[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-algolia-algolia-index-configuration":3,"mdc-jjw5js-key":39,"related-org-algolia-algolia-index-configuration":543,"related-repo-algolia-algolia-index-configuration":711},{"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-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},"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},"Configuration","configuration","tag",{"name":9,"slug":8,"type":15},{"name":18,"slug":19,"type":15},"Data Modeling","data-modeling",{"name":21,"slug":22,"type":15},"Search","search",8,"https:\u002F\u002Fgithub.com\u002Falgolia\u002Fskills","2026-08-01T06:06:34.19163","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-index-configuration","---\nname: algolia-index-configuration\ndescription: >\n  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.\nlicense: MIT\nmetadata:\n  author: algolia\n  version: \"0.3\"\n---\n\n# Algolia Index Configuration\n\nUse this skill when changing how Algolia ranks, filters, facets, merchandises, or sorts results. Relevance configuration should reflect the business outcome and the user's decision path.\n\n## Customer-Facing Standard\n\n- Capture the current settings or assumptions before recommending changes.\n- Tie every setting change to a business goal and representative query set.\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 settings, expected tradeoffs, rollback notes, and validation queries.\n- Produce a settings decision record that distinguishes deterministic constraints, ranking preferences, and query-specific merchandising.\n\n## Official Companion Skills\n\n- Use official `algolia-cli` for live settings, rules, synonyms, replicas, backups, or configuration changes.\n- Use official `algolia-mcp` for live search behavior, analytics, top searches, no-result queries, click positions, and recommendation evidence.\n- Use official A\u002FB testing guidance or tools when an experiment is in scope; keep this skill focused on hypothesis, evidence, decision criteria, and rollback.\n- Use this skill after the official tool call to explain tradeoffs, test queries, rollback expectations, and customer-facing validation criteria.\n\n## Source-Of-Truth Rules\n\n- Do not change or recommend live settings without first capturing the current settings or stating that the plan is provisional.\n- Use official `algolia-cli` for settings, rules, synonyms, replicas, and backups; use this skill to design and explain the change.\n- Verify current docs or official skill guidance before relying on feature behavior such as replicas, virtual replicas, rules, optional filters, or A\u002FB testing.\n\n## Workflow\n\n1. Read `references\u002Fconfiguration-guide.md` before editing settings.\n2. Capture current settings before modifying an existing index.\n3. Ask what good results mean for the use case: exactness, availability, popularity, margin, recency, location, personalization, editorial priority, or diversity.\n4. Classify each relevance lever: deterministic filter, textual match priority, tie-breaker, optional preference, query-specific rule, or explicit sort.\n5. Make the smallest coherent settings change and describe expected tradeoffs.\n6. Validate with representative queries, facet\u002Ffilter combinations, query rules, sorts, and no-result cases.\n7. For material changes, write the hypothesis, baseline, success metric, experiment decision rule, and rollback trigger before launch.\n\n## Questions To Ask\n\n- Which queries or browse pages are most valuable or currently broken?\n- Which attributes should match first, and which should only help recall?\n- Which business metrics should break textual ties?\n- Which filters must be available to users, and which filters are applied silently?\n- Do sort orders need replicas, and are those sort orders allowed to weaken relevance?\n- Are synonyms and rules global, seasonal, category-specific, or campaign-specific?\n- Which constraints are non-negotiable filters, and which are preferences that can rank lower but still return results?\n- Which terms need typo protection or exact treatment, such as SKUs, part numbers, acronyms, postal codes, or regulated names?\n\n## Implementation Standards\n\n- Prefer ordered `searchableAttributes` that reflect the user's mental model.\n- Put numeric or boolean business signals in `customRanking`, not in frontend sort hacks.\n- Declare only needed `attributesForFaceting`; use searchable facets where users search inside facets.\n- Treat synonyms and rules as governed relevance assets. Name, scope, and test them.\n- Use replicas for explicit sort-by experiences and virtual replicas where relevant sorting fits the use case.\n- Avoid irreversible production changes without a settings backup or repeatable configuration file.\n- Keep deterministic constraints in filters or secured filters. Use optional filters only when a result may still be relevant without the preference.\n- Treat facet configuration as a user decision contract: declare only attributes users need to refine, choose searchable facets only when users search within values, and test counts after common refinements.\n- Use synonyms for genuine language equivalence. Use rules for bounded intent, promotions, redirects, or merchandising with a condition, owner, and review\u002Fexpiry date.\n- Protect identifiers and exact-sensitive terms with current documented typo settings rather than weakening all search behavior.\n- Treat every sort choice as a relevance decision. Document the replica type, displayed sort label, expected loss of relevance, and whether filters\u002Ffacets remain consistent.\n- Change one meaningful relevance variable per experiment. Do not infer causality when ranking, rules, data, and UI changed together.\n\n## Anti-Patterns\n\n- Tuning relevance with one anecdotal query instead of a representative query set.\n- Using synonyms to compensate for missing data or unrelated concepts.\n- Pinning or burying results globally when the intent is category, campaign, locale, or segment-specific.\n- Adding every possible facet, which slows decision-making and creates noisy filters.\n- Letting custom ranking overpower exact-match or permission-sensitive behavior without testing.\n- Using optional filters to enforce availability, permission, region, or compliance constraints that must never be violated.\n- Using synonyms where a scoped rule, data correction, or typo exception is the real solution.\n- Interpreting an A\u002FB test before sufficient event-backed data and confidence exist, or stopping and restarting a test as if it were continuous.\n\n## Academy And Customer Education Alignment\n\nWhen source-backed guidance is needed, search public Academy sources for relevance learning objectives and public Algolia docs for searchable attributes, ranking, facets, synonyms, rules, replicas, merchandising, and A\u002FB testing. Map the work to maturity level and use case, then turn source guidance into questions, test queries, and validation criteria rather than copied reference text.\n\n## Maturity Behavior\n\n- Beginner implementation: define the first coherent searchable attributes, facets, and ranking signals from the customer journey.\n- Production readiness: capture settings backup, deterministic-versus-optional filter decisions, representative query set, rollback notes, secured filters, and launch-impact checks.\n- Optimization: require baseline queries, analytics signals, one-variable A\u002FB-test plan, merchandising scope, confidence interpretation, and expected before\u002Fafter behavior.\n- AI readiness: preserve deterministic filters, secured data, business rules, and measurement while validating NeuralSearch or Agent Studio dependencies.\n\n## Output Contract\n\nReturn settings changes as code or JSON, a settings decision record, relevance intent, test queries, and assumptions requiring business review. Include before\u002Fafter expectations for top queries, hard\u002Foptional constraint behavior, experiment criteria, and rollback triggers when relevance changes are material.\n",{"data":40,"body":43},{"name":4,"description":6,"license":26,"metadata":41},{"author":8,"version":42},"0.3",{"type":44,"children":45},"root",[46,54,60,67,174,180,218,224,248,254,301,307,350,356,443,449,492,498,503,509,532,538],{"type":47,"tag":48,"props":49,"children":50},"element","h1",{"id":4},[51],{"type":52,"value":53},"text","Algolia Index Configuration",{"type":47,"tag":55,"props":56,"children":57},"p",{},[58],{"type":52,"value":59},"Use this skill when changing how Algolia ranks, filters, facets, merchandises, or sorts results. Relevance configuration should reflect the business outcome and the user's decision path.",{"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",{},[71,77,82,104,154,159,164,169],{"type":47,"tag":72,"props":73,"children":74},"li",{},[75],{"type":52,"value":76},"Capture the current settings or assumptions before recommending changes.",{"type":47,"tag":72,"props":78,"children":79},{},[80],{"type":52,"value":81},"Tie every setting change to a business goal and representative query set.",{"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 settings, expected tradeoffs, rollback notes, and validation queries.",{"type":47,"tag":72,"props":170,"children":171},{},[172],{"type":52,"value":173},"Produce a settings decision record that distinguishes deterministic constraints, ranking preferences, and query-specific merchandising.",{"type":47,"tag":61,"props":175,"children":177},{"id":176},"official-companion-skills",[178],{"type":52,"value":179},"Official Companion Skills",{"type":47,"tag":68,"props":181,"children":182},{},[183,196,208,213],{"type":47,"tag":72,"props":184,"children":185},{},[186,188,194],{"type":52,"value":187},"Use official ",{"type":47,"tag":88,"props":189,"children":191},{"className":190},[],[192],{"type":52,"value":193},"algolia-cli",{"type":52,"value":195}," for live settings, rules, synonyms, replicas, backups, or configuration changes.",{"type":47,"tag":72,"props":197,"children":198},{},[199,200,206],{"type":52,"value":187},{"type":47,"tag":88,"props":201,"children":203},{"className":202},[],[204],{"type":52,"value":205},"algolia-mcp",{"type":52,"value":207}," for live search behavior, analytics, top searches, no-result queries, click positions, and recommendation evidence.",{"type":47,"tag":72,"props":209,"children":210},{},[211],{"type":52,"value":212},"Use official A\u002FB testing guidance or tools when an experiment is in scope; keep this skill focused on hypothesis, evidence, decision criteria, and rollback.",{"type":47,"tag":72,"props":214,"children":215},{},[216],{"type":52,"value":217},"Use this skill after the official tool call to explain tradeoffs, test queries, rollback expectations, and customer-facing validation criteria.",{"type":47,"tag":61,"props":219,"children":221},{"id":220},"source-of-truth-rules",[222],{"type":52,"value":223},"Source-Of-Truth Rules",{"type":47,"tag":68,"props":225,"children":226},{},[227,232,243],{"type":47,"tag":72,"props":228,"children":229},{},[230],{"type":52,"value":231},"Do not change or recommend live settings without first capturing the current settings or stating that the plan is provisional.",{"type":47,"tag":72,"props":233,"children":234},{},[235,236,241],{"type":52,"value":187},{"type":47,"tag":88,"props":237,"children":239},{"className":238},[],[240],{"type":52,"value":193},{"type":52,"value":242}," for settings, rules, synonyms, replicas, and backups; use this skill to design and explain the change.",{"type":47,"tag":72,"props":244,"children":245},{},[246],{"type":52,"value":247},"Verify current docs or official skill guidance before relying on feature behavior such as replicas, virtual replicas, rules, optional filters, or A\u002FB testing.",{"type":47,"tag":61,"props":249,"children":251},{"id":250},"workflow",[252],{"type":52,"value":253},"Workflow",{"type":47,"tag":255,"props":256,"children":257},"ol",{},[258,271,276,281,286,291,296],{"type":47,"tag":72,"props":259,"children":260},{},[261,263,269],{"type":52,"value":262},"Read ",{"type":47,"tag":88,"props":264,"children":266},{"className":265},[],[267],{"type":52,"value":268},"references\u002Fconfiguration-guide.md",{"type":52,"value":270}," before editing settings.",{"type":47,"tag":72,"props":272,"children":273},{},[274],{"type":52,"value":275},"Capture current settings before modifying an existing index.",{"type":47,"tag":72,"props":277,"children":278},{},[279],{"type":52,"value":280},"Ask what good results mean for the use case: exactness, availability, popularity, margin, recency, location, personalization, editorial priority, or diversity.",{"type":47,"tag":72,"props":282,"children":283},{},[284],{"type":52,"value":285},"Classify each relevance lever: deterministic filter, textual match priority, tie-breaker, optional preference, query-specific rule, or explicit sort.",{"type":47,"tag":72,"props":287,"children":288},{},[289],{"type":52,"value":290},"Make the smallest coherent settings change and describe expected tradeoffs.",{"type":47,"tag":72,"props":292,"children":293},{},[294],{"type":52,"value":295},"Validate with representative queries, facet\u002Ffilter combinations, query rules, sorts, and no-result cases.",{"type":47,"tag":72,"props":297,"children":298},{},[299],{"type":52,"value":300},"For material changes, write the hypothesis, baseline, success metric, experiment decision rule, and rollback trigger before launch.",{"type":47,"tag":61,"props":302,"children":304},{"id":303},"questions-to-ask",[305],{"type":52,"value":306},"Questions To Ask",{"type":47,"tag":68,"props":308,"children":309},{},[310,315,320,325,330,335,340,345],{"type":47,"tag":72,"props":311,"children":312},{},[313],{"type":52,"value":314},"Which queries or browse pages are most valuable or currently broken?",{"type":47,"tag":72,"props":316,"children":317},{},[318],{"type":52,"value":319},"Which attributes should match first, and which should only help recall?",{"type":47,"tag":72,"props":321,"children":322},{},[323],{"type":52,"value":324},"Which business metrics should break textual ties?",{"type":47,"tag":72,"props":326,"children":327},{},[328],{"type":52,"value":329},"Which filters must be available to users, and which filters are applied silently?",{"type":47,"tag":72,"props":331,"children":332},{},[333],{"type":52,"value":334},"Do sort orders need replicas, and are those sort orders allowed to weaken relevance?",{"type":47,"tag":72,"props":336,"children":337},{},[338],{"type":52,"value":339},"Are synonyms and rules global, seasonal, category-specific, or campaign-specific?",{"type":47,"tag":72,"props":341,"children":342},{},[343],{"type":52,"value":344},"Which constraints are non-negotiable filters, and which are preferences that can rank lower but still return results?",{"type":47,"tag":72,"props":346,"children":347},{},[348],{"type":52,"value":349},"Which terms need typo protection or exact treatment, such as SKUs, part numbers, acronyms, postal codes, or regulated names?",{"type":47,"tag":61,"props":351,"children":353},{"id":352},"implementation-standards",[354],{"type":52,"value":355},"Implementation Standards",{"type":47,"tag":68,"props":357,"children":358},{},[359,372,385,398,403,408,413,418,423,428,433,438],{"type":47,"tag":72,"props":360,"children":361},{},[362,364,370],{"type":52,"value":363},"Prefer ordered ",{"type":47,"tag":88,"props":365,"children":367},{"className":366},[],[368],{"type":52,"value":369},"searchableAttributes",{"type":52,"value":371}," that reflect the user's mental model.",{"type":47,"tag":72,"props":373,"children":374},{},[375,377,383],{"type":52,"value":376},"Put numeric or boolean business signals in ",{"type":47,"tag":88,"props":378,"children":380},{"className":379},[],[381],{"type":52,"value":382},"customRanking",{"type":52,"value":384},", not in frontend sort hacks.",{"type":47,"tag":72,"props":386,"children":387},{},[388,390,396],{"type":52,"value":389},"Declare only needed ",{"type":47,"tag":88,"props":391,"children":393},{"className":392},[],[394],{"type":52,"value":395},"attributesForFaceting",{"type":52,"value":397},"; use searchable facets where users search inside facets.",{"type":47,"tag":72,"props":399,"children":400},{},[401],{"type":52,"value":402},"Treat synonyms and rules as governed relevance assets. Name, scope, and test them.",{"type":47,"tag":72,"props":404,"children":405},{},[406],{"type":52,"value":407},"Use replicas for explicit sort-by experiences and virtual replicas where relevant sorting fits the use case.",{"type":47,"tag":72,"props":409,"children":410},{},[411],{"type":52,"value":412},"Avoid irreversible production changes without a settings backup or repeatable configuration file.",{"type":47,"tag":72,"props":414,"children":415},{},[416],{"type":52,"value":417},"Keep deterministic constraints in filters or secured filters. Use optional filters only when a result may still be relevant without the preference.",{"type":47,"tag":72,"props":419,"children":420},{},[421],{"type":52,"value":422},"Treat facet configuration as a user decision contract: declare only attributes users need to refine, choose searchable facets only when users search within values, and test counts after common refinements.",{"type":47,"tag":72,"props":424,"children":425},{},[426],{"type":52,"value":427},"Use synonyms for genuine language equivalence. Use rules for bounded intent, promotions, redirects, or merchandising with a condition, owner, and review\u002Fexpiry date.",{"type":47,"tag":72,"props":429,"children":430},{},[431],{"type":52,"value":432},"Protect identifiers and exact-sensitive terms with current documented typo settings rather than weakening all search behavior.",{"type":47,"tag":72,"props":434,"children":435},{},[436],{"type":52,"value":437},"Treat every sort choice as a relevance decision. Document the replica type, displayed sort label, expected loss of relevance, and whether filters\u002Ffacets remain consistent.",{"type":47,"tag":72,"props":439,"children":440},{},[441],{"type":52,"value":442},"Change one meaningful relevance variable per experiment. Do not infer causality when ranking, rules, data, and UI changed together.",{"type":47,"tag":61,"props":444,"children":446},{"id":445},"anti-patterns",[447],{"type":52,"value":448},"Anti-Patterns",{"type":47,"tag":68,"props":450,"children":451},{},[452,457,462,467,472,477,482,487],{"type":47,"tag":72,"props":453,"children":454},{},[455],{"type":52,"value":456},"Tuning relevance with one anecdotal query instead of a representative query set.",{"type":47,"tag":72,"props":458,"children":459},{},[460],{"type":52,"value":461},"Using synonyms to compensate for missing data or unrelated concepts.",{"type":47,"tag":72,"props":463,"children":464},{},[465],{"type":52,"value":466},"Pinning or burying results globally when the intent is category, campaign, locale, or segment-specific.",{"type":47,"tag":72,"props":468,"children":469},{},[470],{"type":52,"value":471},"Adding every possible facet, which slows decision-making and creates noisy filters.",{"type":47,"tag":72,"props":473,"children":474},{},[475],{"type":52,"value":476},"Letting custom ranking overpower exact-match or permission-sensitive behavior without testing.",{"type":47,"tag":72,"props":478,"children":479},{},[480],{"type":52,"value":481},"Using optional filters to enforce availability, permission, region, or compliance constraints that must never be violated.",{"type":47,"tag":72,"props":483,"children":484},{},[485],{"type":52,"value":486},"Using synonyms where a scoped rule, data correction, or typo exception is the real solution.",{"type":47,"tag":72,"props":488,"children":489},{},[490],{"type":52,"value":491},"Interpreting an A\u002FB test before sufficient event-backed data and confidence exist, or stopping and restarting a test as if it were continuous.",{"type":47,"tag":61,"props":493,"children":495},{"id":494},"academy-and-customer-education-alignment",[496],{"type":52,"value":497},"Academy And Customer Education Alignment",{"type":47,"tag":55,"props":499,"children":500},{},[501],{"type":52,"value":502},"When source-backed guidance is needed, search public Academy sources for relevance learning objectives and public Algolia docs for searchable attributes, ranking, facets, synonyms, rules, replicas, merchandising, and A\u002FB testing. Map the work to maturity level and use case, then turn source guidance into questions, test queries, and validation criteria rather than copied reference text.",{"type":47,"tag":61,"props":504,"children":506},{"id":505},"maturity-behavior",[507],{"type":52,"value":508},"Maturity Behavior",{"type":47,"tag":68,"props":510,"children":511},{},[512,517,522,527],{"type":47,"tag":72,"props":513,"children":514},{},[515],{"type":52,"value":516},"Beginner implementation: define the first coherent searchable attributes, facets, and ranking signals from the customer journey.",{"type":47,"tag":72,"props":518,"children":519},{},[520],{"type":52,"value":521},"Production readiness: capture settings backup, deterministic-versus-optional filter decisions, representative query set, rollback notes, secured filters, and launch-impact checks.",{"type":47,"tag":72,"props":523,"children":524},{},[525],{"type":52,"value":526},"Optimization: require baseline queries, analytics signals, one-variable A\u002FB-test plan, merchandising scope, confidence interpretation, and expected before\u002Fafter behavior.",{"type":47,"tag":72,"props":528,"children":529},{},[530],{"type":52,"value":531},"AI readiness: preserve deterministic filters, secured data, business rules, and measurement while validating NeuralSearch or Agent Studio dependencies.",{"type":47,"tag":61,"props":533,"children":535},{"id":534},"output-contract",[536],{"type":52,"value":537},"Output Contract",{"type":47,"tag":55,"props":539,"children":540},{},[541],{"type":52,"value":542},"Return settings changes as code or JSON, a settings decision record, relevance intent, test queries, and assumptions requiring business review. Include before\u002Fafter expectations for top queries, hard\u002Foptional constraint behavior, experiment criteria, and rollback triggers when relevance changes are material.",{"items":544,"total":710},[545,561,578,591,606,619,632,642,658,669,676,698],{"slug":546,"name":546,"fn":547,"description":548,"org":549,"tags":550,"stars":558,"repoUrl":559,"updatedAt":560},"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},[551,552,555,557],{"name":9,"slug":8,"type":15},{"name":553,"slug":554,"type":15},"Documentation","documentation",{"name":556,"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":562,"name":562,"fn":563,"description":564,"org":565,"tags":566,"stars":23,"repoUrl":24,"updatedAt":577},"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},[567,570,573,576],{"name":568,"slug":569,"type":15},"Agents","agents",{"name":571,"slug":572,"type":15},"Automation","automation",{"name":574,"slug":575,"type":15},"LLM","llm",{"name":21,"slug":22,"type":15},"2026-07-12T08:27:37.649724",{"slug":579,"name":579,"fn":580,"description":581,"org":582,"tags":583,"stars":23,"repoUrl":24,"updatedAt":590},"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},[584,585,588,589],{"name":568,"slug":569,"type":15},{"name":586,"slug":587,"type":15},"AI","ai",{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},"2026-08-01T06:06:28.033767",{"slug":592,"name":592,"fn":593,"description":594,"org":595,"tags":596,"stars":23,"repoUrl":24,"updatedAt":605},"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},[597,598,601,602],{"name":9,"slug":8,"type":15},{"name":599,"slug":600,"type":15},"Frontend","frontend",{"name":21,"slug":22,"type":15},{"name":603,"slug":604,"type":15},"UI Components","ui-components","2026-08-01T06:06:29.968123",{"slug":193,"name":193,"fn":607,"description":608,"org":609,"tags":610,"stars":23,"repoUrl":24,"updatedAt":618},"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},[611,614,617],{"name":612,"slug":613,"type":15},"CLI","cli",{"name":615,"slug":616,"type":15},"Data Engineering","data-engineering",{"name":21,"slug":22,"type":15},"2026-07-12T08:27:35.085246",{"slug":620,"name":620,"fn":621,"description":622,"org":623,"tags":624,"stars":23,"repoUrl":24,"updatedAt":631},"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},[625,626,627,628],{"name":571,"slug":572,"type":15},{"name":615,"slug":616,"type":15},{"name":21,"slug":22,"type":15},{"name":629,"slug":630,"type":15},"Web Scraping","web-scraping","2026-07-12T08:27:40.981109",{"slug":633,"name":633,"fn":634,"description":635,"org":636,"tags":637,"stars":23,"repoUrl":24,"updatedAt":641},"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},[638,639,640],{"name":9,"slug":8,"type":15},{"name":18,"slug":19,"type":15},{"name":21,"slug":22,"type":15},"2026-08-01T06:06:01.500756",{"slug":643,"name":643,"fn":644,"description":645,"org":646,"tags":647,"stars":23,"repoUrl":24,"updatedAt":657},"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},[648,649,652,653,656],{"name":9,"slug":8,"type":15},{"name":650,"slug":651,"type":15},"Analytics","analytics",{"name":13,"slug":14,"type":15},{"name":654,"slug":655,"type":15},"Personalization","personalization",{"name":21,"slug":22,"type":15},"2026-08-01T06:06:03.021452",{"slug":659,"name":659,"fn":660,"description":661,"org":662,"tags":663,"stars":23,"repoUrl":24,"updatedAt":668},"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},[664,665,666,667],{"name":9,"slug":8,"type":15},{"name":650,"slug":651,"type":15},{"name":654,"slug":655,"type":15},{"name":21,"slug":22,"type":15},"2026-08-01T06:06:02.009712",{"slug":4,"name":4,"fn":5,"description":6,"org":670,"tags":671,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[672,673,674,675],{"name":9,"slug":8,"type":15},{"name":13,"slug":14,"type":15},{"name":18,"slug":19,"type":15},{"name":21,"slug":22,"type":15},{"slug":677,"name":677,"fn":678,"description":679,"org":680,"tags":681,"stars":23,"repoUrl":24,"updatedAt":697},"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},[682,683,686,687,690,693,694],{"name":9,"slug":8,"type":15},{"name":684,"slug":685,"type":15},"Angular","angular",{"name":599,"slug":600,"type":15},{"name":688,"slug":689,"type":15},"JavaScript","javascript",{"name":691,"slug":692,"type":15},"React","react",{"name":21,"slug":22,"type":15},{"name":695,"slug":696,"type":15},"Vue","vue","2026-08-01T06:06:33.66513",{"slug":205,"name":205,"fn":699,"description":700,"org":701,"tags":702,"stars":23,"repoUrl":24,"updatedAt":709},"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},[703,704,707,708],{"name":650,"slug":651,"type":15},{"name":705,"slug":706,"type":15},"API Development","api-development",{"name":556,"slug":31,"type":15},{"name":21,"slug":22,"type":15},"2026-07-12T08:27:36.376387",19,{"items":712,"total":761},[713,720,727,734,740,747,753],{"slug":562,"name":562,"fn":563,"description":564,"org":714,"tags":715,"stars":23,"repoUrl":24,"updatedAt":577},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[716,717,718,719],{"name":568,"slug":569,"type":15},{"name":571,"slug":572,"type":15},{"name":574,"slug":575,"type":15},{"name":21,"slug":22,"type":15},{"slug":579,"name":579,"fn":580,"description":581,"org":721,"tags":722,"stars":23,"repoUrl":24,"updatedAt":590},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[723,724,725,726],{"name":568,"slug":569,"type":15},{"name":586,"slug":587,"type":15},{"name":9,"slug":8,"type":15},{"name":21,"slug":22,"type":15},{"slug":592,"name":592,"fn":593,"description":594,"org":728,"tags":729,"stars":23,"repoUrl":24,"updatedAt":605},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[730,731,732,733],{"name":9,"slug":8,"type":15},{"name":599,"slug":600,"type":15},{"name":21,"slug":22,"type":15},{"name":603,"slug":604,"type":15},{"slug":193,"name":193,"fn":607,"description":608,"org":735,"tags":736,"stars":23,"repoUrl":24,"updatedAt":618},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[737,738,739],{"name":612,"slug":613,"type":15},{"name":615,"slug":616,"type":15},{"name":21,"slug":22,"type":15},{"slug":620,"name":620,"fn":621,"description":622,"org":741,"tags":742,"stars":23,"repoUrl":24,"updatedAt":631},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[743,744,745,746],{"name":571,"slug":572,"type":15},{"name":615,"slug":616,"type":15},{"name":21,"slug":22,"type":15},{"name":629,"slug":630,"type":15},{"slug":633,"name":633,"fn":634,"description":635,"org":748,"tags":749,"stars":23,"repoUrl":24,"updatedAt":641},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[750,751,752],{"name":9,"slug":8,"type":15},{"name":18,"slug":19,"type":15},{"name":21,"slug":22,"type":15},{"slug":643,"name":643,"fn":644,"description":645,"org":754,"tags":755,"stars":23,"repoUrl":24,"updatedAt":657},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[756,757,758,759,760],{"name":9,"slug":8,"type":15},{"name":650,"slug":651,"type":15},{"name":13,"slug":14,"type":15},{"name":654,"slug":655,"type":15},{"name":21,"slug":22,"type":15},18]