[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HWVQBQ0W6F69KVCFW6QFYC":3,"skill-same:01M6HWVQBQ0W6F69KVCFW6QFYC":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":23,"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},"01M6HWVQBQ0W6F69KVCFW6QFYC","regulatory-fallback-research",null,"Handle tool failures when researching regulatory\u002Fgovernment content by using fallback methods and domain knowledge","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\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fregulatory-fallback-research\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32],"research","regulatory","fallback","regulatory fallback research","content","knowledge","tool","methods","domain","2026-11-10 10:12:30",false,"---\nname: regulatory-fallback-research\ndescription: Handle tool failures when researching regulatory\u002Fgovernment content by using fallback methods and domain knowledge\n---\n\n# Regulatory\u002FGovernment Content Research with Fallback Strategy\n\n## Overview\n\nWhen researching regulatory, government, or compliance-related content, primary sources (official websites, PDFs, regulatory databases) often become inaccessible due to tool failures, access restrictions, or technical issues. This skill provides a resilient workflow to complete research tasks despite these obstacles.\n\n## When to Use This Skill\n\nUse this workflow when:\n- You need to research regulatory\u002Fgovernment content (FDA, CMS, DEA, state boards, etc.)\n- Primary source tools (read_webpage, search_web) return 'unknown error' or fail repeatedly\n- You need to produce compliance documentation, checklists, or regulatory summaries\n\n## Step-by-Step Procedure\n\n### Step 1: Attempt Primary Source Access\n\nFirst, try to access official sources directly:\n\n```\n1. Use read_webpage on known regulatory URLs\n2. Use search_web for specific regulatory queries\n3. Attempt read_file on any available PDFs or documents\n```\n\n**Expected outcomes:**\n- Success: Proceed with content extraction\n- 'unknown error' or repeated failures: Document the failure and proceed to Step 2\n\n### Step 2: Deploy Shell Agent for Secondary Research\n\nWhen primary tools fail, use shell_agent for alternative information gathering:\n\n```\nshell_agent task: \"Research [topic] compliance requirements using alternative sources. \nSearch for summaries, guides, or cached versions of regulatory information. \nFocus on established compliance frameworks and best practices.\"\n```\n\n**Strategies for shell_agent:**\n- Request research from multiple angles (state vs federal, industry guides, etc.)\n- Ask for aggregated information from secondary sources\n- Request compliance checklist templates from industry resources\n\n### Step 3: Apply Domain Knowledge\n\nWhen both primary and secondary research tools fail:\n\n```\n1. Acknowledge the tool limitations explicitly\n2. State you will proceed using established domain knowledge\n3. Create content based on well-known regulatory frameworks\n```\n\n**Key domains to leverage:**\n- **Pharmacy compliance**: HIPAA, OBRA-90, controlled substance handling, prescription verification, drug storage, patient counseling\n- **Healthcare compliance**: OSHA, HIPAA privacy\u002Fsecurity, Medicare\u002FMedicaid billing, infection control\n- **General regulatory**: Documentation requirements, audit trails, staff training, record retention\n\n### Step 4: Produce Deliverables Despite Limitations\n\nContinue to completion:\n\n```\n1. Create required outputs (checklists, summaries, documentation)\n2. Note any limitations due to inaccessible sources\n3. Recommend verification against current official sources\n4. Structure content for easy updating when sources become available\n```\n\n## Code Examples\n\n### Example: Handling Multiple Tool Failures\n\n```\n# Document failures transparently\n\"Note: Primary regulatory sources (FDA.gov, state board websites) \nreturned access errors. Content compiled from established \ncompliance frameworks and industry standards.\"\n\n# Proceed with domain knowledge\ncreate_pharmacy_checklist(\n    categories=[\"prescription_handling\", \"controlled_substances\", \n                \"patient_counseling\", \"record_keeping\"],\n    basis=\"OBRA-90 and standard pharmacy practice guidelines\"\n)\n\n# Add verification disclaimer\n\"Recommendation: Verify all requirements against current state \nboard regulations before implementation.\"\n```\n\n### Example: Shell Agent Fallback Query\n\n```\nshell_agent task: \"Gather pharmacy compliance requirements from \nsecondary sources including:\n1. Industry association guidelines (NCPDP, ASHP)\n2. Academic pharmacy practice resources\n3. State board examination study materials\n4. Compliance training program outlines\n\nCompile into structured checklist format.\"\n```\n\n## Best Practices\n\n1. **Never abandon the task** - Tool failures are common with government sites; persist using available methods\n\n2. **Be transparent** - Always document which sources were inaccessible and what basis you used instead\n\n3. **Structure for updates** - Create modular content that can be easily revised when sources become available\n\n4. **Prioritize safety-critical items** - When uncertain, include conservative compliance measures\n\n5. **Recommend verification** - Always advise end-users to verify against current official sources\n\n## Common Failure Scenarios\n\n| Failure | Fallback Action |\n|---------|-----------------|\n| read_webpage 'unknown error' | Try search_web, then shell_agent |\n| search_web 'unknown error' | Try shell_agent research task |\n| shell_agent timeout\u002Ffailure | Proceed with domain knowledge |\n| All tools fail | Use established domain knowledge, document limitations |\n\n## Quality Criteria\n\nYour output is successful when:\n- [ ] All required deliverables are produced\n- [ ] Tool failures are documented transparently\n- [ ] Content is based on verifiable regulatory frameworks\n- [ ] Verification recommendations are included\n- [ ] Content structure allows easy updates\n\n---\nname: regulatory-fallback-research\ndescription: Handle tool failures when researching regulatory\u002Fgovernment content by using fallback methods and domain knowledge\n---","# Regulatory\u002FGovernment Content Research with Fallback Strategy\n\n## Overview\n\nWhen researching regulatory, government, or compliance-related content, primary sources (official websites, PDFs, regulatory databases) often become inaccessible due to tool failures, access restrictions, or technical issues. This skill provides a resilient workflow to complete research tasks despite these obstacles.\n\n## When to Use This Skill\n\nUse this workflow when:\n- You need to research regulatory\u002Fgovernment content (FDA, CMS, DEA, state boards, etc.)\n- Primary source tools (read_webpage, search_web) return 'unknown error' or fail repeatedly\n- You need to produce compliance documentation, checklists, or regulatory summaries\n\n## Step-by-Step Procedure\n\n### Step 1: Attempt Primary Source Access\n\nFirst, try to access official sources directly:\n\n```\n1. Use read_webpage on known regulatory URLs\n2. Use search_web for specific regulatory queries\n3. Attempt read_file on any available PDFs or documents\n```\n\n**Expected outcomes:**\n- Success: Proceed with content extraction\n- 'unknown error' or repeated failures: Document the failure and proceed to Step 2\n\n### Step 2: Deploy Shell Agent for Secondary Research\n\nWhen primary tools fail, use shell_agent for alternative information gathering:\n\n```\nshell_agent task: \"Research [topic] compliance requirements using alternative sources. \nSearch for summaries, guides, or cached versions of regulatory information. \nFocus on established compliance frameworks and best practices.\"\n```\n\n**Strategies for shell_agent:**\n- Request research from multiple angles (state vs federal, industry guides, etc.)\n- Ask for aggregated information from secondary sources\n- Request compliance checklist templates from industry resources\n\n### Step 3: Apply Domain Knowledge\n\nWhen both primary and secondary research tools fail:\n\n```\n1. Acknowledge the tool limitations explicitly\n2. State you will proceed using established domain knowledge\n3. Create content based on well-known regulatory frameworks\n```\n\n**Key domains to leverage:**\n- **Pharmacy compliance**: HIPAA, OBRA-90, controlled substance handling, prescription verification, drug storage, patient counseling\n- **Healthcare compliance**: OSHA, HIPAA privacy\u002Fsecurity, Medicare\u002FMedicaid billing, infection control\n- **General regulatory**: Documentation requirements, audit trails, staff training, record retention\n\n### Step 4: Produce Deliverables Despite Limitations\n\nContinue to completion:\n\n```\n1. Create required outputs (checklists, summaries, documentation)\n2. Note any limitations due to inaccessible sources\n3. Recommend verification against current official sources\n4. Structure content for easy updating when sources become available\n```\n\n## Code Examples\n\n### Example: Handling Multiple Tool Failures\n\n```\n# Document failures transparently\n\"Note: Primary regulatory sources (FDA.gov, state board websites) \nreturned access errors. Content compiled from established \ncompliance frameworks and industry standards.\"\n\n# Proceed with domain knowledge\ncreate_pharmacy_checklist(\n    categories=[\"prescription_handling\", \"controlled_substances\", \n                \"patient_counseling\", \"record_keeping\"],\n    basis=\"OBRA-90 and standard pharmacy practice guidelines\"\n)\n\n# Add verification disclaimer\n\"Recommendation: Verify all requirements against current state \nboard regulations before implementation.\"\n```\n\n### Example: Shell Agent Fallback Query\n\n```\nshell_agent task: \"Gather pharmacy compliance requirements from \nsecondary sources including:\n1. Industry association guidelines (NCPDP, ASHP)\n2. Academic pharmacy practice resources\n3. State board examination study materials\n4. Compliance training program outlines\n\nCompile into structured checklist format.\"\n```\n\n## Best Practices\n\n1. **Never abandon the task** - Tool failures are common with government sites; persist using available methods\n\n2. **Be transparent** - Always document which sources were inaccessible and what basis you used instead\n\n3. **Structure for updates** - Create modular content that can be easily revised when sources become available\n\n4. **Prioritize safety-critical items** - When uncertain, include conservative compliance measures\n\n5. **Recommend verification** - Always advise end-users to verify against current official sources\n\n## Common Failure Scenarios\n\n| Failure | Fallback Action |\n|---------|-----------------|\n| read_webpage 'unknown error' | Try search_web, then shell_agent |\n| search_web 'unknown error' | Try shell_agent research task |\n| shell_agent timeout\u002Ffailure | Proceed with domain knowledge |\n| All tools fail | Use established domain knowledge, document limitations |\n\n## Quality Criteria\n\nYour output is successful when:\n- [ ] All required deliverables are produced\n- [ ] Tool failures are documented transparently\n- [ ] Content is based on verifiable regulatory frameworks\n- [ ] Verification recommendations are included\n- [ ] Content structure allows easy updates\n\n---\nname: regulatory-fallback-research\ndescription: Handle tool failures when researching regulatory\u002Fgovernment content by using fallback methods and domain knowledge\n---",{"name":5,"description":7},"main","6b84b0689ca0d9e7b1e4061188ff6b60758e0f8a","openspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fregulatory-fallback-research",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 regulatory-fallback-research",{"tool":52,"command":53},"bunx","bunx skills add HKUDS\u002FAgentPilot --skill regulatory-fallback-research",{"tool":55,"command":56},"pnpm","pnpm dlx skills add HKUDS\u002FAgentPilot --skill regulatory-fallback-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fregulatory-fallback-research\u002FSKILL.md",true,[60],{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},".skill_id","OTHER","其他",42,"https:\u002F\u002Fgithub.com\u002FHKUDS\u002FAgentPilot\u002Fblob\u002Fmain\u002Fopenspace\u002Fbenchmarks\u002Fgdpval\u002Fskills\u002Fregulatory-fallback-research\u002F.skill_id",[67,87,106,129,152,175],{"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",[],[69,74,75,76,77,78,79,80,81,82,83,84,85,86],"prepare","requests","with","missing","installation","rsi","up","use","user","work","SET","run","experiments",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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",[],[89,94,95,96,97,98,99,100,101,102,103,104,105],"memory","review","auto","openspace","changes","facts","detect","entries","local","conflicts","stale","duplicates",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":115,"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",[112],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[116,117,118,97,119,120,121,122,123,124,125,126,127,128],"skill discovery","discovery","reusable","step by step","tokens","packages","help","cloud","reliability","capabilities","browse","search","Tools",{"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":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",[135],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},[137,138,139,97,140,141,142,143,144,118,96,81,145,30,146,147,148,149,150,151],"delegate","task","delegate task","time","improve","desktop automation","worker","community","autonomous","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",[],[159,160,161,162,163,164,165,166,167,168,169,170,171,172,147,173,174],"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":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",[],[182,183,160,76,147,174,184,185,186,187,188,166,167,189,190,168],"write special chars readback","readback","helper","post","via","scripts","read","verification","cleanup"]