[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-algolia-algolia-neuralsearch":3,"mdc-q2vho1-key":39,"related-org-algolia-algolia-neuralsearch":562,"related-repo-algolia-algolia-neuralsearch":736},{"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":34,"sourceUrl":37,"mdContent":38},"algolia-neuralsearch","configure and tune Algolia NeuralSearch","Product-specific Algolia NeuralSearch implementation, validation, and optimization guidance. Use when planning, enabling, configuring, testing, or tuning NeuralSearch, AI relevance, semantic retrieval, adaptive intent, model training, A\u002FB testing, limitations review, query analysis, relevance diagnostics, event readiness, and data preparation for neural or hybrid search experiences. Do NOT use for generic vector database, embeddings, or non-Algolia semantic search architecture. Do NOT use for live settings changes, replica creation, or analytics retrieval; use algolia-cli or algolia-mcp first, then this skill for readiness and rollout guidance.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"algolia","Algolia","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Falgolia.png",[12,16,17,20],{"name":13,"slug":14,"type":15},"Performance","performance","tag",{"name":9,"slug":8,"type":15},{"name":18,"slug":19,"type":15},"AI","ai",{"name":21,"slug":22,"type":15},"Search","search",8,"https:\u002F\u002Fgithub.com\u002Falgolia\u002Fskills","2026-08-01T06:06:29.105127","MIT",2,[29,30,8,31,32,22,33],"agent","ai-assistant","mcp","recommendations","skills",{"repoUrl":24,"stars":23,"forks":27,"topics":35,"description":36},[29,30,8,31,32,22,33],"Algolia skills for AI Agents","https:\u002F\u002Fgithub.com\u002Falgolia\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Falgolia-neuralsearch","---\nname: algolia-neuralsearch\ndescription: >\n  Product-specific Algolia NeuralSearch implementation, validation, and optimization guidance. Use when planning, enabling, configuring, testing, or tuning NeuralSearch, AI relevance, semantic retrieval, adaptive intent, model training, A\u002FB testing, limitations review, query analysis, relevance diagnostics, event readiness, and data preparation for neural or hybrid search experiences. Do NOT use for generic vector database, embeddings, or non-Algolia semantic search architecture. Do NOT use for live settings changes, replica creation, or analytics retrieval; use algolia-cli or algolia-mcp first, then this skill for readiness and rollout guidance.\nlicense: MIT\nmetadata:\n  author: algolia\n  version: \"0.4\"\n---\n\n# Algolia NeuralSearch\n\nUse this skill when adding or optimizing NeuralSearch. Neural relevance depends on good records, explicit relevance intent, representative queries, and measurement signals; do not treat it as a switch that fixes poor data. Current public docs state that click and conversion events are not required to activate NeuralSearch, but when present they guide semantic attribute selection and unlock retraining and Adaptive Intent; recheck them before advising on activation.\n\n## Customer-Facing Standard\n\n- Treat NeuralSearch as a rollout decision, not a standalone toggle.\n- Require evidence for data readiness, event readiness, query evaluation, filters, permissions, and rollback.\n- Use public `academy.algolia.com` for learning alignment and public `algolia.com\u002Fdoc` for current implementation guidance when source-backed context is needed.\n- When an Academy metadata reference pack is available, use only its `title`, `url`, `course`, `module`, `learning_objectives`, and `updated_at` fields for structure. If it is stale or no match exists, fall back to live Academy\u002Fdocs lookup. Do not treat cached metadata as course content or implementation authority.\n- Do not require custom Academy\u002Fdocs access; use customer-provided sources only as optional context.\n- When live Algolia data, analytics, index inspection, settings changes, or account actions are needed, use Algolia MCP, the Algolia CLI, or official Algolia skills for the live operation, then apply this skill to interpret results and validate the customer-ready implementation path.\n- Produce a clear go, limited rollout, fix-first, or do-not-start recommendation.\n\n## Official Companion Skills\n\n- Use official `algolia-mcp` for live query behavior, top searches, no-result searches, click\u002Fno-click signals, recommendations, and analytics evidence.\n- Use official `algolia-cli` when settings, replicas, rules, synonyms, or index changes are required.\n- Use this skill after the official tool call to produce rollout readiness, semantic query sets, measurement plans, and customer-facing launch guidance.\n\n## Source-Of-Truth Rules\n\n- Verify current NeuralSearch docs before stating activation steps, limitations, model training behavior, Adaptive Intent requirements, A\u002FB testing behavior, or replica\u002Fsort constraints.\n- Current public docs state that click and conversion events are not activation prerequisites: without events NeuralSearch selects semantic attributes from record structure, and with events it selects and weights attributes from real behavior. Adaptive Intent and retraining do depend on engagement data. Recheck the chosen mode's current docs before advising on cold-start, preview, activation, model training, or Adaptive Intent behavior.\n- Do not recommend launch without a representative query set and a rollback or staged rollout plan.\n\n## Workflow\n\n1. Read `references\u002Fneuralsearch-guide.md` before implementation or review.\n2. Read `references\u002Fexample-output.md` when producing a readiness report or rollout plan.\n3. Use `$algolia-discovery-planning` to clarify the search journey, success metrics, and query patterns.\n4. Use `$algolia-data-modeling` to ensure semantic fields, titles, descriptions, categories, and attributes are search-ready.\n5. Use `$algolia-index-configuration` to preserve the right balance of textual relevance, filters, facets, custom ranking, replicas, and business rules.\n6. Use `$algolia-events-insights` and `$algolia-release-qa` for event readiness, A\u002FB testing, analytics, and launch validation.\n7. Teach the rollout path: confirm eligibility and readiness, preview with a representative query set, test with a replica or controlled configuration, compare against baseline, tune one semantic variable at a time, then monitor and optimize.\n\n## Questions To Ask\n\n- Which query classes should NeuralSearch improve: vague, conceptual, natural-language, synonym-heavy, long-tail, support\u002Fcontent, or product discovery queries?\n- Which queries must remain exact, deterministic, compliance-sensitive, or heavily merchandised?\n- Which record fields carry semantic meaning, and which are noisy or internal?\n- Is the customer's plan and application eligible for the NeuralSearch mode they want to use?\n- Will testing happen in a replica, an A\u002FB test, a staged rollout, or a manual evaluation environment?\n- Which semantic behavior should be conservative, broader reach, or append-only relative to keyword relevance?\n- Are click, conversion, view, add-to-cart, purchase, or feedback events available to evaluate relevance?\n- What is the baseline: current conversion, CTR, zero-result rate, no-click searches, top-query relevance, or manual judgment set?\n- Is A\u002FB testing available before broad rollout?\n- Which limitations, language\u002Flocale constraints, filters, and sort expectations need to be reviewed in current docs?\n- Which attributes should carry semantic meaning, in priority order, and which attributes must never influence semantic matching?\n- For a surprising result, which evidence will distinguish a data problem, semantic-setting choice, keyword behavior, or merchandising override?\n\n## Implementation Standards\n\n- Audit records before enabling neural relevance. Titles, descriptions, categories, brand, attributes, and content summaries should reflect how users search.\n- Keep filters, facets, secured data, and business rules explicit; semantic matching must not leak inaccessible or irrelevant records.\n- Build a query evaluation set that includes head, tail, exact, vague, natural-language, branded, typo, category, and no-result queries.\n- Use A\u002FB testing or a staged rollout for meaningful relevance changes.\n- Do not optimize only by subjective spot checks. Pair human review with analytics and event signals.\n- Document limitations and feature constraints from current Algolia docs before promising behavior.\n- Use explainability tools or result inspection to diagnose surprising results before changing many settings.\n- Treat merchandising rules as compatible with NeuralSearch, but test pinned, buried, suppressed, promoted, and campaign-driven results against semantic behavior.\n- Use analytics tags, replica comparisons, or A\u002FB test segmentation so NeuralSearch impact can be isolated from unrelated relevance changes.\n- Select a small, meaningful semantic attribute set and justify the priority of each field; do not let IDs, supplier boilerplate, internal notes, or duplicated text dilute semantic meaning.\n- Compare hybrid behavior by result origin where current diagnostics expose it: keyword match, semantic match, or both. Use this evidence to diagnose rather than guessing from a result list.\n- Change one meaningful variable per evaluation round: semantic fields or priority, blend behavior, business rule, or ranking context. Keep the before\u002Fafter query set and decision record together.\n\n## Anti-Patterns\n\n- Treating NeuralSearch as a fix for poor record content, missing filters, weak relevance settings, or unclear business rules.\n- Evaluating only aggregate conversion or a handful of favorable queries.\n- Ignoring exact-match, compliance, permissions, merchandising, or sorted-result regressions.\n- Claiming events are required to activate NeuralSearch, or skipping event readiness entirely because activation does not require events; events still gate Adaptive Intent, retraining, and trustworthy measurement.\n- Promising Adaptive Intent or model-training behavior without checking current docs and event readiness.\n- Treating semantic configuration as a one-time activation choice instead of a testable, reversible relevance decision.\n- Diagnosing a surprising result by changing multiple fields, ranking rules, and merchandising settings at once.\n\n## Academy And Customer Education Alignment\n\nWhen source-backed guidance is needed, search public Academy sources for NeuralSearch and AI-readiness learning objectives and public Algolia docs for semantic retrieval, data readiness, events-informed optimization, A\u002FB testing, limitations, and current rollout guidance. Map the request to maturity level and use case, then produce guided prompts such as \"Use this skill to design my NeuralSearch rollout\" or \"Use this skill to validate my data, measurement path, and query set before rolling out NeuralSearch.\"\n\n## Maturity Behavior\n\n- Beginner implementation: do not start with NeuralSearch if basic data, filters, and search UI are not yet stable.\n- Production readiness: require deterministic filters, secured data strategy, rollback plan, and query evaluation set.\n- Optimization: compare semantic relevance against baseline relevance with representative query classes and outcome metrics.\n- AI readiness: prefer reliable events and feedback loops for measurement and Adaptive Intent readiness, while requiring permission-aware records and a clear go\u002Ffix-first\u002Fdo-not-start recommendation.\n\n## Output Contract\n\nReturn a NeuralSearch readiness assessment, semantic attribute rationale, query test set, measurement plan, rollout strategy, explainability\u002Fdiagnostic plan, and validation report. Call out missing data, missing or weak events, noisy fields, unsupported feature constraints, or business-rule conflicts before recommending launch.\n",{"data":40,"body":43},{"name":4,"description":6,"license":26,"metadata":41},{"author":8,"version":42},"0.4",{"type":44,"children":45},"root",[46,54,60,67,169,175,208,214,232,238,329,335,398,404,467,473,511,517,522,528,551,557],{"type":47,"tag":48,"props":49,"children":50},"element","h1",{"id":4},[51],{"type":52,"value":53},"text","Algolia NeuralSearch",{"type":47,"tag":55,"props":56,"children":57},"p",{},[58],{"type":52,"value":59},"Use this skill when adding or optimizing NeuralSearch. Neural relevance depends on good records, explicit relevance intent, representative queries, and measurement signals; do not treat it as a switch that fixes poor data. Current public docs state that click and conversion events are not required to activate NeuralSearch, but when present they guide semantic attribute selection and unlock retraining and Adaptive Intent; recheck them before advising on activation.",{"type":47,"tag":61,"props":62,"children":64},"h2",{"id":63},"customer-facing-standard",[65],{"type":52,"value":66},"Customer-Facing Standard",{"type":47,"tag":68,"props":69,"children":70},"ul",{},[71,77,82,104,154,159,164],{"type":47,"tag":72,"props":73,"children":74},"li",{},[75],{"type":52,"value":76},"Treat NeuralSearch as a rollout decision, not a standalone toggle.",{"type":47,"tag":72,"props":78,"children":79},{},[80],{"type":52,"value":81},"Require evidence for data readiness, event readiness, query evaluation, filters, permissions, and rollback.",{"type":47,"tag":72,"props":83,"children":84},{},[85,87,94,96,102],{"type":52,"value":86},"Use public ",{"type":47,"tag":88,"props":89,"children":91},"code",{"className":90},[],[92],{"type":52,"value":93},"academy.algolia.com",{"type":52,"value":95}," for learning alignment and public ",{"type":47,"tag":88,"props":97,"children":99},{"className":98},[],[100],{"type":52,"value":101},"algolia.com\u002Fdoc",{"type":52,"value":103}," for current implementation guidance when source-backed context is needed.",{"type":47,"tag":72,"props":105,"children":106},{},[107,109,115,117,123,124,130,131,137,138,144,146,152],{"type":52,"value":108},"When an Academy metadata reference pack is available, use only its ",{"type":47,"tag":88,"props":110,"children":112},{"className":111},[],[113],{"type":52,"value":114},"title",{"type":52,"value":116},", ",{"type":47,"tag":88,"props":118,"children":120},{"className":119},[],[121],{"type":52,"value":122},"url",{"type":52,"value":116},{"type":47,"tag":88,"props":125,"children":127},{"className":126},[],[128],{"type":52,"value":129},"course",{"type":52,"value":116},{"type":47,"tag":88,"props":132,"children":134},{"className":133},[],[135],{"type":52,"value":136},"module",{"type":52,"value":116},{"type":47,"tag":88,"props":139,"children":141},{"className":140},[],[142],{"type":52,"value":143},"learning_objectives",{"type":52,"value":145},", and ",{"type":47,"tag":88,"props":147,"children":149},{"className":148},[],[150],{"type":52,"value":151},"updated_at",{"type":52,"value":153}," fields for structure. If it is stale or no match exists, fall back to live Academy\u002Fdocs lookup. Do not treat cached metadata as course content or implementation authority.",{"type":47,"tag":72,"props":155,"children":156},{},[157],{"type":52,"value":158},"Do not require custom Academy\u002Fdocs access; use customer-provided sources only as optional context.",{"type":47,"tag":72,"props":160,"children":161},{},[162],{"type":52,"value":163},"When live Algolia data, analytics, index inspection, settings changes, or account actions are needed, use Algolia MCP, the Algolia CLI, or official Algolia skills for the live operation, then apply this skill to interpret results and validate the customer-ready implementation path.",{"type":47,"tag":72,"props":165,"children":166},{},[167],{"type":52,"value":168},"Produce a clear go, limited rollout, fix-first, or do-not-start recommendation.",{"type":47,"tag":61,"props":170,"children":172},{"id":171},"official-companion-skills",[173],{"type":52,"value":174},"Official Companion Skills",{"type":47,"tag":68,"props":176,"children":177},{},[178,191,203],{"type":47,"tag":72,"props":179,"children":180},{},[181,183,189],{"type":52,"value":182},"Use official ",{"type":47,"tag":88,"props":184,"children":186},{"className":185},[],[187],{"type":52,"value":188},"algolia-mcp",{"type":52,"value":190}," for live query behavior, top searches, no-result searches, click\u002Fno-click signals, recommendations, and analytics evidence.",{"type":47,"tag":72,"props":192,"children":193},{},[194,195,201],{"type":52,"value":182},{"type":47,"tag":88,"props":196,"children":198},{"className":197},[],[199],{"type":52,"value":200},"algolia-cli",{"type":52,"value":202}," when settings, replicas, rules, synonyms, or index changes are required.",{"type":47,"tag":72,"props":204,"children":205},{},[206],{"type":52,"value":207},"Use this skill after the official tool call to produce rollout readiness, semantic query sets, measurement plans, and customer-facing launch guidance.",{"type":47,"tag":61,"props":209,"children":211},{"id":210},"source-of-truth-rules",[212],{"type":52,"value":213},"Source-Of-Truth Rules",{"type":47,"tag":68,"props":215,"children":216},{},[217,222,227],{"type":47,"tag":72,"props":218,"children":219},{},[220],{"type":52,"value":221},"Verify current NeuralSearch docs before stating activation steps, limitations, model training behavior, Adaptive Intent requirements, A\u002FB testing behavior, or replica\u002Fsort constraints.",{"type":47,"tag":72,"props":223,"children":224},{},[225],{"type":52,"value":226},"Current public docs state that click and conversion events are not activation prerequisites: without events NeuralSearch selects semantic attributes from record structure, and with events it selects and weights attributes from real behavior. Adaptive Intent and retraining do depend on engagement data. Recheck the chosen mode's current docs before advising on cold-start, preview, activation, model training, or Adaptive Intent behavior.",{"type":47,"tag":72,"props":228,"children":229},{},[230],{"type":52,"value":231},"Do not recommend launch without a representative query set and a rollback or staged rollout plan.",{"type":47,"tag":61,"props":233,"children":235},{"id":234},"workflow",[236],{"type":52,"value":237},"Workflow",{"type":47,"tag":239,"props":240,"children":241},"ol",{},[242,255,267,280,292,304,324],{"type":47,"tag":72,"props":243,"children":244},{},[245,247,253],{"type":52,"value":246},"Read ",{"type":47,"tag":88,"props":248,"children":250},{"className":249},[],[251],{"type":52,"value":252},"references\u002Fneuralsearch-guide.md",{"type":52,"value":254}," before implementation or review.",{"type":47,"tag":72,"props":256,"children":257},{},[258,259,265],{"type":52,"value":246},{"type":47,"tag":88,"props":260,"children":262},{"className":261},[],[263],{"type":52,"value":264},"references\u002Fexample-output.md",{"type":52,"value":266}," when producing a readiness report or rollout plan.",{"type":47,"tag":72,"props":268,"children":269},{},[270,272,278],{"type":52,"value":271},"Use ",{"type":47,"tag":88,"props":273,"children":275},{"className":274},[],[276],{"type":52,"value":277},"$algolia-discovery-planning",{"type":52,"value":279}," to clarify the search journey, success metrics, and query patterns.",{"type":47,"tag":72,"props":281,"children":282},{},[283,284,290],{"type":52,"value":271},{"type":47,"tag":88,"props":285,"children":287},{"className":286},[],[288],{"type":52,"value":289},"$algolia-data-modeling",{"type":52,"value":291}," to ensure semantic fields, titles, descriptions, categories, and attributes are search-ready.",{"type":47,"tag":72,"props":293,"children":294},{},[295,296,302],{"type":52,"value":271},{"type":47,"tag":88,"props":297,"children":299},{"className":298},[],[300],{"type":52,"value":301},"$algolia-index-configuration",{"type":52,"value":303}," to preserve the right balance of textual relevance, filters, facets, custom ranking, replicas, and business rules.",{"type":47,"tag":72,"props":305,"children":306},{},[307,308,314,316,322],{"type":52,"value":271},{"type":47,"tag":88,"props":309,"children":311},{"className":310},[],[312],{"type":52,"value":313},"$algolia-events-insights",{"type":52,"value":315}," and ",{"type":47,"tag":88,"props":317,"children":319},{"className":318},[],[320],{"type":52,"value":321},"$algolia-release-qa",{"type":52,"value":323}," for event readiness, A\u002FB testing, analytics, and launch validation.",{"type":47,"tag":72,"props":325,"children":326},{},[327],{"type":52,"value":328},"Teach the rollout path: confirm eligibility and readiness, preview with a representative query set, test with a replica or controlled configuration, compare against baseline, tune one semantic variable at a time, then monitor and optimize.",{"type":47,"tag":61,"props":330,"children":332},{"id":331},"questions-to-ask",[333],{"type":52,"value":334},"Questions To Ask",{"type":47,"tag":68,"props":336,"children":337},{},[338,343,348,353,358,363,368,373,378,383,388,393],{"type":47,"tag":72,"props":339,"children":340},{},[341],{"type":52,"value":342},"Which query classes should NeuralSearch improve: vague, conceptual, natural-language, synonym-heavy, long-tail, support\u002Fcontent, or product discovery queries?",{"type":47,"tag":72,"props":344,"children":345},{},[346],{"type":52,"value":347},"Which queries must remain exact, deterministic, compliance-sensitive, or heavily merchandised?",{"type":47,"tag":72,"props":349,"children":350},{},[351],{"type":52,"value":352},"Which record fields carry semantic meaning, and which are noisy or internal?",{"type":47,"tag":72,"props":354,"children":355},{},[356],{"type":52,"value":357},"Is the customer's plan and application eligible for the NeuralSearch mode they want to use?",{"type":47,"tag":72,"props":359,"children":360},{},[361],{"type":52,"value":362},"Will testing happen in a replica, an A\u002FB test, a staged rollout, or a manual evaluation environment?",{"type":47,"tag":72,"props":364,"children":365},{},[366],{"type":52,"value":367},"Which semantic behavior should be conservative, broader reach, or append-only relative to keyword relevance?",{"type":47,"tag":72,"props":369,"children":370},{},[371],{"type":52,"value":372},"Are click, conversion, view, add-to-cart, purchase, or feedback events available to evaluate relevance?",{"type":47,"tag":72,"props":374,"children":375},{},[376],{"type":52,"value":377},"What is the baseline: current conversion, CTR, zero-result rate, no-click searches, top-query relevance, or manual judgment set?",{"type":47,"tag":72,"props":379,"children":380},{},[381],{"type":52,"value":382},"Is A\u002FB testing available before broad rollout?",{"type":47,"tag":72,"props":384,"children":385},{},[386],{"type":52,"value":387},"Which limitations, language\u002Flocale constraints, filters, and sort expectations need to be reviewed in current docs?",{"type":47,"tag":72,"props":389,"children":390},{},[391],{"type":52,"value":392},"Which attributes should carry semantic meaning, in priority order, and which attributes must never influence semantic matching?",{"type":47,"tag":72,"props":394,"children":395},{},[396],{"type":52,"value":397},"For a surprising result, which evidence will distinguish a data problem, semantic-setting choice, keyword behavior, or merchandising override?",{"type":47,"tag":61,"props":399,"children":401},{"id":400},"implementation-standards",[402],{"type":52,"value":403},"Implementation Standards",{"type":47,"tag":68,"props":405,"children":406},{},[407,412,417,422,427,432,437,442,447,452,457,462],{"type":47,"tag":72,"props":408,"children":409},{},[410],{"type":52,"value":411},"Audit records before enabling neural relevance. Titles, descriptions, categories, brand, attributes, and content summaries should reflect how users search.",{"type":47,"tag":72,"props":413,"children":414},{},[415],{"type":52,"value":416},"Keep filters, facets, secured data, and business rules explicit; semantic matching must not leak inaccessible or irrelevant records.",{"type":47,"tag":72,"props":418,"children":419},{},[420],{"type":52,"value":421},"Build a query evaluation set that includes head, tail, exact, vague, natural-language, branded, typo, category, and no-result queries.",{"type":47,"tag":72,"props":423,"children":424},{},[425],{"type":52,"value":426},"Use A\u002FB testing or a staged rollout for meaningful relevance changes.",{"type":47,"tag":72,"props":428,"children":429},{},[430],{"type":52,"value":431},"Do not optimize only by subjective spot checks. Pair human review with analytics and event signals.",{"type":47,"tag":72,"props":433,"children":434},{},[435],{"type":52,"value":436},"Document limitations and feature constraints from current Algolia docs before promising behavior.",{"type":47,"tag":72,"props":438,"children":439},{},[440],{"type":52,"value":441},"Use explainability tools or result inspection to diagnose surprising results before changing many settings.",{"type":47,"tag":72,"props":443,"children":444},{},[445],{"type":52,"value":446},"Treat merchandising rules as compatible with NeuralSearch, but test pinned, buried, suppressed, promoted, and campaign-driven results against semantic behavior.",{"type":47,"tag":72,"props":448,"children":449},{},[450],{"type":52,"value":451},"Use analytics tags, replica comparisons, or A\u002FB test segmentation so NeuralSearch impact can be isolated from unrelated relevance changes.",{"type":47,"tag":72,"props":453,"children":454},{},[455],{"type":52,"value":456},"Select a small, meaningful semantic attribute set and justify the priority of each field; do not let IDs, supplier boilerplate, internal notes, or duplicated text dilute semantic meaning.",{"type":47,"tag":72,"props":458,"children":459},{},[460],{"type":52,"value":461},"Compare hybrid behavior by result origin where current diagnostics expose it: keyword match, semantic match, or both. Use this evidence to diagnose rather than guessing from a result list.",{"type":47,"tag":72,"props":463,"children":464},{},[465],{"type":52,"value":466},"Change one meaningful variable per evaluation round: semantic fields or priority, blend behavior, business rule, or ranking context. Keep the before\u002Fafter query set and decision record together.",{"type":47,"tag":61,"props":468,"children":470},{"id":469},"anti-patterns",[471],{"type":52,"value":472},"Anti-Patterns",{"type":47,"tag":68,"props":474,"children":475},{},[476,481,486,491,496,501,506],{"type":47,"tag":72,"props":477,"children":478},{},[479],{"type":52,"value":480},"Treating NeuralSearch as a fix for poor record content, missing filters, weak relevance settings, or unclear business rules.",{"type":47,"tag":72,"props":482,"children":483},{},[484],{"type":52,"value":485},"Evaluating only aggregate conversion or a handful of favorable queries.",{"type":47,"tag":72,"props":487,"children":488},{},[489],{"type":52,"value":490},"Ignoring exact-match, compliance, permissions, merchandising, or sorted-result regressions.",{"type":47,"tag":72,"props":492,"children":493},{},[494],{"type":52,"value":495},"Claiming events are required to activate NeuralSearch, or skipping event readiness entirely because activation does not require events; events still gate Adaptive Intent, retraining, and trustworthy measurement.",{"type":47,"tag":72,"props":497,"children":498},{},[499],{"type":52,"value":500},"Promising Adaptive Intent or model-training behavior without checking current docs and event readiness.",{"type":47,"tag":72,"props":502,"children":503},{},[504],{"type":52,"value":505},"Treating semantic configuration as a one-time activation choice instead of a testable, reversible relevance decision.",{"type":47,"tag":72,"props":507,"children":508},{},[509],{"type":52,"value":510},"Diagnosing a surprising result by changing multiple fields, ranking rules, and merchandising settings at once.",{"type":47,"tag":61,"props":512,"children":514},{"id":513},"academy-and-customer-education-alignment",[515],{"type":52,"value":516},"Academy And Customer Education Alignment",{"type":47,"tag":55,"props":518,"children":519},{},[520],{"type":52,"value":521},"When source-backed guidance is needed, search public Academy sources for NeuralSearch and AI-readiness learning objectives and public Algolia docs for semantic retrieval, data readiness, events-informed optimization, A\u002FB testing, limitations, and current rollout guidance. Map the request to maturity level and use case, then produce guided prompts such as \"Use this skill to design my NeuralSearch rollout\" or \"Use this skill to validate my data, measurement path, and query set before rolling out NeuralSearch.\"",{"type":47,"tag":61,"props":523,"children":525},{"id":524},"maturity-behavior",[526],{"type":52,"value":527},"Maturity Behavior",{"type":47,"tag":68,"props":529,"children":530},{},[531,536,541,546],{"type":47,"tag":72,"props":532,"children":533},{},[534],{"type":52,"value":535},"Beginner implementation: do not start with NeuralSearch if basic data, filters, and search UI are not yet stable.",{"type":47,"tag":72,"props":537,"children":538},{},[539],{"type":52,"value":540},"Production readiness: require deterministic filters, secured data strategy, rollback plan, and query evaluation set.",{"type":47,"tag":72,"props":542,"children":543},{},[544],{"type":52,"value":545},"Optimization: compare semantic relevance against baseline relevance with representative query classes and outcome metrics.",{"type":47,"tag":72,"props":547,"children":548},{},[549],{"type":52,"value":550},"AI readiness: prefer reliable events and feedback loops for measurement and Adaptive Intent readiness, while requiring permission-aware records and a clear go\u002Ffix-first\u002Fdo-not-start recommendation.",{"type":47,"tag":61,"props":552,"children":554},{"id":553},"output-contract",[555],{"type":52,"value":556},"Output Contract",{"type":47,"tag":55,"props":558,"children":559},{},[560],{"type":52,"value":561},"Return a NeuralSearch readiness assessment, semantic attribute rationale, query test set, measurement plan, rollout strategy, explainability\u002Fdiagnostic plan, and validation report. Call out missing data, missing or weak events, noisy fields, unsupported feature constraints, or business-rule conflicts before recommending launch.",{"items":563,"total":735},[564,580,597,608,623,636,649,661,679,690,701,723],{"slug":565,"name":565,"fn":566,"description":567,"org":568,"tags":569,"stars":577,"repoUrl":578,"updatedAt":579},"algolia-docsearch-mcp","search developer documentation with Algolia","Use this skill when the user asks about public developer documentation, SDKs, APIs, libraries, frameworks, setup, configuration, or code examples. Fetch current docs from Algolia DocSearch MCP and cite source URLs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[570,571,574,576],{"name":9,"slug":8,"type":15},{"name":572,"slug":573,"type":15},"Documentation","documentation",{"name":575,"slug":31,"type":15},"MCP",{"name":21,"slug":22,"type":15},4365,"https:\u002F\u002Fgithub.com\u002Falgolia\u002Fdocsearch","2026-08-01T06:06:11.572314",{"slug":581,"name":581,"fn":582,"description":583,"org":584,"tags":585,"stars":23,"repoUrl":24,"updatedAt":596},"algobot-cli","build conversational AI with Algolia","Use for anything AI\u002Fagent\u002Fconversational built on Algolia: algobot CLI, Agent Studio, RAG systems, conversational product discovery, genAI content generation from search results (carousels, descriptions, headers), chatbots or recommendation agents using Algolia as retrieval, config-as-code workflows, multi-environment deploy (dev\u002Fstaging\u002Fprod), memory and personalization, MCP tool integrations, conversation history \u002F GDPR retention, or adding a chat widget alongside InstantSearch. Trigger on: \"algobot\", \"Agent Studio\", \"RAG with Algolia\", \"conversational experience\", \"AI agent\" + Algolia, \"genAI carousel\", \"chat widget\", or building AI features on top of Algolia search. Do NOT use for raw index ops (records, synonyms, settings) — use algolia-cli. Do NOT use for pure frontend search UI (InstantSearch, autocomplete) with no AI\u002Fagent layer.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[586,589,592,595],{"name":587,"slug":588,"type":15},"Agents","agents",{"name":590,"slug":591,"type":15},"Automation","automation",{"name":593,"slug":594,"type":15},"LLM","llm",{"name":21,"slug":22,"type":15},"2026-07-12T08:27:37.649724",{"slug":598,"name":598,"fn":599,"description":600,"org":601,"tags":602,"stars":23,"repoUrl":24,"updatedAt":607},"algolia-agent-studio","build conversational agents with Algolia Agent Studio","Product-specific Algolia Agent Studio implementation, validation, and optimization guidance. Use when planning, building, integrating, or auditing Agent Studio agents, AI-powered conversational experiences, LLM provider setup, Algolia Search tools, client-side tools, MCP tools, memory, prompting, conversations, turn context, caching, analytics, feedback, authentication, approved domains, guardrails, or tool security. Do NOT use for live Agent Studio configuration, dry runs, publish\u002Fdeploy actions, or config-as-code operations; use the official algobot-cli skill instead. Do NOT use for generic non-Algolia RAG or chatbot architecture unless Agent Studio is the target product.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[603,604,605,606],{"name":587,"slug":588,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"2026-08-01T06:06:28.033767",{"slug":609,"name":609,"fn":610,"description":611,"org":612,"tags":613,"stars":23,"repoUrl":24,"updatedAt":622},"algolia-autocomplete","build Algolia autocomplete and query suggestions","Build and review Algolia Autocomplete and query suggestion experiences. Use when planning or implementing typeahead, query suggestions, recent searches, popular searches, federated autocomplete panels, product\u002Fcontent suggestions, detached mobile mode, plugins, keyboard navigation, insights events, or Autocomplete integration with InstantSearch. For net-new search or ecommerce builds, start with algolia-discovery-planning, which loads algolia-search-implementation so source strategy, data contract, and event taxonomy decisions are visible before autocomplete is marked ready. Do NOT use for full search results pages, browse pages, filters, pagination, or current refinements; use algolia-instantsearch-ui instead. Do NOT use for choosing between Algolia UI libraries; use algolia-ui-libraries. Do NOT use as the source of truth for current Autocomplete package APIs; use the official instantsearch skill and current docs alongside this customer-readiness skill.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[614,615,618,619],{"name":9,"slug":8,"type":15},{"name":616,"slug":617,"type":15},"Frontend","frontend",{"name":21,"slug":22,"type":15},{"name":620,"slug":621,"type":15},"UI Components","ui-components","2026-08-01T06:06:29.968123",{"slug":200,"name":200,"fn":624,"description":625,"org":626,"tags":627,"stars":23,"repoUrl":24,"updatedAt":635},"manage Algolia indices and accounts","Use this skill whenever a user wants to execute operations against Algolia indices or accounts — deleting records, copying\u002Fmigrating indices, backing up data, importing\u002Fexporting records, managing API keys, editing synonyms, configuring rules, changing settings like facets, clearing indices, or automating Algolia in CI\u002FCD pipelines. The key signal is that the user wants to *act on* their Algolia data or configuration (server-side \u002F backend \u002F admin operations), regardless of whether they mention \"CLI\" or \"command line.\" If someone names a specific Algolia index and wants to change, move, query, or manage it, use this skill. Do NOT use for frontend search UI work (InstantSearch, React components, autocomplete widgets), Algolia dashboard GUI questions, or evaluating Algolia vs. other providers.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[628,631,634],{"name":629,"slug":630,"type":15},"CLI","cli",{"name":632,"slug":633,"type":15},"Data Engineering","data-engineering",{"name":21,"slug":22,"type":15},"2026-07-12T08:27:35.085246",{"slug":637,"name":637,"fn":638,"description":639,"org":640,"tags":641,"stars":23,"repoUrl":24,"updatedAt":648},"algolia-crawler","crawl websites into Algolia indices","Use this skill whenever a user wants to crawl one or more web pages or a whole site and turn them into an Algolia index using the Algolia CLI — especially for RAG, AI search, semantic search, or Agent Studio retrieval. Triggers: \"index my website\u002Fdocs with Algolia\", \"set up the Algolia Crawler\", \"crawl this page for RAG\", \"scrape my site into Algolia\", \"build a knowledge base for my AI agent from these URLs\", writing or debugging a crawler recordExtractor, or handling JavaScript-rendered pages that won't index. It guides ingestion end-to-end with `algolia crawler` commands: inspect the page, write a RAG-optimized recordExtractor, validate with `algolia crawler test` BEFORE indexing, apply index settings explicitly, then reindex. Do NOT use for building the chatbot\u002Fagent layer itself (use algobot-cli), raw record\u002Fsynonym\u002Fsettings ops on an existing index (use algolia-cli), frontend search UI (use instantsearch), or read-only search\u002Fanalytics (use algolia-mcp).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[642,643,644,645],{"name":590,"slug":591,"type":15},{"name":632,"slug":633,"type":15},{"name":21,"slug":22,"type":15},{"name":646,"slug":647,"type":15},"Web Scraping","web-scraping","2026-07-12T08:27:40.981109",{"slug":650,"name":650,"fn":651,"description":652,"org":653,"tags":654,"stars":23,"repoUrl":24,"updatedAt":660},"algolia-data-modeling","design Algolia data models and indices","Algolia data modeling and indexing guidance. Use before or alongside indexing records or building Algolia search UI for net-new search, browse, autocomplete, ecommerce, personalization, Dynamic Re-Ranking, recommendations, or analytics-aware implementations. Makes record shape, objectID, display fields, facets, ranking fields, and event attribution explicit decisions. Use for records, variants, SKUs, indices, replicas, searchable and faceting attributes, denormalization, merchandising fields, timestamps, inventory, event attribution, indexing pipelines, partial updates, secured data, multi-language or multi-region strategies, and migrations. Do NOT use for live imports, exports, record mutations, settings changes, or account actions; use algolia-cli or algolia-mcp. Do NOT use for frontend UI implementation; use algolia-instantsearch-ui, algolia-autocomplete, algolia-ui-libraries, or the official instantsearch skill.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[655,656,659],{"name":9,"slug":8,"type":15},{"name":657,"slug":658,"type":15},"Data Modeling","data-modeling",{"name":21,"slug":22,"type":15},"2026-08-01T06:06:01.500756",{"slug":662,"name":662,"fn":663,"description":664,"org":665,"tags":666,"stars":23,"repoUrl":24,"updatedAt":678},"algolia-discovery-planning","plan and audit Algolia search implementations","START HERE for any non-trivial Algolia work — building, adding, migrating, redesigning, auditing, or configuring search, browse, autocomplete, indexing, relevance, recommendations, personalization, merchandising, events, or analytics. Invoke this FIRST even when the task already seems scoped or the user names one specific feature (e.g. \"add InstantSearch\", \"build a storefront search\"): its job is to map the request to the full Algolia implementation lifecycle and load every companion skill each in-scope phase needs (algolia-search-implementation, algolia-data-modeling, algolia-index-configuration, algolia-ui-libraries, algolia-instantsearch-ui, algolia-autocomplete, algolia-events-insights, algolia-neuralsearch, algolia-agent-studio, algolia-release-qa) rather than jumping straight into a single skill. This skill plans and orchestrates; the focused companion skills and the official Algolia skills execute. Do NOT use for live account inspection or write actions; use algolia-mcp or algolia-cli for those.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[667,668,671,674,677],{"name":9,"slug":8,"type":15},{"name":669,"slug":670,"type":15},"Analytics","analytics",{"name":672,"slug":673,"type":15},"Configuration","configuration",{"name":675,"slug":676,"type":15},"Personalization","personalization",{"name":21,"slug":22,"type":15},"2026-08-01T06:06:03.021452",{"slug":680,"name":680,"fn":681,"description":682,"org":683,"tags":684,"stars":23,"repoUrl":24,"updatedAt":689},"algolia-events-insights","instrument Algolia events for analytics","Algolia event instrumentation guidance for Insights, analytics, personalization, Dynamic Re-Ranking, Recommend, and merchandising feedback loops. Use for search, autocomplete, browse, ecommerce, personalization, recommendations, or analytics instrumentation. Makes event decisions explicit before an Algolia UI is considered ready. Use when implementing or auditing clickedObjectIDsAfterSearch, convertedObjectIDsAfterSearch, viewedObjectIDs, addedToCartObjectIDsAfterSearch, purchasedObjectIDsAfterSearch, userToken, queryID, eventName, eventSubtype, or frontend\u002Fbackend event pipelines. Do NOT use for live analytics retrieval, top-query inspection, or account-aware diagnostics; use algolia-mcp. Do NOT use for framework-specific InstantSearch or Autocomplete APIs; use the official instantsearch skill alongside this planning and validation skill.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[685,686,687,688],{"name":9,"slug":8,"type":15},{"name":669,"slug":670,"type":15},{"name":675,"slug":676,"type":15},{"name":21,"slug":22,"type":15},"2026-08-01T06:06:02.009712",{"slug":691,"name":691,"fn":692,"description":693,"org":694,"tags":695,"stars":23,"repoUrl":24,"updatedAt":700},"algolia-index-configuration","configure Algolia index settings and relevance","Algolia index settings and relevance configuration guidance. Use when configuring searchableAttributes, attributesForFaceting, customRanking, ranking, replicas, virtual replicas, rules, synonyms, typo tolerance, distinct, filters, optional filters, merchandising, browse\u002Fcategory relevance, or A\u002FB-testable relevance changes. Do NOT use for live settings writes, backups, copies, or operational account tasks; use algolia-cli or algolia-mcp instead. Do NOT use for record-shape or variant strategy; use algolia-data-modeling instead.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[696,697,698,699],{"name":9,"slug":8,"type":15},{"name":672,"slug":673,"type":15},{"name":657,"slug":658,"type":15},{"name":21,"slug":22,"type":15},"2026-08-01T06:06:34.19163",{"slug":702,"name":702,"fn":703,"description":704,"org":705,"tags":706,"stars":23,"repoUrl":24,"updatedAt":722},"algolia-instantsearch-ui","build Algolia InstantSearch frontend experiences","Build and review Algolia InstantSearch experiences in JavaScript, React, Vue, Angular (via InstantSearch.js; Angular InstantSearch is deprecated), or compatible frontend stacks. Use when planning or reviewing search results pages, browse\u002Fcategory pages, routing, widgets, filters, facets, sort-by, pagination, infinite hits, current refinements, insights middleware, SSR, or UI-state synchronization. For net-new search UI builds, start with algolia-discovery-planning, which loads algolia-search-implementation so data contract and event taxonomy decisions are visible before UI is marked ready. Do NOT use for autocomplete\u002Ftypeahead experiences before the user commits to a results page; use algolia-autocomplete instead. Do NOT use for choosing between Algolia UI libraries; use algolia-ui-libraries. Do NOT use as the source of truth for current framework APIs or code-level implementation details; use the official instantsearch skill and current docs alongside this customer-readiness skill.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[707,708,711,712,715,718,719],{"name":9,"slug":8,"type":15},{"name":709,"slug":710,"type":15},"Angular","angular",{"name":616,"slug":617,"type":15},{"name":713,"slug":714,"type":15},"JavaScript","javascript",{"name":716,"slug":717,"type":15},"React","react",{"name":21,"slug":22,"type":15},{"name":720,"slug":721,"type":15},"Vue","vue","2026-08-01T06:06:33.66513",{"slug":188,"name":188,"fn":724,"description":725,"org":726,"tags":727,"stars":23,"repoUrl":24,"updatedAt":734},"search Algolia indices and retrieve analytics","Search Algolia indices via the Algolia MCP server, retrieve analytics (top searches, no-result rates, click positions, user counts), and get product recommendations (bought-together, related, trending). Triggers on search, indexing, analytics, Algolia, recommendations, MCP.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[728,729,732,733],{"name":669,"slug":670,"type":15},{"name":730,"slug":731,"type":15},"API Development","api-development",{"name":575,"slug":31,"type":15},{"name":21,"slug":22,"type":15},"2026-07-12T08:27:36.376387",19,{"items":737,"total":786},[738,745,752,759,765,772,778],{"slug":581,"name":581,"fn":582,"description":583,"org":739,"tags":740,"stars":23,"repoUrl":24,"updatedAt":596},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[741,742,743,744],{"name":587,"slug":588,"type":15},{"name":590,"slug":591,"type":15},{"name":593,"slug":594,"type":15},{"name":21,"slug":22,"type":15},{"slug":598,"name":598,"fn":599,"description":600,"org":746,"tags":747,"stars":23,"repoUrl":24,"updatedAt":607},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[748,749,750,751],{"name":587,"slug":588,"type":15},{"name":18,"slug":19,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},{"slug":609,"name":609,"fn":610,"description":611,"org":753,"tags":754,"stars":23,"repoUrl":24,"updatedAt":622},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[755,756,757,758],{"name":9,"slug":8,"type":15},{"name":616,"slug":617,"type":15},{"name":21,"slug":22,"type":15},{"name":620,"slug":621,"type":15},{"slug":200,"name":200,"fn":624,"description":625,"org":760,"tags":761,"stars":23,"repoUrl":24,"updatedAt":635},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[762,763,764],{"name":629,"slug":630,"type":15},{"name":632,"slug":633,"type":15},{"name":21,"slug":22,"type":15},{"slug":637,"name":637,"fn":638,"description":639,"org":766,"tags":767,"stars":23,"repoUrl":24,"updatedAt":648},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[768,769,770,771],{"name":590,"slug":591,"type":15},{"name":632,"slug":633,"type":15},{"name":21,"slug":22,"type":15},{"name":646,"slug":647,"type":15},{"slug":650,"name":650,"fn":651,"description":652,"org":773,"tags":774,"stars":23,"repoUrl":24,"updatedAt":660},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[775,776,777],{"name":9,"slug":8,"type":15},{"name":657,"slug":658,"type":15},{"name":21,"slug":22,"type":15},{"slug":662,"name":662,"fn":663,"description":664,"org":779,"tags":780,"stars":23,"repoUrl":24,"updatedAt":678},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[781,782,783,784,785],{"name":9,"slug":8,"type":15},{"name":669,"slug":670,"type":15},{"name":672,"slug":673,"type":15},{"name":675,"slug":676,"type":15},{"name":21,"slug":22,"type":15},18]