memory-cache
High-performance temporary storage system using Redis. Supports namespaced keys (mema:*), TTL management, and session context caching. Use for: (1) Saving agent state, (2) Caching API results, (3) Sharing data between sub-agents.
azure-resource-manager-redis-dotnet
Azure Resource Manager SDK for Redis in .NET. Use for MANAGEMENT PLANE operations: creating/managing Azure Cache for Redis instances, firewall rules, access keys, patch schedules, linked servers (geo-replication), and private endpoints via Azure Resource Manager. NOT for data plane operations (ge...
mongodb-mean
MongoDB database architecture for MEAN stack apps. Use when designing collections, schemas, indexes, relationships, and data modeling with Mongoose ODM.
elasticsearch-expert
Use this skill when working with Elasticsearch in any capacity — designing index mappings, writing or optimizing queries (Query DSL, ES|QL, KQL), planning cluster architecture, configuring ingest pipelines, tuning performance, troubleshooting cluster health, implementing search features, or building AI-powered search with retrievers. Also activate for Elasticsearch security tasks — authentication, RBAC, API key management, audit logging, DLS/FLS, or security troubleshooting. Activate whenever the user mentions Elasticsearch, OpenSearch, Elastic Stack, Kibana queries, Lucene-based search, vector/semantic/hybrid search with Elasticsearch, retrievers, LogsDB, TSDB, Elasticsearch Serverless, ES|QL CATEGORIZE/CHANGE_POINT, or any index/shard/mapping/analyzer/security topic.
data-layer
Working with OpenBench data layer - vector stores, chunking, embeddings, and RAG patterns. Use when implementing PineconeStore, chunking documents, generating embeddings, or building RAG workflows.
filtered-search
Use when user needs vector search with scalar field filtering. Triggers on: filtered search, filter by category, metadata filter, faceted search, conditional search, attribute filtering, search with constraints.
mongodb-mongoose
MongoDB with Mongoose — schemas, models, aggregation pipelines, migrations, and Atlas connections. Use when designing collections, writing queries, or integrating MongoDB into Node.js/Next.js apps.
memory-cache
High-performance temporary storage system using Redis. Supports namespaced keys (mema:*), TTL management, and session context caching. Use for: (1) Saving agent state, (2) Caching API results, (3) Sharing data between sub-agents.
cems-remember
Store memories with project context, categories, and tags into CEMS long-term memory
cems-foundation
View foundation guidelines (rules, principles, constraints) stored in CEMS memory
tm-generate-mongo
根据 MongoDB 集合信息生成 TM（表模型）文件。当用户需要为 MongoDB 集合创建数据模型、生成 mongo 类型的 .tm 文件时使用。
redis-caching-queues
Redis patterns, caching strategies, and Laravel Horizon / Python task queues.
redis-expert
Use when implementing redis functionality with production-grade patterns and safeguards.
redis-caching
Redis data structures, caching patterns, pub/sub, Lua scripting, and cluster configuration. Trigger for Redis usage patterns, caching strategies, or Redis-specific optimization.
