[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6KFVGJVP65ST21JTMPABRKF":3,"skill-same:01M6KFVGJVP65ST21JTMPABRKF":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":14,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":44,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M6KFVGJVP65ST21JTMPABRKF","prioritize-context-data",null,"Ensures agents check and use provided context files for data before attempting external searches.","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\u002Fprioritize-context-data\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33],"data","prioritize","context","prioritize context data","workflow","check","use","files","context files","for","2026-11-10 10:12:30",false,"---\nname: prioritize-context-data\ndescription: Ensures agents check and use provided context files for data before attempting external searches.\ncategory: workflow\n---\n\n# Prioritize Context Data\n\n## Objective\nPrevent data hallucination and inefficiency by mandating that agents inspect and utilize provided reference files (CSV, XLSX, PDF, TXT, etc.) before attempting web searches or generating synthetic data.\n\n## Critical Rule\n**If a reference file is provided in the task context, it is the source of truth.** Do not fabricate data or search the web for information that exists within the provided attachments.\n\n## Workflow Steps\n\n### 1. Scan Context for Attachments\nAt the start of every task, explicitly list all files provided in the context window or attachment panel.\n- Check for spreadsheets (`.xlsx`, `.csv`), documents (`.pdf`, `.docx`), or data dumps (`.json`, `.txt`).\n- Note the filename and inferred content type.\n\n### 2. Evaluate Relevance\nDetermine if any provided file contains the data required to complete the task.\n- **Match Keywords:** Do filenames or column headers match task requirements?\n- **Check Scope:** Does the data cover the necessary timeframe or地域 (region)?\n\n### 3. Extract Data First\nIf relevant files are found:\n- Read the file content using appropriate tools (e.g., `read_file`, `pandas`, `pdf_reader`).\n- Extract the specific data points needed.\n- **Do not** proceed to web search until you have confirmed the file lacks the necessary information.\n\n### 4. Cite Source Explicitly\nWhen presenting data in the final output:\n- Explicitly state which file the data came from.\n- Example: \"According to `Massabama_active_listings.xlsx`...\"\n- This verifies to the user that real data was used, not hallucinated.\n\n### 5. Fallback to Search (Only if Necessary)\nIf the provided files do not contain the specific data needed:\n- State clearly what was missing from the files.\n- Then proceed with web search or estimation.\n- Mark any non-file data as \"External Search\" or \"Estimated\".\n\n## Checklist\n\n- [ ] Did I list all attached files?\n- [ ] Did I open and read the relevant files?\n- [ ] Did I verify the data exists in the files before searching?\n- [ ] Did I cite the file name in my output?\n- [ ] Did I avoid fabricating numbers that should have come from the file?\n\n## Example Usage\n\n**Task:** Create a report on active property listings.\n**Context:** `Massabama_active_listings.xlsx` is attached.\n\n**Incorrect Approach:**\n- Ignore the Excel file.\n- Search web for \"Massabama property listings\".\n- Fabricate numbers based on search snippets.\n- **Result:** Inaccurate data, ignored source of truth.\n\n**Correct Approach:**\n- Identify `Massabama_active_listings.xlsx` in context.\n- Load the Excel file.\n- Count rows and sum prices directly from the sheet.\n- Output: \"Based on the 50 entries in `Massabama_active_listings.xlsx`, the total value is...\"\n- **Result:** Accurate data, verified source.\n\n## Warnings\n\n- **Hallucination Risk:** Ignoring provided files is a primary cause of data fabrication.\n- **Efficiency:** Reading a local file is faster and more reliable than web scraping.\n- **User Expectation:** Users attach files expecting them to be used. Ignoring them is a failure of instruction following.","# Prioritize Context Data\n\n## Objective\nPrevent data hallucination and inefficiency by mandating that agents inspect and utilize provided reference files (CSV, XLSX, PDF, TXT, etc.) before attempting web searches or generating synthetic data.\n\n## Critical Rule\n**If a reference file is provided in the task context, it is the source of truth.** Do not fabricate data or search the web for information that exists within the provided attachments.\n\n## Workflow Steps\n\n### 1. Scan Context for Attachments\nAt the start of every task, explicitly list all files provided in the context window or attachment panel.\n- Check for spreadsheets (`.xlsx`, `.csv`), documents (`.pdf`, `.docx`), or data dumps (`.json`, `.txt`).\n- Note the filename and inferred content type.\n\n### 2. Evaluate Relevance\nDetermine if any provided file contains the data required to complete the task.\n- **Match Keywords:** Do filenames or column headers match task requirements?\n- **Check Scope:** Does the data cover the necessary timeframe or地域 (region)?\n\n### 3. Extract Data First\nIf relevant files are found:\n- Read the file content using appropriate tools (e.g., `read_file`, `pandas`, `pdf_reader`).\n- Extract the specific data points needed.\n- **Do not** proceed to web search until you have confirmed the file lacks the necessary information.\n\n### 4. Cite Source Explicitly\nWhen presenting data in the final output:\n- Explicitly state which file the data came from.\n- Example: \"According to `Massabama_active_listings.xlsx`...\"\n- This verifies to the user that real data was used, not hallucinated.\n\n### 5. Fallback to Search (Only if Necessary)\nIf the provided files do not contain the specific data needed:\n- State clearly what was missing from the files.\n- Then proceed with web search or estimation.\n- Mark any non-file data as \"External Search\" or \"Estimated\".\n\n## Checklist\n\n- [ ] Did I list all attached files?\n- [ ] Did I open and read the relevant files?\n- [ ] Did I verify the data exists in the files before searching?\n- [ ] Did I cite the file name in my output?\n- [ ] Did I avoid fabricating numbers that should have come from the file?\n\n## Example Usage\n\n**Task:** Create a report on active property listings.\n**Context:** `Massabama_active_listings.xlsx` is attached.\n\n**Incorrect Approach:**\n- Ignore the Excel file.\n- Search web for \"Massabama property listings\".\n- Fabricate numbers based on search snippets.\n- **Result:** Inaccurate data, ignored source of truth.\n\n**Correct Approach:**\n- Identify `Massabama_active_listings.xlsx` in context.\n- Load the Excel file.\n- Count rows and sum prices directly from the sheet.\n- Output: \"Based on the 50 entries in `Massabama_active_listings.xlsx`, the total value is...\"\n- **Result:** Accurate data, verified source.\n\n## Warnings\n\n- **Hallucination Risk:** Ignoring provided files is a primary cause of data fabrication.\n- **Efficiency:** Reading a local file is faster and more reliable than web scraping.\n- **User Expectation:** Users attach files expecting them to be used. Ignoring them is a failure of instruction following.",{"name":5,"category":28,"description":7},"main","af1b40a42167d09c30b3a63000aa14ace4c1e229","gdpval_bench\u002Fskills\u002Fprioritize-context-data","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":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add xyliu-cs\u002FOpenSpace-GDPval --skill prioritize-context-data",{"tool":53,"command":54},"bunx","bunx skills add xyliu-cs\u002FOpenSpace-GDPval --skill prioritize-context-data",{"tool":56,"command":57},"pnpm","pnpm dlx skills add xyliu-cs\u002FOpenSpace-GDPval --skill prioritize-context-data","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fprioritize-context-data\u002FSKILL.md",true,[61],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},".skill_id","OTHER","其他",37,"https:\u002F\u002Fgithub.com\u002Fxyliu-cs\u002FOpenSpace-GDPval\u002Fblob\u002Fmain\u002Fgdpval_bench\u002Fskills\u002Fprioritize-context-data\u002F.skill_id",[68,81,89,105,128,149],{"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},"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",[],[75,76,77,78,79,80],"zip export deliverable","zip","export","deliverables","codebase","as",{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":34},"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",[],[88,76,78,79,80],"zip deliverable finalization",{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":34},"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",[],[96,97,98,99,100,101,102,103,80,104],"failure analysis","ZeRO","analysis","iteration","zero iteration failure analysis","with","issues","execution","system",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":114,"publishedAt":34},"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",[111],{"categoryNo":112,"categoryName":113,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000034","行政与办公人员",[115,116,117,118,119,120,121,122,123,124,125,126,24,127],"fallback","write","file","report","write file fallback report","domain","professional","sources","retrieval","generate","embedded","documents","knowledge",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":139,"publishedAt":34},"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",[134],{"categoryNo":135,"categoryName":136,"taxonomyType":137,"taxonomyTypeDesc":138},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[140,101,115,141,142,143,126,124,117,144,145,146,116,147,121,148,33],"fallback doc with delegation","doc","delegation","shell","markdown","tool","text","simple","formats",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":156,"publishedAt":34},"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",[155],{"categoryNo":112,"categoryName":113,"taxonomyType":21,"taxonomyTypeDesc":22},[115,118,26,157,124,117,158,159,116,160,161,123,101,162,126],"context anchored fallback report","Guardrails","Tools","task","drift","context drift"]