Design and build AI-powered applications on Couchbase, including RAG pipelines, vector search architecture, embedding strategies, and AI agent data patterns. Use whenever the user asks about RAG, retrieval-augmented generation, vector search for AI, Hyperscale Vector Index (HVI), Composite Vector Index (CVI), Search Vector Index (SVI), embedding pipelines, semantic search, AI agent memory, grounding LLMs with Couchbase, agentic data patterns, billion-scale vector search, multi-vector search, AI application architecture, or 'how do I build an AI app with Couchbase.' Distinct from couchbase-fts (which covers FTS index mechanics and query syntax) — this skill is about end-to-end AI application design: the data model, embedding pipeline, index type selection, retrieval strategy, and integration with LLM frameworks. Use proactively when the user is building AI features or has a use case involving language models, embeddings, or semantic retrieval.
Apply coding standards and a style guide for writing production application code against Couchbase, combining general software-engineering best practices (naming, functions, error handling, testing, docstrings, version control, code review, secrets hygiene) with Couchbase-specific conventions (SDK idioms, document-key naming, exception and retry handling, durability, parameterized SQL++, connection lifecycle). Use whenever the user asks about coding standards, code style, a style guide, clean code, naming conventions, structuring Couchbase application code, idiomatic SDK usage, how to write or review Couchbase code, code-review checklists, linting, formatting, testing Couchbase code, or best practices for writing Couchbase apps. Distinct from couchbase-app-integration (SDK mechanics: pooling, durability, scan consistency) and couchbase-data-modeling (document design) — this is the how-to-write-and-review-the-code layer on top of them. Use proactively when reviewing or authoring code that touches Couchbase.
Design and use Couchbase Capella Analytics (formerly Capella Columnar), the standalone columnar analytics database service on Capella. Use whenever the user asks about Capella Analytics, Capella Columnar, columnar analytics, an Analytics instance, Capella Analytics vs the operational Analytics Service, Analytics collections, links to operational data, Analytics SQL++, pricing, when to use standalone Capella Analytics vs the embedded Analytics Service, or 'I need to run analytical queries on my Couchbase data.' Distinct from the cb-analytics-* skills (which cover the Couchbase Analytics Service embedded in Couchbase Server / Capella operational clusters) — Capella Analytics is a separate, standalone columnar database product on Capella. Use proactively when the user needs OLAP-scale analytics, BI tool integration, or columnar storage for analytical workloads.
Design, deploy, and troubleshoot Couchbase Eventing functions. Use whenever the user asks about Eventing, eventing functions, JavaScript functions on document mutations, source bucket, metadata bucket, source keyspace, metadata keyspace, OnUpdate, OnDelete, cron triggers, curl() in eventing, N1QL in eventing, eventing deployment state (deployed / undeployed / paused), eventing worker count, DCP feed, Eventing service, admin_eventing_* tools, or 'how do I run code when a document changes.' Distinct from couchbase-mcp (calling the tools) and couchbase-app-integration (SDK-based change notification via DCP/Kafka). Use proactively when the user has a change-driven processing need: cache warming, audit logging, cross-collection sync, event publishing, or derived document generation.
Design, build, and tune Couchbase Full Text Search (FTS) and vector search indexes. Use whenever the user asks about FTS indexes, Search service, text search, full-text search, fuzzy search, phrase search, wildcard search, regex search, geo search, geo-distance, geo-bounding-box, facets, scoring, boosting, analyzers, tokenizers, custom analyzers, language analyzers, type mappings, dynamic mappings, child mappings, FTS index design, FTS synonyms (8.x), vector search, kNN search, vector index, embedding search, hybrid search (FTS + vector), cb_fts_search, admin_fts_*, BLEVE, or 'how do I search text in Couchbase.' Distinct from couchbase-sqlpp-tuning (SQL++ index design) and couchbase-mcp (operating the tools). Use proactively when the user has a search use case — text relevance, semantic similarity, geo-proximity, or faceted navigation.
Understand and tune the Magma storage engine in Couchbase. Use whenever the user asks about Magma, Magma storage engine, Couchbase storage backend, couchstore vs Magma, 128 vBuckets vs 1024 vBuckets, Magma compaction, Magma memory requirements, Magma disk layout, storage engine selection, when to use Magma vs couchstore, storageBackend bucket setting, numVBuckets bucket setting, or 'which storage engine should I use.' Distinct from couchbase-sizing (which has a brief Magma section in disk.md) — this skill covers Magma behavior, tradeoffs, and tuning in depth. Use proactively when the user is creating new buckets on 8.0 or is investigating storage-related performance issues.
Operate Couchbase clusters and Capella v4 through an MCP server. Primary target is celticht32/MCP-Couchbase (167 tools) for full data-plane AND cluster admin; also covers the official Couchbase-Ecosystem/mcp-server-couchbase (narrower, data-plane-only, community-maintained, enterprise-supported via AI Data Plane license) and when to pick which. Use whenever the user mentions Couchbase, buckets, scopes, collections, SQL++ / N1QL, KV ops, subdocument ops, FTS, vector indexes, XDCR, eventing, backup, encryption / KMIP / DARE, user lock/unlock, query performance, Index Advisor, synonyms (8.x), or Capella organizations / projects / clusters / database users / allowed CIDRs / app services. Use proactively for cluster admin (rebalance, failover, recovery, autofailover, autocompaction, logs, alerts, audit, password policy), RBAC design, troubleshooting Couchbase errors, operational runbooks (rolling upgrade, node add/remove, post-failover recovery, backup/restore, credential rotation), and observability.
Design and build mobile, edge, and offline-first applications with Couchbase Lite, Sync Gateway, and Capella App Services. Use whenever the user asks about Couchbase Lite, Sync Gateway, App Services, offline-first, mobile sync, data replication to mobile, Couchbase Lite database, replicator, push/pull replication, sync function, channel access, user authentication in mobile, conflict resolution in mobile, iOS Couchbase, Android Couchbase, React Native Couchbase, Xamarin Couchbase, .NET MAUI Couchbase, peer-to-peer sync, edge database, Couchbase Lite vector search, or 'how do I sync data to mobile apps.' Distinct from couchbase-xdcr (server-to-server replication) and couchbase-app-integration (server-side SDKs). Use proactively when the user has a mobile, IoT, field worker, or offline-capable application requirement.