[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KFYN52WES2RE9WF5BK8F2S":3,"skill-same:01M6KFYN52WES2RE9WF5BK8F2S":69},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":14,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M6KFYN52WES2RE9WF5BK8F2S","research-fallback-robust",null,"Handle web research failures with explicit error recognition and domain-specific fallback strategies","xyliu-cs\u002FOpenSpace-GDPval","xyliu-cs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F89236536?v=4","01M6KF8Z1V4TXS86CKSH48BY8T","xy","01M6KF8Z67443W0SHXM85JEF0B",0,"MIT","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fresearch-fallback-enhanced\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35],"research","fallback","research fallback robust","research fallback","web","web research","domain","domain-specific","strategies","error","recognition","with","2026-11-10 10:12:30",false,"---\nname: research-fallback-robust\ndescription: Handle web research failures with explicit error recognition and domain-specific fallback strategies\n---\n\n# Research Fallback Workflow\n\nThis skill provides a workflow for handling tasks that require external research when web search or webpage reading tools fail due to network issues or tool unavailability.\n\n## When to Use\n\n- Task requires external research (legal analysis, market research, technical documentation, anatomical\u002Fmedical information, etc.)\n- Web search or webpage reading tools are failing or unavailable\n- You have sufficient internal knowledge to proceed with reasonable accuracy\n- Task completion is prioritized over perfect external sourcing\n\n## Workflow Steps\n\n### Step 1: Attempt External Research First\n\nBegin by attempting to use available web research tools:\n\n```\n1. Use search_web for current information, statistics, or recent developments\n2. Use read_webpage for detailed source material when URLs are provided\n3. Document what you attempted to find\n```\n\n### Step 2: Detect Tool Failure\n\nRecognize when to pivot — **including explicit error patterns**:\n\n- Web search returns errors, timeouts, or empty results\n- **`unknown error` from search_web** — immediately recognize this as a tool failure trigger (do not retry excessively)\n- Page extraction fails repeatedly\n- Network errors persist after 1-2 retry attempts\n- Tool explicitly reports unavailability\n\n**Do not** spend excessive time retrying failed tools. After 1-2 attempts with `unknown error` or similar failures, proceed to Step 3.\n\n### Step 3: Pivot to Internal Knowledge\n\nWhen external tools fail:\n\n1. **Acknowledge the limitation**: Note that external research was attempted but tools were unavailable\n2. **Assess internal knowledge**: Determine what you know from training that covers the topic\n3. **Identify gaps**: Be transparent about what information may be dated or unavailable\n4. **Proceed with available knowledge**: Generate content using internal understanding\n\n### Step 4: Generate Content with Appropriate Disclaimers\n\nWhen producing deliverables:\n\n```\n- Include a note that external verification is recommended for time-sensitive information\n- Flag any claims that would benefit from current source verification\n- Focus on established principles, frameworks, and well-documented facts\n- Avoid making specific claims about very recent events or statistics\n```\n\n### Step 5: Complete File Creation\n\nProceed with the original task deliverable:\n\n- Create the requested file format (PDF, DOCX, markdown, etc.)\n- Ensure content meets quality standards despite the research limitation\n- Stay within any specified constraints (page limits, word counts, etc.)\n\n## Example Decision Flow\n\n```\nTask requires research on [TOPIC]\n         |\n         v\nAttempt search_web \u002F read_webpage\n         |\n    +----+----+\n    |         |\n Success    Failure (after 1-2 attempts)\n    |         |\n    |         | **Note: `unknown error` = immediate pivot signal**\n    v         v\nUse sources  Pivot to internal knowledge\n    |         |\n    +----+----+\n         |\n         v\nGenerate content with appropriate disclaimers\n         |\n         v\nCreate deliverable file\n```\n\n## Best Practices\n\n1. **Recognize error patterns quickly**: `unknown error` from search_web is a clear signal to pivot, not a reason for extended retries\n2. **Be transparent**: Clearly note when external verification wasn't possible\n3. **Prioritize accuracy**: Only assert what you're confident about from training\n4. **Flag uncertainties**: Mark areas where current sources would be valuable\n5. **Don't block progress**: Tool failures shouldn't prevent task completion\n6. **Maintain quality**: Internal knowledge can still produce high-quality, useful content\n7. **Leverage stable knowledge domains**: Anatomical, medical, legal, and technical fundamentals from training are reliable even without external verification\n\n## Example Applications\n\n**Example 1: Legal Memo**\n\n**Task**: Create legal memo on privacy law violations\n\n**Workflow**:\n1. Attempt search_web for recent COPPA enforcement cases → `unknown error`\n2. Attempt read_webpage on provided URLs → Connection timeout\n3. Pivot: Use internal knowledge of COPPA requirements, California privacy laws, established case law principles\n4. Generate memo with note that recent case citations should be verified\n5. Create PDF deliverable within page limits\n\n**Outcome**: Comprehensive memo produced despite tool failures, with appropriate disclaimers about verification.\n\n**Example 2: Anatomical\u002FMedical Content**\n\n**Task**: Create proposal with anatomical utilization analysis and procedure capacity estimates\n\n**Workflow**:\n1. Attempt search_web for anatomical area statistics → `unknown error`\n2. Attempt execute_code_sandbox for analysis → `unknown error`\n3. Pivot: Use internal training knowledge of:\n   - Anatomical structures and terminology\n   - Standard medical procedures and their requirements\n   - Established frameworks for capacity estimation\n   - Common cost structures in medical\u002Fcadaver programs\n4. Generate content using reliable internal knowledge (anatomical facts are well-established)\n5. Create DOCX deliverable with appropriate verification notes for any statistics\n\n**Outcome**: High-quality proposal with anatomical tables, procedure estimates, and cost analysis created using internal knowledge, with transparent disclaimers about statistical verification.\n\n## When NOT to Use This Skill\n\n- Task explicitly requires current, verified external sources (e.g., real-time stock prices, breaking news)\n- Legal\u002Fmedical advice where current regulations are critical and disclaimer is insufficient\n- Client specifically requires cited external sources for the deliverable\n\nIn these cases, report the tool failure and request guidance rather than proceeding with internal knowledge alone.\n","# Research Fallback Workflow\n\nThis skill provides a workflow for handling tasks that require external research when web search or webpage reading tools fail due to network issues or tool unavailability.\n\n## When to Use\n\n- Task requires external research (legal analysis, market research, technical documentation, anatomical\u002Fmedical information, etc.)\n- Web search or webpage reading tools are failing or unavailable\n- You have sufficient internal knowledge to proceed with reasonable accuracy\n- Task completion is prioritized over perfect external sourcing\n\n## Workflow Steps\n\n### Step 1: Attempt External Research First\n\nBegin by attempting to use available web research tools:\n\n```\n1. Use search_web for current information, statistics, or recent developments\n2. Use read_webpage for detailed source material when URLs are provided\n3. Document what you attempted to find\n```\n\n### Step 2: Detect Tool Failure\n\nRecognize when to pivot — **including explicit error patterns**:\n\n- Web search returns errors, timeouts, or empty results\n- **`unknown error` from search_web** — immediately recognize this as a tool failure trigger (do not retry excessively)\n- Page extraction fails repeatedly\n- Network errors persist after 1-2 retry attempts\n- Tool explicitly reports unavailability\n\n**Do not** spend excessive time retrying failed tools. After 1-2 attempts with `unknown error` or similar failures, proceed to Step 3.\n\n### Step 3: Pivot to Internal Knowledge\n\nWhen external tools fail:\n\n1. **Acknowledge the limitation**: Note that external research was attempted but tools were unavailable\n2. **Assess internal knowledge**: Determine what you know from training that covers the topic\n3. **Identify gaps**: Be transparent about what information may be dated or unavailable\n4. **Proceed with available knowledge**: Generate content using internal understanding\n\n### Step 4: Generate Content with Appropriate Disclaimers\n\nWhen producing deliverables:\n\n```\n- Include a note that external verification is recommended for time-sensitive information\n- Flag any claims that would benefit from current source verification\n- Focus on established principles, frameworks, and well-documented facts\n- Avoid making specific claims about very recent events or statistics\n```\n\n### Step 5: Complete File Creation\n\nProceed with the original task deliverable:\n\n- Create the requested file format (PDF, DOCX, markdown, etc.)\n- Ensure content meets quality standards despite the research limitation\n- Stay within any specified constraints (page limits, word counts, etc.)\n\n## Example Decision Flow\n\n```\nTask requires research on [TOPIC]\n         |\n         v\nAttempt search_web \u002F read_webpage\n         |\n    +----+----+\n    |         |\n Success    Failure (after 1-2 attempts)\n    |         |\n    |         | **Note: `unknown error` = immediate pivot signal**\n    v         v\nUse sources  Pivot to internal knowledge\n    |         |\n    +----+----+\n         |\n         v\nGenerate content with appropriate disclaimers\n         |\n         v\nCreate deliverable file\n```\n\n## Best Practices\n\n1. **Recognize error patterns quickly**: `unknown error` from search_web is a clear signal to pivot, not a reason for extended retries\n2. **Be transparent**: Clearly note when external verification wasn't possible\n3. **Prioritize accuracy**: Only assert what you're confident about from training\n4. **Flag uncertainties**: Mark areas where current sources would be valuable\n5. **Don't block progress**: Tool failures shouldn't prevent task completion\n6. **Maintain quality**: Internal knowledge can still produce high-quality, useful content\n7. **Leverage stable knowledge domains**: Anatomical, medical, legal, and technical fundamentals from training are reliable even without external verification\n\n## Example Applications\n\n**Example 1: Legal Memo**\n\n**Task**: Create legal memo on privacy law violations\n\n**Workflow**:\n1. Attempt search_web for recent COPPA enforcement cases → `unknown error`\n2. Attempt read_webpage on provided URLs → Connection timeout\n3. Pivot: Use internal knowledge of COPPA requirements, California privacy laws, established case law principles\n4. Generate memo with note that recent case citations should be verified\n5. Create PDF deliverable within page limits\n\n**Outcome**: Comprehensive memo produced despite tool failures, with appropriate disclaimers about verification.\n\n**Example 2: Anatomical\u002FMedical Content**\n\n**Task**: Create proposal with anatomical utilization analysis and procedure capacity estimates\n\n**Workflow**:\n1. Attempt search_web for anatomical area statistics → `unknown error`\n2. Attempt execute_code_sandbox for analysis → `unknown error`\n3. Pivot: Use internal training knowledge of:\n   - Anatomical structures and terminology\n   - Standard medical procedures and their requirements\n   - Established frameworks for capacity estimation\n   - Common cost structures in medical\u002Fcadaver programs\n4. Generate content using reliable internal knowledge (anatomical facts are well-established)\n5. Create DOCX deliverable with appropriate verification notes for any statistics\n\n**Outcome**: High-quality proposal with anatomical tables, procedure estimates, and cost analysis created using internal knowledge, with transparent disclaimers about statistical verification.\n\n## When NOT to Use This Skill\n\n- Task explicitly requires current, verified external sources (e.g., real-time stock prices, breaking news)\n- Legal\u002Fmedical advice where current regulations are critical and disclaimer is insufficient\n- Client specifically requires cited external sources for the deliverable\n\nIn these cases, report the tool failure and request guidance rather than proceeding with internal knowledge alone.\n",{"name":5,"description":7},"main","af1b40a42167d09c30b3a63000aa14ace4c1e229","gdpval_bench\u002Fskills\u002Fresearch-fallback-enhanced","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval","https:\u002F\u002Fgithub.com\u002Fxyliu-cs","https:\u002F\u002Fxyliu-cs.github.io","PhD Student in CS, CUHK-Shenzhen.","2026-04-06 20:32:15",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add xyliu-cs\u002FOpenSpace-GDPval --skill research-fallback-robust",{"tool":55,"command":56},"bunx","bunx skills add xyliu-cs\u002FOpenSpace-GDPval --skill research-fallback-robust",{"tool":58,"command":59},"pnpm","pnpm dlx skills add xyliu-cs\u002FOpenSpace-GDPval --skill research-fallback-robust","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fresearch-fallback-enhanced\u002FSKILL.md",true,[63],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},".skill_id","OTHER","其他",40,"https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fresearch-fallback-enhanced\u002F.skill_id",[70,83,91,106,130,150],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":36},"01M6KG8MF1S664SWBDENYRSCK8","zip-export-deliverable","Ensures codebase deliverables are properly exported as ZIP archives through a dedicated finalization step","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fzip-export-deliverable\u002FSKILL.md",[],[77,78,79,80,81,82],"zip export deliverable","zip","export","deliverables","codebase","as",{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":36},"01M6KG8GAZWHHEK7VNJDW0ME21","zip-deliverable-finalization","Ensure codebase deliverables are properly packaged as ZIP exports in a dedicated final step","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fzip-deliverable-finalization\u002FSKILL.md",[],[90,78,80,81,82],"zip deliverable finalization",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":36},"01M6KG8CMQQ1PYMNTSRZ9VS1MD","zero-iteration-failure-analysis","Identify and handle agent failures with 0 iterations as pre-execution system issues","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fzero-iteration-failure-analysis\u002FSKILL.md",[],[98,99,100,101,102,35,103,104,82,105],"failure analysis","ZeRO","analysis","iteration","zero iteration failure analysis","issues","execution","system",{"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":117,"publishedAt":36},"01M6KG86W3PA07FT9W58YHHERM","write-file-fallback-report","Generate professional documents using write_file when primary data sources fail, leveraging embedded domain knowledge instead of external retrieval","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fwrite-file-fallback-report\u002FSKILL.md",[112],{"categoryNo":113,"categoryName":114,"taxonomyType":115,"taxonomyTypeDesc":116},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[25,118,119,120,121,30,122,123,124,125,126,127,128,129],"write","file","report","write file fallback report","professional","sources","retrieval","generate","embedded","documents","data","knowledge",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":139,"publishedAt":36},"01M6KG82GAEY3GG77CMGCK1C2T","fallback-doc-with-delegation","Generate professional documents after tool failures using shell_agent for complex formats or write_file for simple text\u002Fmarkdown","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fwrite-file-fallback-report-enhanced\u002FSKILL.md",[136],{"categoryNo":137,"categoryName":138,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[140,35,25,141,142,143,127,125,119,144,145,146,118,147,122,148,149],"fallback doc with delegation","doc","delegation","shell","markdown","tool","text","simple","formats","for",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":157,"publishedAt":36},"01M6KG7WT7GX5NYCGEFHW22NV7","context-anchored-fallback-report","Generate documents with write_file when retrieval tools fail, with explicit guardrails against task context drift","https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fwrite-file-fallback-report-enhanced-4bc5c2\u002FSKILL.md",[156],{"categoryNo":113,"categoryName":114,"taxonomyType":115,"taxonomyTypeDesc":116},[25,120,158,159,125,119,160,161,118,162,163,124,35,164,127],"context","context anchored fallback report","Guardrails","Tools","task","drift","context drift"]