[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-mongodb-mongodb-search-and-ai":3,"mdc--pekx1m-key":40,"related-repo-mongodb-mongodb-search-and-ai":897,"related-org-mongodb-mongodb-search-and-ai":987},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":35,"sourceUrl":38,"mdContent":39},"mongodb-search-and-ai","implement Atlas Search and Vector Search","Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions. Use this skill when users need to build search functionality for text-based queries (autocomplete, fuzzy matching, faceted search), semantic similarity (embeddings, RAG applications), or combined approaches. Also use when users need text containment, substring matching ('contains', 'includes', 'appears in'), case-insensitive or multi-field text search, or filtering across many fields with variable combinations. Provides workflows for selecting the right search type, creating indexes, constructing queries, and optimizing performance using the MongoDB MCP server.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"mongodb","MongoDB","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fmongodb.jpg",[12,16,19,20],{"name":13,"slug":14,"type":15},"LLM","llm","tag",{"name":17,"slug":18,"type":15},"RAG","rag",{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"Search","search",155,"https:\u002F\u002Fgithub.com\u002Fmongodb\u002Fagent-skills","2026-07-16T06:01:58.645908","Apache-2.0",28,[29,30,31,32,33,34],"agent","claude","cursor","gemini-cli-extension","mcp","skills",{"repoUrl":24,"stars":23,"forks":27,"topics":36,"description":37},[29,30,31,32,33,34],"Use the official MongoDB Skills with your favorite coding agent to build faster.","https:\u002F\u002Fgithub.com\u002Fmongodb\u002Fagent-skills\u002Ftree\u002FHEAD\u002Fskills\u002Fmongodb-search-and-ai","---\nname: mongodb-search-and-ai\ndescription: |\n  Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions. Use this skill when users need to build search functionality for text-based queries (autocomplete, fuzzy matching, faceted search), semantic similarity (embeddings, RAG applications), or combined approaches. Also use when users need text containment, substring matching ('contains', 'includes', 'appears in'), case-insensitive or multi-field text search, or filtering across many fields with variable combinations. Provides workflows for selecting the right search type, creating indexes, constructing queries, and optimizing performance using the MongoDB MCP server.\nlicense: Apache-2.0\nmetadata:\n  version: \"1.0.0\"\n---\n\n# MongoDB Search and AI Recommendations Skill\n\nYou are helping MongoDB users implement, optimize, and troubleshoot Atlas Search (lexical), Vector Search (semantic), and Hybrid Search (combined) solutions. Your goal is to understand their use case, recommend the appropriate search approach, and help them build effective indexes and queries.\n\n## Core Principles\n\n1. **Understand before building** - Validate the use case to ensure you recommend the right solution\n2. **Always inspect first** - Check existing indexes and schema before making recommendations\n3. **Explain before executing** - Describe what indexes will be created and require explicit approval\n4. **Optimize for the use case** - Different use cases require different index configurations and query patterns\n5. **Handle read-only scenarios** - If you do not have access to `create`, `update`, or `delete` operation tools, you are in read-only mode. Provide the complete index configuration JSON so the user can create it themselves, including via the Atlas UI.\n\n## Workflow\n\n### 1. Discovery Phase\n\n**Check the environment:**\n- Use `list-databases` and `list-collections` to understand available data\n- If the user mentions a collection, use `collection-schema` to inspect field structure\n- Use `collection-indexes` to see existing indexes\n- Use `atlas-inspect-cluster` to determine the cluster's MongoDB version\n\n**Understand the use case:**\nIf the user's request is vague:\n- Ask clarifying questions about their needs\n- Infer likely collection and fields from schema\n- Confirm understanding before proceeding\n\nCommon questions to ask:\n- What are users searching for? (products, movies, documents, etc.)\n- What fields contain the searchable content?\n- Do they need exact matching, fuzzy matching, or semantic similarity?\n- Do they need filters (price ranges, categories, dates)?\n- Do they need autocomplete\u002Ftypeahead functionality?\n\n### 2. Determine Search Type\n\n**Atlas Search (Lexical\u002FFull-Text):**\nUse when users need:\n- Keyword matching with relevance scoring\n- Fuzzy matching for typo tolerance\n- Autocomplete\u002Ftypeahead\n- Faceted search with filters\n- Language-specific text analysis\n- Token-based search\n- Lexical search with views\n\n**Vector Search (Semantic):**\nUse when users need:\n- Semantic similarity (\"find movies about coming of age stories\")\n- Natural language understanding\n- RAG (Retrieval Augmented Generation) applications\n- Finding conceptually similar items\n- Cross-modal search\n- Vector search with views\n\n**Hybrid Search:**\nUse when users need:\n- Combining multiple search approaches (e.g., vector + lexical, multiple text searches)\n- Queries like \"find action movies similar to 'epic space battles'\" (combining keyword filtering with semantic similarity)\n- Results that factor in multiple relevance criteria\n- Uses `$rankFusion` (rank-based) or `$scoreFusion` (score-based) to merge pipelines\n\n### 3. Version Check (Hybrid Search only)\n\nIf the search type is **Hybrid using `$rankFusion` or `$scoreFusion`**, verify the cluster version before proceeding:\n- `$rankFusion` requires MongoDB 8.0+\n- `$scoreFusion` requires MongoDB 8.2+\n\nIf the version requirement is not met, do not proceed — inform the user the feature is unavailable and suggest upgrading. Do not consult `references\u002Fhybrid-search.md`.\n\nIf the search type is Lexical, Vector, or the lexical prefilter pattern (`vectorSearch` operator inside `$search`), proceed to the next step.\n\n### 4. Consult Reference Files\n\nAlways consult the appropriate reference file(s) before recommending indexes or queries:\n- **Lexical**: consult both `references\u002Flexical-search-indexing.md` (index) and `references\u002Flexical-search-querying.md` (query)\n- **Vector**: consult `references\u002Fvector-search.md`\n- **Hybrid**: consult `references\u002Fhybrid-search.md` (and the lexical\u002Fvector files for the individual pipeline stages within it)\n\n### 5. Execution and Validation\n\n**Creating indexes:**\n1. Explain the index configuration in plain language\n2. Show the JSON structure\n3. Ask what the user wants to name the index\n4. Get explicit approval: \"Should I create this index?\"\n5. Use MCP's `create-index` tool after approval\n6. In read-only mode, provide the complete index JSON for creation via the Atlas UI\n\n**Running queries:**\n1. Show the aggregation pipeline\n2. Execute using MCP's `aggregate` tool\n3. Present results clearly\n\n**Refining existing queries:**\n1. Ask the user to share their current query\n2. Compare against the query patterns and best practices in the relevant reference file(s)\n3. Propose specific improvements with before\u002Fafter examples\n4. Run the revised query with `aggregate` to validate the results\n\n## Anti-Patterns to Avoid\n\n**NEVER recommend $regex or $text for search use cases:**\n- **$regex**: Not designed for full-text search. Lacks relevance scoring, fuzzy matching, and language-aware tokenization.\n- **$text**: Legacy operator that doesn't scale well for search workloads.\n\nIf a user asks for regex\u002Ftext for a search use case, explain why Atlas Search is more appropriate and show the equivalent pattern.\n\n## Handling Edge Cases\n\n**User mentions fields you can't find:**\n- Use `collection-schema` to inspect available fields\n- Suggest alternatives or ask for clarification\n\n**Required field doesn't exist:**\n- Explain what needs to be added and how (e.g., embedding field for vector search)\n\n**Query fails or index missing:**\n- Use `collection-indexes` to verify index exists\n- If missing, explain index needs to be created first\n\n**Multiple collections are relevant:**\n- List options and ask which one they mean\n- If context makes it obvious, confirm your assumption\n\n## Remember\n\n- Always check existing indexes before recommending new ones\n- Explain technical concepts in accessible language\n- Require approval before creating indexes\n- Map user's business requirements to technical implementations\n- Use the appropriate search type for the use case\n",{"data":41,"body":44},{"name":4,"description":6,"license":26,"metadata":42},{"version":43},"1.0.0",{"type":45,"children":46},"root",[47,56,62,69,150,156,163,171,233,243,261,266,294,300,310,348,357,390,399,438,444,468,491,504,525,531,536,597,603,611,652,660,686,694,724,730,738,761,766,772,780,799,807,815,823,842,850,863,869],{"type":48,"tag":49,"props":50,"children":52},"element","h1",{"id":51},"mongodb-search-and-ai-recommendations-skill",[53],{"type":54,"value":55},"text","MongoDB Search and AI Recommendations Skill",{"type":48,"tag":57,"props":58,"children":59},"p",{},[60],{"type":54,"value":61},"You are helping MongoDB users implement, optimize, and troubleshoot Atlas Search (lexical), Vector Search (semantic), and Hybrid Search (combined) solutions. Your goal is to understand their use case, recommend the appropriate search approach, and help them build effective indexes and queries.",{"type":48,"tag":63,"props":64,"children":66},"h2",{"id":65},"core-principles",[67],{"type":54,"value":68},"Core Principles",{"type":48,"tag":70,"props":71,"children":72},"ol",{},[73,85,95,105,115],{"type":48,"tag":74,"props":75,"children":76},"li",{},[77,83],{"type":48,"tag":78,"props":79,"children":80},"strong",{},[81],{"type":54,"value":82},"Understand before building",{"type":54,"value":84}," - Validate the use case to ensure you recommend the right solution",{"type":48,"tag":74,"props":86,"children":87},{},[88,93],{"type":48,"tag":78,"props":89,"children":90},{},[91],{"type":54,"value":92},"Always inspect first",{"type":54,"value":94}," - Check existing indexes and schema before making recommendations",{"type":48,"tag":74,"props":96,"children":97},{},[98,103],{"type":48,"tag":78,"props":99,"children":100},{},[101],{"type":54,"value":102},"Explain before executing",{"type":54,"value":104}," - Describe what indexes will be created and require explicit approval",{"type":48,"tag":74,"props":106,"children":107},{},[108,113],{"type":48,"tag":78,"props":109,"children":110},{},[111],{"type":54,"value":112},"Optimize for the use case",{"type":54,"value":114}," - Different use cases require different index configurations and query patterns",{"type":48,"tag":74,"props":116,"children":117},{},[118,123,125,132,134,140,142,148],{"type":48,"tag":78,"props":119,"children":120},{},[121],{"type":54,"value":122},"Handle read-only scenarios",{"type":54,"value":124}," - If you do not have access to ",{"type":48,"tag":126,"props":127,"children":129},"code",{"className":128},[],[130],{"type":54,"value":131},"create",{"type":54,"value":133},", ",{"type":48,"tag":126,"props":135,"children":137},{"className":136},[],[138],{"type":54,"value":139},"update",{"type":54,"value":141},", or ",{"type":48,"tag":126,"props":143,"children":145},{"className":144},[],[146],{"type":54,"value":147},"delete",{"type":54,"value":149}," operation tools, you are in read-only mode. Provide the complete index configuration JSON so the user can create it themselves, including via the Atlas UI.",{"type":48,"tag":63,"props":151,"children":153},{"id":152},"workflow",[154],{"type":54,"value":155},"Workflow",{"type":48,"tag":157,"props":158,"children":160},"h3",{"id":159},"_1-discovery-phase",[161],{"type":54,"value":162},"1. Discovery Phase",{"type":48,"tag":57,"props":164,"children":165},{},[166],{"type":48,"tag":78,"props":167,"children":168},{},[169],{"type":54,"value":170},"Check the environment:",{"type":48,"tag":172,"props":173,"children":174},"ul",{},[175,196,209,221],{"type":48,"tag":74,"props":176,"children":177},{},[178,180,186,188,194],{"type":54,"value":179},"Use ",{"type":48,"tag":126,"props":181,"children":183},{"className":182},[],[184],{"type":54,"value":185},"list-databases",{"type":54,"value":187}," and ",{"type":48,"tag":126,"props":189,"children":191},{"className":190},[],[192],{"type":54,"value":193},"list-collections",{"type":54,"value":195}," to understand available data",{"type":48,"tag":74,"props":197,"children":198},{},[199,201,207],{"type":54,"value":200},"If the user mentions a collection, use ",{"type":48,"tag":126,"props":202,"children":204},{"className":203},[],[205],{"type":54,"value":206},"collection-schema",{"type":54,"value":208}," to inspect field structure",{"type":48,"tag":74,"props":210,"children":211},{},[212,213,219],{"type":54,"value":179},{"type":48,"tag":126,"props":214,"children":216},{"className":215},[],[217],{"type":54,"value":218},"collection-indexes",{"type":54,"value":220}," to see existing indexes",{"type":48,"tag":74,"props":222,"children":223},{},[224,225,231],{"type":54,"value":179},{"type":48,"tag":126,"props":226,"children":228},{"className":227},[],[229],{"type":54,"value":230},"atlas-inspect-cluster",{"type":54,"value":232}," to determine the cluster's MongoDB version",{"type":48,"tag":57,"props":234,"children":235},{},[236,241],{"type":48,"tag":78,"props":237,"children":238},{},[239],{"type":54,"value":240},"Understand the use case:",{"type":54,"value":242},"\nIf the user's request is vague:",{"type":48,"tag":172,"props":244,"children":245},{},[246,251,256],{"type":48,"tag":74,"props":247,"children":248},{},[249],{"type":54,"value":250},"Ask clarifying questions about their needs",{"type":48,"tag":74,"props":252,"children":253},{},[254],{"type":54,"value":255},"Infer likely collection and fields from schema",{"type":48,"tag":74,"props":257,"children":258},{},[259],{"type":54,"value":260},"Confirm understanding before proceeding",{"type":48,"tag":57,"props":262,"children":263},{},[264],{"type":54,"value":265},"Common questions to ask:",{"type":48,"tag":172,"props":267,"children":268},{},[269,274,279,284,289],{"type":48,"tag":74,"props":270,"children":271},{},[272],{"type":54,"value":273},"What are users searching for? (products, movies, documents, etc.)",{"type":48,"tag":74,"props":275,"children":276},{},[277],{"type":54,"value":278},"What fields contain the searchable content?",{"type":48,"tag":74,"props":280,"children":281},{},[282],{"type":54,"value":283},"Do they need exact matching, fuzzy matching, or semantic similarity?",{"type":48,"tag":74,"props":285,"children":286},{},[287],{"type":54,"value":288},"Do they need filters (price ranges, categories, dates)?",{"type":48,"tag":74,"props":290,"children":291},{},[292],{"type":54,"value":293},"Do they need autocomplete\u002Ftypeahead functionality?",{"type":48,"tag":157,"props":295,"children":297},{"id":296},"_2-determine-search-type",[298],{"type":54,"value":299},"2. Determine Search Type",{"type":48,"tag":57,"props":301,"children":302},{},[303,308],{"type":48,"tag":78,"props":304,"children":305},{},[306],{"type":54,"value":307},"Atlas Search (Lexical\u002FFull-Text):",{"type":54,"value":309},"\nUse when users need:",{"type":48,"tag":172,"props":311,"children":312},{},[313,318,323,328,333,338,343],{"type":48,"tag":74,"props":314,"children":315},{},[316],{"type":54,"value":317},"Keyword matching with relevance scoring",{"type":48,"tag":74,"props":319,"children":320},{},[321],{"type":54,"value":322},"Fuzzy matching for typo tolerance",{"type":48,"tag":74,"props":324,"children":325},{},[326],{"type":54,"value":327},"Autocomplete\u002Ftypeahead",{"type":48,"tag":74,"props":329,"children":330},{},[331],{"type":54,"value":332},"Faceted search with filters",{"type":48,"tag":74,"props":334,"children":335},{},[336],{"type":54,"value":337},"Language-specific text analysis",{"type":48,"tag":74,"props":339,"children":340},{},[341],{"type":54,"value":342},"Token-based search",{"type":48,"tag":74,"props":344,"children":345},{},[346],{"type":54,"value":347},"Lexical search with views",{"type":48,"tag":57,"props":349,"children":350},{},[351,356],{"type":48,"tag":78,"props":352,"children":353},{},[354],{"type":54,"value":355},"Vector Search (Semantic):",{"type":54,"value":309},{"type":48,"tag":172,"props":358,"children":359},{},[360,365,370,375,380,385],{"type":48,"tag":74,"props":361,"children":362},{},[363],{"type":54,"value":364},"Semantic similarity (\"find movies about coming of age stories\")",{"type":48,"tag":74,"props":366,"children":367},{},[368],{"type":54,"value":369},"Natural language understanding",{"type":48,"tag":74,"props":371,"children":372},{},[373],{"type":54,"value":374},"RAG (Retrieval Augmented Generation) applications",{"type":48,"tag":74,"props":376,"children":377},{},[378],{"type":54,"value":379},"Finding conceptually similar items",{"type":48,"tag":74,"props":381,"children":382},{},[383],{"type":54,"value":384},"Cross-modal search",{"type":48,"tag":74,"props":386,"children":387},{},[388],{"type":54,"value":389},"Vector search with views",{"type":48,"tag":57,"props":391,"children":392},{},[393,398],{"type":48,"tag":78,"props":394,"children":395},{},[396],{"type":54,"value":397},"Hybrid Search:",{"type":54,"value":309},{"type":48,"tag":172,"props":400,"children":401},{},[402,407,412,417],{"type":48,"tag":74,"props":403,"children":404},{},[405],{"type":54,"value":406},"Combining multiple search approaches (e.g., vector + lexical, multiple text searches)",{"type":48,"tag":74,"props":408,"children":409},{},[410],{"type":54,"value":411},"Queries like \"find action movies similar to 'epic space battles'\" (combining keyword filtering with semantic similarity)",{"type":48,"tag":74,"props":413,"children":414},{},[415],{"type":54,"value":416},"Results that factor in multiple relevance criteria",{"type":48,"tag":74,"props":418,"children":419},{},[420,422,428,430,436],{"type":54,"value":421},"Uses ",{"type":48,"tag":126,"props":423,"children":425},{"className":424},[],[426],{"type":54,"value":427},"$rankFusion",{"type":54,"value":429}," (rank-based) or ",{"type":48,"tag":126,"props":431,"children":433},{"className":432},[],[434],{"type":54,"value":435},"$scoreFusion",{"type":54,"value":437}," (score-based) to merge pipelines",{"type":48,"tag":157,"props":439,"children":441},{"id":440},"_3-version-check-hybrid-search-only",[442],{"type":54,"value":443},"3. Version Check (Hybrid Search only)",{"type":48,"tag":57,"props":445,"children":446},{},[447,449,466],{"type":54,"value":448},"If the search type is ",{"type":48,"tag":78,"props":450,"children":451},{},[452,454,459,461],{"type":54,"value":453},"Hybrid using ",{"type":48,"tag":126,"props":455,"children":457},{"className":456},[],[458],{"type":54,"value":427},{"type":54,"value":460}," or ",{"type":48,"tag":126,"props":462,"children":464},{"className":463},[],[465],{"type":54,"value":435},{"type":54,"value":467},", verify the cluster version before proceeding:",{"type":48,"tag":172,"props":469,"children":470},{},[471,481],{"type":48,"tag":74,"props":472,"children":473},{},[474,479],{"type":48,"tag":126,"props":475,"children":477},{"className":476},[],[478],{"type":54,"value":427},{"type":54,"value":480}," requires MongoDB 8.0+",{"type":48,"tag":74,"props":482,"children":483},{},[484,489],{"type":48,"tag":126,"props":485,"children":487},{"className":486},[],[488],{"type":54,"value":435},{"type":54,"value":490}," requires MongoDB 8.2+",{"type":48,"tag":57,"props":492,"children":493},{},[494,496,502],{"type":54,"value":495},"If the version requirement is not met, do not proceed — inform the user the feature is unavailable and suggest upgrading. Do not consult ",{"type":48,"tag":126,"props":497,"children":499},{"className":498},[],[500],{"type":54,"value":501},"references\u002Fhybrid-search.md",{"type":54,"value":503},".",{"type":48,"tag":57,"props":505,"children":506},{},[507,509,515,517,523],{"type":54,"value":508},"If the search type is Lexical, Vector, or the lexical prefilter pattern (",{"type":48,"tag":126,"props":510,"children":512},{"className":511},[],[513],{"type":54,"value":514},"vectorSearch",{"type":54,"value":516}," operator inside ",{"type":48,"tag":126,"props":518,"children":520},{"className":519},[],[521],{"type":54,"value":522},"$search",{"type":54,"value":524},"), proceed to the next step.",{"type":48,"tag":157,"props":526,"children":528},{"id":527},"_4-consult-reference-files",[529],{"type":54,"value":530},"4. Consult Reference Files",{"type":48,"tag":57,"props":532,"children":533},{},[534],{"type":54,"value":535},"Always consult the appropriate reference file(s) before recommending indexes or queries:",{"type":48,"tag":172,"props":537,"children":538},{},[539,565,581],{"type":48,"tag":74,"props":540,"children":541},{},[542,547,549,555,557,563],{"type":48,"tag":78,"props":543,"children":544},{},[545],{"type":54,"value":546},"Lexical",{"type":54,"value":548},": consult both ",{"type":48,"tag":126,"props":550,"children":552},{"className":551},[],[553],{"type":54,"value":554},"references\u002Flexical-search-indexing.md",{"type":54,"value":556}," (index) and ",{"type":48,"tag":126,"props":558,"children":560},{"className":559},[],[561],{"type":54,"value":562},"references\u002Flexical-search-querying.md",{"type":54,"value":564}," (query)",{"type":48,"tag":74,"props":566,"children":567},{},[568,573,575],{"type":48,"tag":78,"props":569,"children":570},{},[571],{"type":54,"value":572},"Vector",{"type":54,"value":574},": consult ",{"type":48,"tag":126,"props":576,"children":578},{"className":577},[],[579],{"type":54,"value":580},"references\u002Fvector-search.md",{"type":48,"tag":74,"props":582,"children":583},{},[584,589,590,595],{"type":48,"tag":78,"props":585,"children":586},{},[587],{"type":54,"value":588},"Hybrid",{"type":54,"value":574},{"type":48,"tag":126,"props":591,"children":593},{"className":592},[],[594],{"type":54,"value":501},{"type":54,"value":596}," (and the lexical\u002Fvector files for the individual pipeline stages within it)",{"type":48,"tag":157,"props":598,"children":600},{"id":599},"_5-execution-and-validation",[601],{"type":54,"value":602},"5. Execution and Validation",{"type":48,"tag":57,"props":604,"children":605},{},[606],{"type":48,"tag":78,"props":607,"children":608},{},[609],{"type":54,"value":610},"Creating indexes:",{"type":48,"tag":70,"props":612,"children":613},{},[614,619,624,629,634,647],{"type":48,"tag":74,"props":615,"children":616},{},[617],{"type":54,"value":618},"Explain the index configuration in plain language",{"type":48,"tag":74,"props":620,"children":621},{},[622],{"type":54,"value":623},"Show the JSON structure",{"type":48,"tag":74,"props":625,"children":626},{},[627],{"type":54,"value":628},"Ask what the user wants to name the index",{"type":48,"tag":74,"props":630,"children":631},{},[632],{"type":54,"value":633},"Get explicit approval: \"Should I create this index?\"",{"type":48,"tag":74,"props":635,"children":636},{},[637,639,645],{"type":54,"value":638},"Use MCP's ",{"type":48,"tag":126,"props":640,"children":642},{"className":641},[],[643],{"type":54,"value":644},"create-index",{"type":54,"value":646}," tool after approval",{"type":48,"tag":74,"props":648,"children":649},{},[650],{"type":54,"value":651},"In read-only mode, provide the complete index JSON for creation via the Atlas UI",{"type":48,"tag":57,"props":653,"children":654},{},[655],{"type":48,"tag":78,"props":656,"children":657},{},[658],{"type":54,"value":659},"Running queries:",{"type":48,"tag":70,"props":661,"children":662},{},[663,668,681],{"type":48,"tag":74,"props":664,"children":665},{},[666],{"type":54,"value":667},"Show the aggregation pipeline",{"type":48,"tag":74,"props":669,"children":670},{},[671,673,679],{"type":54,"value":672},"Execute using MCP's ",{"type":48,"tag":126,"props":674,"children":676},{"className":675},[],[677],{"type":54,"value":678},"aggregate",{"type":54,"value":680}," tool",{"type":48,"tag":74,"props":682,"children":683},{},[684],{"type":54,"value":685},"Present results clearly",{"type":48,"tag":57,"props":687,"children":688},{},[689],{"type":48,"tag":78,"props":690,"children":691},{},[692],{"type":54,"value":693},"Refining existing queries:",{"type":48,"tag":70,"props":695,"children":696},{},[697,702,707,712],{"type":48,"tag":74,"props":698,"children":699},{},[700],{"type":54,"value":701},"Ask the user to share their current query",{"type":48,"tag":74,"props":703,"children":704},{},[705],{"type":54,"value":706},"Compare against the query patterns and best practices in the relevant reference file(s)",{"type":48,"tag":74,"props":708,"children":709},{},[710],{"type":54,"value":711},"Propose specific improvements with before\u002Fafter examples",{"type":48,"tag":74,"props":713,"children":714},{},[715,717,722],{"type":54,"value":716},"Run the revised query with ",{"type":48,"tag":126,"props":718,"children":720},{"className":719},[],[721],{"type":54,"value":678},{"type":54,"value":723}," to validate the results",{"type":48,"tag":63,"props":725,"children":727},{"id":726},"anti-patterns-to-avoid",[728],{"type":54,"value":729},"Anti-Patterns to Avoid",{"type":48,"tag":57,"props":731,"children":732},{},[733],{"type":48,"tag":78,"props":734,"children":735},{},[736],{"type":54,"value":737},"NEVER recommend $regex or $text for search use cases:",{"type":48,"tag":172,"props":739,"children":740},{},[741,751],{"type":48,"tag":74,"props":742,"children":743},{},[744,749],{"type":48,"tag":78,"props":745,"children":746},{},[747],{"type":54,"value":748},"$regex",{"type":54,"value":750},": Not designed for full-text search. Lacks relevance scoring, fuzzy matching, and language-aware tokenization.",{"type":48,"tag":74,"props":752,"children":753},{},[754,759],{"type":48,"tag":78,"props":755,"children":756},{},[757],{"type":54,"value":758},"$text",{"type":54,"value":760},": Legacy operator that doesn't scale well for search workloads.",{"type":48,"tag":57,"props":762,"children":763},{},[764],{"type":54,"value":765},"If a user asks for regex\u002Ftext for a search use case, explain why Atlas Search is more appropriate and show the equivalent pattern.",{"type":48,"tag":63,"props":767,"children":769},{"id":768},"handling-edge-cases",[770],{"type":54,"value":771},"Handling Edge Cases",{"type":48,"tag":57,"props":773,"children":774},{},[775],{"type":48,"tag":78,"props":776,"children":777},{},[778],{"type":54,"value":779},"User mentions fields you can't find:",{"type":48,"tag":172,"props":781,"children":782},{},[783,794],{"type":48,"tag":74,"props":784,"children":785},{},[786,787,792],{"type":54,"value":179},{"type":48,"tag":126,"props":788,"children":790},{"className":789},[],[791],{"type":54,"value":206},{"type":54,"value":793}," to inspect available fields",{"type":48,"tag":74,"props":795,"children":796},{},[797],{"type":54,"value":798},"Suggest alternatives or ask for clarification",{"type":48,"tag":57,"props":800,"children":801},{},[802],{"type":48,"tag":78,"props":803,"children":804},{},[805],{"type":54,"value":806},"Required field doesn't exist:",{"type":48,"tag":172,"props":808,"children":809},{},[810],{"type":48,"tag":74,"props":811,"children":812},{},[813],{"type":54,"value":814},"Explain what needs to be added and how (e.g., embedding field for vector search)",{"type":48,"tag":57,"props":816,"children":817},{},[818],{"type":48,"tag":78,"props":819,"children":820},{},[821],{"type":54,"value":822},"Query fails or index missing:",{"type":48,"tag":172,"props":824,"children":825},{},[826,837],{"type":48,"tag":74,"props":827,"children":828},{},[829,830,835],{"type":54,"value":179},{"type":48,"tag":126,"props":831,"children":833},{"className":832},[],[834],{"type":54,"value":218},{"type":54,"value":836}," to verify index exists",{"type":48,"tag":74,"props":838,"children":839},{},[840],{"type":54,"value":841},"If missing, explain index needs to be created first",{"type":48,"tag":57,"props":843,"children":844},{},[845],{"type":48,"tag":78,"props":846,"children":847},{},[848],{"type":54,"value":849},"Multiple collections are relevant:",{"type":48,"tag":172,"props":851,"children":852},{},[853,858],{"type":48,"tag":74,"props":854,"children":855},{},[856],{"type":54,"value":857},"List options and ask which one they mean",{"type":48,"tag":74,"props":859,"children":860},{},[861],{"type":54,"value":862},"If context makes it obvious, confirm your assumption",{"type":48,"tag":63,"props":864,"children":866},{"id":865},"remember",[867],{"type":54,"value":868},"Remember",{"type":48,"tag":172,"props":870,"children":871},{},[872,877,882,887,892],{"type":48,"tag":74,"props":873,"children":874},{},[875],{"type":54,"value":876},"Always check existing indexes before recommending new ones",{"type":48,"tag":74,"props":878,"children":879},{},[880],{"type":54,"value":881},"Explain technical concepts in accessible language",{"type":48,"tag":74,"props":883,"children":884},{},[885],{"type":54,"value":886},"Require approval before creating indexes",{"type":48,"tag":74,"props":888,"children":889},{},[890],{"type":54,"value":891},"Map user's business requirements to technical implementations",{"type":48,"tag":74,"props":893,"children":894},{},[895],{"type":54,"value":896},"Use the appropriate search type for the use case",{"items":898,"total":986},[899,916,928,941,953,966,979],{"slug":900,"name":900,"fn":901,"description":902,"org":903,"tags":904,"stars":23,"repoUrl":24,"updatedAt":915},"mongodb-atlas-stream-processing","manage MongoDB Atlas Stream Processing workflows","Manages MongoDB Atlas Stream Processing (ASP) workflows. Handles workspace provisioning, data source\u002Fsink connections, processor lifecycle operations, debugging diagnostics, and tier sizing. Supports Kafka, Atlas clusters, S3, HTTPS, and Lambda integrations for streaming data workloads and event processing. NOT for general MongoDB queries or Atlas cluster management. Requires MongoDB MCP Server with Atlas API credentials.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[905,908,911,914],{"name":906,"slug":907,"type":15},"Data Engineering","data-engineering",{"name":909,"slug":910,"type":15},"Data Pipeline","data-pipeline",{"name":912,"slug":913,"type":15},"Database","database",{"name":9,"slug":8,"type":15},"2026-07-13T06:15:32.953796",{"slug":917,"name":917,"fn":918,"description":919,"org":920,"tags":921,"stars":23,"repoUrl":24,"updatedAt":927},"mongodb-connection","configure MongoDB client connections","Optimize MongoDB client connection configuration (pools, timeouts, patterns) for any supported driver language. Use this skill when working\u002Fupdating\u002Freviewing on functions that instantiate or configure a MongoDB client (eg, when calling `connect()`), configuring connection pools, troubleshooting connection errors (ECONNREFUSED, timeouts, pool exhaustion), optimizing performance issues related to connections. This includes scenarios like building serverless functions with MongoDB, creating API endpoints that use MongoDB, optimizing high-traffic MongoDB applications, creating long-running tasks and concurrency, or debugging connection-related failures.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[922,923,924],{"name":912,"slug":913,"type":15},{"name":9,"slug":8,"type":15},{"name":925,"slug":926,"type":15},"Performance","performance","2026-07-13T06:15:26.144554",{"slug":929,"name":929,"fn":930,"description":931,"org":932,"tags":933,"stars":23,"repoUrl":24,"updatedAt":940},"mongodb-mcp-setup","configure MongoDB MCP server","Guide users through configuring key MongoDB MCP server options. Use this skill when a user has the MongoDB MCP server installed but hasn't configured the required environment variables, or when they ask about connecting to MongoDB\u002FAtlas and don't have the credentials set up.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[934,937,939],{"name":935,"slug":936,"type":15},"Configuration","configuration",{"name":938,"slug":33,"type":15},"MCP",{"name":9,"slug":8,"type":15},"2026-07-16T06:00:24.26424",{"slug":942,"name":942,"fn":943,"description":944,"org":945,"tags":946,"stars":23,"repoUrl":24,"updatedAt":952},"mongodb-natural-language-querying","generate MongoDB queries from natural language","Generate read-only MongoDB queries (find) or aggregation pipelines using natural language, with collection schema context and sample documents. Use this skill whenever the user asks to write, create, or generate MongoDB queries, wants to filter\u002Fquery\u002Faggregate data in MongoDB, asks \"how do I query...\", needs help with query syntax, or discusses finding\u002Ffiltering\u002Fgrouping MongoDB documents. Also use for translating SQL-like requests to MongoDB syntax. Does NOT handle Atlas Search ($search operator), vector\u002Fsemantic search ($vectorSearch operator), fuzzy matching, autocomplete indexes, or relevance scoring - use search-and-ai for those. Does NOT analyze or optimize existing queries - use mongodb-query-optimizer for that. Does NOT handle aggregation pipelines that involve write operations. Requires MongoDB MCP server.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[947,950,951],{"name":948,"slug":949,"type":15},"Data Analysis","data-analysis",{"name":912,"slug":913,"type":15},{"name":9,"slug":8,"type":15},"2026-07-16T06:02:02.491655",{"slug":954,"name":954,"fn":955,"description":956,"org":957,"tags":958,"stars":23,"repoUrl":24,"updatedAt":965},"mongodb-query-optimizer","optimize MongoDB queries and indexes","Help with MongoDB query optimization and indexing. Use only when the user asks for optimization or performance: \"How do I optimize this query?\", \"How do I index this?\", \"Why is this query slow?\", \"Can you fix my slow queries?\", \"What are the slow queries on my cluster?\", etc. Do not invoke for general MongoDB query writing unless user asks for performance or index help. Prefer indexing as optimization strategy. Use MongoDB MCP when available.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[959,960,963,964],{"name":912,"slug":913,"type":15},{"name":961,"slug":962,"type":15},"Debugging","debugging",{"name":9,"slug":8,"type":15},{"name":925,"slug":926,"type":15},"2026-07-13T06:15:44.51826",{"slug":967,"name":967,"fn":968,"description":969,"org":970,"tags":971,"stars":23,"repoUrl":24,"updatedAt":978},"mongodb-schema-design","design and optimize MongoDB schemas","MongoDB schema design patterns and anti-patterns. Use when designing data models, reviewing schemas, migrating from SQL, or troubleshooting performance issues caused by schema problems. Triggers on \"design schema\", \"embed vs reference\", \"MongoDB data model\", \"schema review\", \"unbounded arrays\", \"one-to-many\", \"tree structure\", \"16MB limit\", \"schema validation\", \"JSON Schema\", \"time series\", \"schema migration\", \"polymorphic\", \"TTL\", \"data lifecycle\", \"archive\", \"index explosion\", \"unnecessary indexes\", \"approximation pattern\", \"document versioning\".",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[972,975,976,977],{"name":973,"slug":974,"type":15},"Data Modeling","data-modeling",{"name":912,"slug":913,"type":15},{"name":9,"slug":8,"type":15},{"name":925,"slug":926,"type":15},"2026-07-16T06:00:24.782785",{"slug":4,"name":4,"fn":5,"description":6,"org":980,"tags":981,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[982,983,984,985],{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":21,"slug":22,"type":15},7,{"items":988,"total":1070},[989,996,1002,1008,1014,1021,1028,1035,1052],{"slug":900,"name":900,"fn":901,"description":902,"org":990,"tags":991,"stars":23,"repoUrl":24,"updatedAt":915},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[992,993,994,995],{"name":906,"slug":907,"type":15},{"name":909,"slug":910,"type":15},{"name":912,"slug":913,"type":15},{"name":9,"slug":8,"type":15},{"slug":917,"name":917,"fn":918,"description":919,"org":997,"tags":998,"stars":23,"repoUrl":24,"updatedAt":927},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[999,1000,1001],{"name":912,"slug":913,"type":15},{"name":9,"slug":8,"type":15},{"name":925,"slug":926,"type":15},{"slug":929,"name":929,"fn":930,"description":931,"org":1003,"tags":1004,"stars":23,"repoUrl":24,"updatedAt":940},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1005,1006,1007],{"name":935,"slug":936,"type":15},{"name":938,"slug":33,"type":15},{"name":9,"slug":8,"type":15},{"slug":942,"name":942,"fn":943,"description":944,"org":1009,"tags":1010,"stars":23,"repoUrl":24,"updatedAt":952},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1011,1012,1013],{"name":948,"slug":949,"type":15},{"name":912,"slug":913,"type":15},{"name":9,"slug":8,"type":15},{"slug":954,"name":954,"fn":955,"description":956,"org":1015,"tags":1016,"stars":23,"repoUrl":24,"updatedAt":965},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1017,1018,1019,1020],{"name":912,"slug":913,"type":15},{"name":961,"slug":962,"type":15},{"name":9,"slug":8,"type":15},{"name":925,"slug":926,"type":15},{"slug":967,"name":967,"fn":968,"description":969,"org":1022,"tags":1023,"stars":23,"repoUrl":24,"updatedAt":978},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1024,1025,1026,1027],{"name":973,"slug":974,"type":15},{"name":912,"slug":913,"type":15},{"name":9,"slug":8,"type":15},{"name":925,"slug":926,"type":15},{"slug":4,"name":4,"fn":5,"description":6,"org":1029,"tags":1030,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1031,1032,1033,1034],{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"name":21,"slug":22,"type":15},{"slug":1036,"name":1036,"fn":1037,"description":1038,"org":1039,"tags":1040,"stars":1049,"repoUrl":1050,"updatedAt":1051},"kafka-to-asp","migrate Kafka connectors to Atlas Stream Processing","Converts MongoDB Kafka managed connector configurations (MongoDbAtlasSource \u002F MongoDbAtlasSink) to equivalent Atlas Stream Processing processors. One-time migration workflow: reads connector JSON, validates it, maps fields to ASP pipeline stages, and creates connections and processors via the MongoDB MCP Server. Requires MongoDB MCP Server with Atlas API credentials.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1041,1042,1045,1048],{"name":909,"slug":910,"type":15},{"name":1043,"slug":1044,"type":15},"ETL","etl",{"name":1046,"slug":1047,"type":15},"Migration","migration",{"name":9,"slug":8,"type":15},10,"https:\u002F\u002Fgithub.com\u002Fmongodb\u002FASP_example","2026-07-16T06:02:02.15744",{"slug":1053,"name":1053,"fn":1054,"description":1055,"org":1056,"tags":1057,"stars":1067,"repoUrl":1068,"updatedAt":1069},"tines","manage Tines security automation workflows","Use when creating, modifying, or managing Tines stories, actions, workflows, or automations. Also use when the user mentions Tines, asks about building SOAR workflows, or wants to automate security operations. Triggers on keywords like tines, story, action, webhook, workflow automation, SOAR.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1058,1061,1064],{"name":1059,"slug":1060,"type":15},"Automation","automation",{"name":1062,"slug":1063,"type":15},"Security","security",{"name":1065,"slug":1066,"type":15},"Workflow Automation","workflow-automation",1,"https:\u002F\u002Fgithub.com\u002Fmongodb\u002Ftines-claude","2026-07-13T06:15:24.618317",9]