Author or review a Drizzle DB migration for zero-downtime safety — expand/contract phasing, backward-compatibility with the deployed app…
JPA/Hibernate patterns for entity design, relationships, query optimization, transactions, auditing, indexing, pagination, and pooling in…
Managed vector DB for production RAG and search.
Vector search engine for production RAG systems.
Track and inspect graph changes, diffs, temporal updates, and the impact of new data on Semantica knowledge graphs.
Ingest data from files, databases, APIs, or streams into Semantica knowledge graphs with schema mapping and entity linking.
Query the Semantica knowledge graph using SPARQL, Cypher, keyword search, and structured graph query patterns.
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist
Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements.
Use when working with KDB-X Python for Python-to-q data conversion, querying tables with Column API, IPC connections, DB management, or…
When to activate: Exposed ORM, Kotlin SQL, DSL query, DAO pattern, Exposed transactions, type-safe queries, database migrations
Installs and configures ktx, the open-source context layer for data agents — runs ktx setup non-interactively with hidden CLI flags…
Automated heterogeneous database migration skill for KaiwuDB / KWDB via KDTS REST API.
Triggered when the user wants to install or deploy KaiwuDB (kwdb, kaiwudb).
Optimize SQL query performance for KaiwuDB time-series and relational engines.
Design KWDB schemas and generate DDL for relational, time-series, and mixed workloads.
Convert natural language queries to KWDB SQL for time series data, relational data and cross-model analysis.
Use when diagnosing KWDB incidents from logs, metrics, or system evidence, especially crashes, OOM, slow SQL, restarts, and cluster-wide…
Analyzes PHP code for lazy loading issues.
Delete an entry from LogosDB by row ID or by semantic query match.
Use Lians financial-grade agent memory - store and recall facts with a bitemporal model so stale revisions never contaminate context.