celticht32
UserThis is a collection of skills I have created for Couchbase for Claude.ai
Categories
Indexed Skills (29)
cb-analytics-admin
Use this skill when the user wants to inspect or manage the Analytics service's runtime — checking ingestion health, killing runaway queries, restarting nodes, or diagnosing performance. Trigger when they mention "ingestion status", "active queries", "completed requests", "restart service", "cancel request", "service status", or "Analytics health".
cb-analytics-capella
Use this skill when the user wants to manage Couchbase Capella resources through the Cloud Management API — listing organisations and clusters, provisioning or deleting clusters, triggering and restoring backups, or auditing API keys. Trigger when they mention "Capella", "cloud cluster", "capella_*", "organization", "project", "backup", "restore", or the Capella v4 API.
cb-analytics-cluster
Use this skill when the user wants to inspect or configure the Couchbase cluster itself — node membership, memory quotas, rebalance, auto-failover, system events, or just verifying that a cluster is reachable. Trigger when they mention "cluster info", "ping", "rebalance", "auto-failover", "system events", "nodes", "memory quota", or "who_am_i".
cb-analytics-links
Use this skill when the user is managing Analytics data-source links — S3, Azure Blob, GCS, or remote Couchbase links — including creating, updating, listing, or deleting them. Trigger when they mention "S3 link", "Azure Blob", "GCS link", "remote Couchbase link", "external dataset", "data source", "create_link", or credentials for any of those.
cb-analytics-mcp-setup
Use this skill when the user is setting up cb-analytics-mcp from scratch or troubleshooting an existing install — generating secrets, configuring .env, running --check, picking single- vs multi-cluster mode, tuning rate limits, configuring audit rotation, or using the CLI. Trigger when the user mentions "install", "configure", "first run", "MCP_API_KEY", "GUI_PASSWORD", "clusters.json", "cb-analytics-mcp --check", "MAX_QUERY_ROWS", "RATE_LIMIT_", "AUDIT_ROTATE", "tools call", or "tools list".
cb-analytics-query
Use this skill when the user wants to write or improve SQL++ queries against Couchbase Analytics through cb-analytics-mcp. Trigger when they mention "SQL++", "Analytics query", "execute_query", "scan_consistency", "request_plus", "pagination", "EXPLAIN", "truncated", "row cap", or anything about querying datasets, dataverses, joins, aggregations, windowing, query plans, or N1QL/SQL++ language features in this server's context.
cb-analytics-schema
Use this skill when the user wants to inspect, discover, or document the structure of Couchbase Analytics dataverses and datasets — listing what exists, inferring document shapes, or building a data dictionary. Trigger when they mention "schema", "dataverses", "datasets", "what fields are in", "what's the structure of", "infer_schema", or "Metadata.\`Dataverse\`".
cb-analytics-security
Use this skill when the user wants to manage Couchbase users, groups, roles, or check permissions on the cluster — creating service accounts, rotating passwords, granting analytics privileges, or auditing who can do what. Trigger when they mention "user", "group", "role", "RBAC", "permission", "upsert_user", "check_permissions", "local domain", "external domain", or "analytics_reader" / "analytics_admin".
couchbase-ai-applications
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.
couchbase-app-integration
Build application code that integrates with Couchbase. Use whenever the user asks about Couchbase SDKs (Python, Java, Node.js, .NET, Go, C, Ruby, PHP, Scala, Kotlin), connection strings, connection pooling, async vs sync clients, retry strategies, timeout patterns, circuit breakers, durability levels, scan consistency, bulk / batch operations, application-side transactions, the transactions library, idempotency, write conflict handling, active-active XDCR application patterns, error categorization (transient vs durable), TLS / mTLS client setup, certificate handling in clients, or any 'how do I do X in the Couchbase SDK' question. Triggers on application-developer language distinct from couchbase-mcp (server operation), couchbase-data-modeling (database design), and couchbase-sizing (capacity). Use proactively for: integrating a new app, debugging client-side errors, choosing durability for a write, picking the right SDK pattern, handling XDCR conflicts at the application layer.
couchbase-backup-restore
Plan and execute Couchbase backup and restore operations. Use whenever the user asks about backup, restore, cbbackupmgr, backup repository, backup archive, full backup, incremental backup, differential backup, backup schedule, retention policy, backup verification, Capella managed backup, backup to S3, backup to filesystem, restoring a bucket, restoring specific documents, admin_backup_* tools, or 'how do I back up / restore Couchbase.' Distinct from couchbase-migration-execution (one-time data migration to a new cluster) and couchbase-mcp (operating the tools). Use proactively for DR planning, RPO/RTO requirements, backup verification workflows, and pre-upgrade snapshots.
couchbase-capella
Provision, configure, and manage Couchbase Capella deployments. Use whenever the user asks about Capella cluster setup, Capella free tier, Capella trial, creating a Capella cluster, Capella pricing tiers, Capella compute tiers, database credentials, Capella allowed CIDRs, Capella VPC peering, Capella AWS PrivateLink, Azure Private Endpoint, Capella App Services setup, Capella networking, Capella database users vs cluster admin, Capella organizations, Capella projects, Capella connection strings, or 'how do I get started with Capella / set up Capella for production.' Distinct from couchbase-sizing (which has a Capella tier reference) and couchbase-security-hardening (which covers TLS and RBAC). This skill covers Capella as a product — provisioning, networking, credentials, and connecting your application to it.
couchbase-columnar
Design and use Couchbase Capella Columnar, the columnar analytics database service. Use whenever the user asks about Capella Columnar, columnar analytics, Columnar instance, Columnar vs Analytics service, Columnar collections, Columnar links to operational data, Columnar SQL++, Columnar pricing, when to use Columnar vs the 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 Columnar 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.
couchbase-data-modeling
Design document models, choose document boundaries, and pick access patterns for Couchbase. Use whenever the user asks about document model, schema design, key design, document shape, embed vs reference, denormalization, scope vs collection vs bucket, modeling for query / index / FTS / vector search, time-series in Couchbase, TTL strategies, anti-patterns, migrating from SQL / MongoDB / DynamoDB / DocumentDB, or general 'how should I structure this data.' Triggers on design-phase conversations before any tools are called — distinct from the couchbase-mcp skill, which is for operating an existing cluster. Use proactively for: greenfield Couchbase projects, schema migrations, re-architecting an existing model, deciding between scopes/collections/buckets, modeling time-series or vector embeddings, planning denormalization tradeoffs, naming keys, choosing between embedded sub-documents and references.
couchbase-eventing
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.
couchbase-fts
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.
couchbase-kubernetes
Deploy and operate Couchbase on Kubernetes using the Couchbase Autonomous Operator (CAO). Use whenever the user asks about Couchbase Autonomous Operator, CAO, CouchbaseCluster CRD, Couchbase on Kubernetes, Couchbase on EKS, Couchbase on GKE, Couchbase on AKS, Couchbase on OpenShift, Helm chart for Couchbase, CouchbaseBucket CRD, CouchbaseUser CRD, CouchbaseBackup CRD, CouchbaseReplicationRepresentation, server groups in Kubernetes, rack awareness in Kubernetes, persistent volumes for Couchbase, Couchbase pod resources, rolling upgrades via operator, Couchbase operator RBAC, Prometheus with CAO, or 'how do I run Couchbase on Kubernetes.' Distinct from couchbase-capella (managed Capella — no Kubernetes involved) and couchbase-upgrade (server binary upgrades outside Kubernetes). Use proactively when the user has a Kubernetes or OpenShift deployment requirement.
couchbase-magma
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.
couchbase-mcp
Operate Couchbase clusters and Capella v4 through celticht32/MCP-Couchbase (167 tools). 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, server groups, audit, password policy, security settings), RBAC design, troubleshooting Couchbase errors (connection, auth, query, index, replication, eventing, KMIP), operational runbooks (rolling upgrade, add/remove node, post-failover recovery, backup/restore, credential rotation), and observability (monitoring, metrics, Prometheus, alerting, dashboards).
couchbase-migration-execution
Execute data migrations into Couchbase from MongoDB, PostgreSQL, MySQL, Oracle, SQL Server, DynamoDB, Cassandra, files, or custom sources. Use whenever the user asks about migrating, migration strategy, dual-write, change data capture / CDC, Debezium, AWS DMS, big-bang vs phased migration, strangler-fig, cutover, rollback, cbimport, cbexport, cbtransfer, validation after migration, count parity, traffic switching, feature flags during migration, reconciliation between source and target, or 'how do I move my data from X to Couchbase.' Triggers on operational mechanics distinct from couchbase-data-modeling (modeling AFTER migration) — this skill is about actually MOVING the data, keeping source and target in sync during transition, validating equivalence, switching traffic, and rolling back if needed. Use proactively for migration planning, ETL pipeline design, dual-write patterns, CDC tool selection, cutover runbooks, and migration rollback decisions.
couchbase-mobile
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.
couchbase-observability
Monitor, alert on, and observe Couchbase clusters in production. Use whenever the user asks about Couchbase metrics, Prometheus, Grafana, alerting, alert thresholds, memory high watermark, disk usage, replication lag, query latency, index build progress, DCP lag, ops/sec, cache miss ratio, Couchbase Exporter, admin_stats_* tools, log aggregation, SIEM shipping, health checks, or 'how do I know if my Couchbase cluster is healthy.' Distinct from couchbase-mcp (calling the tools) and couchbase-security-hardening (audit log shipping). Use proactively for new production deployments needing an observability stack, incident response setup, and SLO definition.
couchbase-performance-tuning
Diagnose and tune cluster-level performance problems in Couchbase. Use whenever the user asks about slow KV operations, high latency, low throughput, DCP backpressure, connection limits, thread pool tuning, compaction impact on performance, autocompaction settings, KV engine tuning, vBucket distribution, rebalance performance, disk I/O bottlenecks, CPU saturation on Couchbase nodes, network throughput limits, or 'my cluster is healthy but slow.' Distinct from couchbase-sqlpp-tuning (SQL++ query tuning — index design and EXPLAIN plans), couchbase-observability (what metrics to watch), and couchbase-sizing (how much capacity to provision). This skill covers the operational tuning layer: what to change when the cluster is right-sized but still not performing.
couchbase-security-hardening
Harden and audit Couchbase security posture for production deployments. Use whenever the user asks about TLS configuration, mTLS, certificate management, LDAP integration, SAML, PAM authentication, audit logging, audit log configuration, network isolation, firewall rules for Couchbase, RBAC design, least-privilege, password policy, account lockout (8.x), encryption at rest (DARE), KMIP key management, compliance (SOC2, HIPAA, PCI-DSS, FedRAMP), security hardening checklist, admin_encryption_*, admin_kmip_*, or 'how do I secure Couchbase for production.' Distinct from couchbase-mcp (calling the tools) and couchbase-app-integration (TLS in SDK clients). Use proactively for new production deployments, compliance reviews, security audits, and pre-certification hardening.
couchbase-sizing
Size Couchbase clusters, plan capacity, and pick the right Capella tier. Use whenever the user asks about sizing, capacity planning, RAM quota, working set, replicas, node count, scale up vs scale out, how much memory / disk / network is needed, Capella tier selection, GSI / FTS / vector index memory, eventing memory budget, or 'will this fit.' Triggers on numerical planning questions distinct from the couchbase-mcp skill (which operates an existing cluster) and the couchbase-data-modeling skill (which designs document shape). Use proactively for: planning a new deployment, deciding whether to scale up or out, right-sizing a Capella tier, estimating storage growth, planning for burst load, sizing for vector search, calculating XDCR bandwidth, deciding replica count, planning multi-service node mix, estimating eventing memory footprint, and any question that starts with 'how much' or 'how many nodes.'
couchbase-sqlpp-tuning
Diagnose and tune slow Couchbase SQL++ / N1QL queries. Use whenever the user asks about query performance, slow queries, EXPLAIN plans, why an index isn't being used, IntersectScan, PrimaryScan, covering indexes, partial indexes, array indexes (ANY / EVERY / UNNEST), index selection, query hints, the cost-based optimizer, the Index Advisor (ADVISE), system:completed_requests, query profiling (kernTime / servTime / execTime), pagination performance, prepared statements, or 'this query is slow / how do I make it faster.' Distinct from couchbase-data-modeling (document shape) and couchbase-mcp (operating the cluster) — this skill is about reading plans, designing the right indexes, and reshaping queries that already exist. Use proactively when the user shares an EXPLAIN output or a slow query.
couchbase-transactions
Design and implement Couchbase distributed ACID transactions across multiple documents. Use whenever the user asks about transactions, multi-document atomicity, ACID, transaction library, TransactionAttemptContext, commit, rollback, transaction retry, Active Transaction Records (ATRs), transaction expiry, transaction lost write, transaction conflict, transaction performance, cb_transaction_run, or 'how do I atomically update multiple documents.' Distinct from couchbase-app-integration (which covers single-document KV ops, subdocument ops, and has a brief transactions overview) — this skill is for users who need the full depth: designing around transactions, understanding the two-phase commit mechanics, debugging failures, and tuning performance. Use proactively when the user has a use case requiring consistency across multiple documents.
couchbase-upgrade
Plan and execute Couchbase Server version upgrades, including rolling upgrades and the specific considerations for upgrading to 8.0. Use whenever the user asks about upgrading Couchbase, rolling upgrade, upgrade path, upgrade from 7.x to 8.0, upgrade checklist, cluster compatibility version, Magma storage engine default change in 8.0, 128 vBucket change in 8.0, EE features required for 8.0 defaults, pre-upgrade backup, post-upgrade verification, or 'how do I upgrade Couchbase without downtime.' Distinct from couchbase-mcp (which has an operational-runbooks reference covering rolling upgrade mechanics via MCP tools). This skill covers the planning, compatibility, and 8.0-specific breaking changes that require attention before and after the MCP-level upgrade steps.
couchbase-xdcr
Design and operate Couchbase XDCR (Cross-Datacenter Replication). Use whenever the user asks about XDCR, cross-datacenter replication, multi-region replication, active-active replication, active-passive replication, XDCR topology, XDCR references, XDCR replications, XDCR filtering, conflict resolution, last-write-wins, custom conflict resolution, XDCR conflict logging (8.x), admin_xdcr_* tools, replication lag, changes_left, or 'how do I replicate data between clusters / regions.' Distinct from couchbase-app-integration (application-layer XDCR-aware patterns) and couchbase-migration-execution (one-time data migration). Use proactively for disaster recovery planning, multi-region active-active architecture, read-local write-global patterns, and XDCR performance diagnosis.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.