Template PDF document. Include sections for:\n- Situation: Brief description of the current situation\n- Background: Relevant context and history\n- Assessment: Current assessment and analysis\n- Recommendation: Proposed actions and next steps\nUse a professional layout with clear headings and adequate whitespace.\n```\n\n**Key elements to include:**\n- The end goal (what should be produced)\n- Required sections\u002Fcomponents\n- Format requirements (PDF, DOCX, etc.)\n- Any style or layout preferences\n\n### Step 3: Execute the Delegation\n\nCall shell_agent with your task description:\n\n```python\n# Conceptual example\nshell_agent(task=\"Create a professional SBAR Template PDF with Situation, Background, Assessment, and Recommendation sections. Include clear headings and professional formatting.\")\n```\n\n### Step 4: Monitor and Verify\n\nAfter shell_agent completes:\n1. Check that the output file was created in the working directory\n2. Verify the content meets requirements\n3. If issues remain, provide refined instructions to shell_agent\n\n## Code Example\n\n```python\n# When direct approaches fail:\n# execute_code_sandbox(code=\"...\")  # Returns 'unknown error'\n# search_web(query=\"...\")  # Returns 'unknown error'\n\n# Pivot to shell_agent:\nshell_agent(\n    task=\"Generate a professional one-page template document in PDF format. \"\n         \"Include clearly labeled sections with appropriate spacing and formatting. \"\n         \"Select the most appropriate Python library for PDF generation.\",\n    timeout=300  # Allow time for iteration and error recovery\n)\n```\n\n## Best Practices\n\n1. **Be specific about the output**: Clearly describe what the final product should look like\n2. **Trust the autonomy**: Let shell_agent decide on libraries and implementation details\n3. **Allow sufficient timeout**: Set timeout to 300+ seconds for complex tasks requiring iteration\n4. **One task at a time**: Give shell_agent a complete, self-contained objective\n5. **Don't micromanage**: Avoid prescribing specific libraries or code unless necessary\n\n## Common Use Cases\n\n- Document generation (PDF, DOCX, reports, templates)\n- Data processing pipelines with multiple steps\n- Web scraping with fallback handling\n- Complex file manipulation tasks\n- Tasks requiring library discovery and selection\n\n## Anti-Patterns to Avoid\n\n❌ Don't use shell_agent for simple, single-command tasks (use run_shell instead)\n❌ Don't provide overly prescriptive code instructions (defeats the autonomous benefit)\n❌ Don't set timeout too low (\u003C60 seconds for complex tasks)\n❌ Don't split a coherent task into multiple shell_agent calls unnecessarily","# Shell Agent Delegation for Resilient Workflow Execution\n\n## When to Use This Skill\n\nApply this pattern when:\n- Direct tool execution (execute_code_sandbox, read_webpage, search_web) fails with 'unknown error'\n- Multiple tool attempts have failed in sequence\n- The task requires complex document generation or data processing\n- You need a tool that can autonomously select libraries and handle multi-step workflows\n\n## Why This Works\n\nThe `shell_agent` tool differs from direct execution tools in key ways:\n- **Autonomous tool selection**: Decides whether to use Python or Bash based on the task\n- **Built-in error recovery**: Automatically retries and fixes errors (up to several rounds)\n- **Iterative execution**: Writes code, executes, inspects output, and adapts\n- **Full workflow ownership**: Handles the entire task end-to-end without manual intervention\n\n## Step-by-Step Instructions\n\n### Step 1: Recognize the Failure Pattern\n\nIdentify when to pivot to shell_agent:\n```\n- execute_code_sandbox returned 'unknown error'\n- read_webpage\u002Fsearch_web failed multiple times\n- Direct approaches are struggling with the task complexity\n```\n\n### Step 2: Formulate the Delegation Task\n\nCreate a clear, self-contained task description for shell_agent:\n\n**Good task description:**\n```\nCreate a 1-page SBAR Template PDF document. Include sections for:\n- Situation: Brief description of the current situation\n- Background: Relevant context and history\n- Assessment: Current assessment and analysis\n- Recommendation: Proposed actions and next steps\nUse a professional layout with clear headings and adequate whitespace.\n```\n\n**Key elements to include:**\n- The end goal (what should be produced)\n- Required sections\u002Fcomponents\n- Format requirements (PDF, DOCX, etc.)\n- Any style or layout preferences\n\n### Step 3: Execute the Delegation\n\nCall shell_agent with your task description:\n\n```python\n# Conceptual example\nshell_agent(task=\"Create a professional SBAR Template PDF with Situation, Background, Assessment, and Recommendation sections. Include clear headings and professional formatting.\")\n```\n\n### Step 4: Monitor and Verify\n\nAfter shell_agent completes:\n1. Check that the output file was created in the working directory\n2. Verify the content meets requirements\n3. If issues remain, provide refined instructions to shell_agent\n\n## Code Example\n\n```python\n# When direct approaches fail:\n# execute_code_sandbox(code=\"...\")  # Returns 'unknown error'\n# search_web(query=\"...\")  # Returns 'unknown error'\n\n# Pivot to shell_agent:\nshell_agent(\n    task=\"Generate a professional one-page template document in PDF format. \"\n         \"Include clearly labeled sections with appropriate spacing and formatting. \"\n         \"Select the most appropriate Python library for PDF generation.\",\n    timeout=300  # Allow time for iteration and error recovery\n)\n```\n\n## Best Practices\n\n1. **Be specific about the output**: Clearly describe what the final product should look like\n2. **Trust the autonomy**: Let shell_agent decide on libraries and implementation details\n3. **Allow sufficient timeout**: Set timeout to 300+ seconds for complex tasks requiring iteration\n4. **One task at a time**: Give shell_agent a complete, self-contained objective\n5. **Don't micromanage**: Avoid prescribing specific libraries or code unless necessary\n\n## Common Use Cases\n\n- Document generation (PDF, DOCX, reports, templates)\n- Data processing pipelines with multiple steps\n- Web scraping with fallback handling\n- Complex file manipulation tasks\n- Tasks requiring library discovery and selection\n\n## Anti-Patterns to Avoid\n\n❌ Don't use shell_agent for simple, single-command tasks (use run_shell instead)\n❌ Don't provide overly prescriptive code instructions (defeats the autonomous benefit)\n❌ Don't set timeout too low (\u003C60 seconds for complex tasks)\n❌ Don't split a coherent task into multiple shell_agent calls unnecessarily",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fshell-agent-delegation",941,"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":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add HKUDS\u002FAgentPilot --skill shell-agent-delegation",{"tool":57,"command":58},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill shell-agent-delegation",{"tool":60,"command":61},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill shell-agent-delegation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fshell-agent-delegation\u002FSKILL.md",true,[65],{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},".skill_id","OTHER","其他",36,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Flegacy\u002Fv1\u002Fgdpval_bench\u002Fskills\u002Fshell-agent-delegation\u002F.skill_id",[72,92,111,132,152,175],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":38},"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",[],[74,79,80,81,82,83,84,85,86,87,88,89,90,91],"prepare","requests","with","missing","installation","rsi","up","use","user","work","SET","run","experiments",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":38},"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",[],[94,99,100,101,102,103,104,105,106,107,108,109,110],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":118,"publishedAt":38},"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",[117],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[119,120,121,102,122,123,124,125,126,127,128,129,130,131],"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":38},"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":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[34,140,141,102,142,143,144,145,146,121,101,86,35,32,147,148,149,28,150,151],"task","delegate task","time","improve","desktop automation","worker","community","stack","for","share","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":38},"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",[],[159,160,161,162,163,164,165,166,167,168,169,170,171,172,148,173,174],"write special chars ts check","write","check","type","files","filters","only","template","file","python","typescript","output","Existing","type-checking","errors","script",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":181,"publishedAt":38},"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",[],[182,183,160,81,148,174,184,185,186,187,188,166,167,189,190,168],"write special chars readback","readback","helper","post","via","scripts","read","verification","cleanup"]