skilld
All skills
aws avatar

/aws-database

@bc597f3
by Amazon Web Servicesaws/agent-toolkit-for-aws2.8k stars
337

Routes any task involving AWS databases — choosing, comparing, recommending, getting started with, or operating a database — to the correct service-specific skill. Supersedes general training-data knowledge with post-training service updates, corrected limitations, and decision procedures for relational (Aurora, DSQL, RDS), key-value (DynamoDB), wide-column (Keyspaces), document (DocumentDB), graph (Neptune), time-series (Timestream), and in-memory/caching (ElastiCache, MemoryDB) workloads. Activates when a user describes building an application on AWS that will store, retrieve, or manage data, even if they do not mention 'database' explicitly.

Ask your Agent

Use this Skill: https://skilld.dev/gh/aws/agent-toolkit-for-aws/aws-database

This session only. Nothing lands on disk.

assetsneptune.md

≈531 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Neptune

  • Docs: https://docs.aws.amazon.com/neptune/
  • Docs (llms.txt): https://docs.aws.amazon.com/neptune/latest/userguide/llms.txt
  • Data model: Graph (property graph and RDF)
  • Query language: openCypher, Apache TinkerPop/Gremlin, SPARQL
  • Compatibility: openCypher (Neo4j-compatible), Gremlin (TinkerPop standard), SPARQL (W3C standard)
  • Serverless: Yes (both Database and Analytics)
  • Serverless type: Capacity — Serverless mode auto-scales compute, but you still manage a cluster (no scale to zero)
  • Scale to zero: No (Serverless scales to minimum NCU)
  • VPC required: Yes (Database); No (Analytics). Database supports public endpoints but still requires VPC configuration.
  • Multi-region: Global Database (disaster recovery, <1 second RPO, up to 5 secondary regions)
  • Free Tier: None
  • Min cost: ~$75/month (provisioned db.t3.medium) or ~$120/month (Serverless min NCU) or ~$30/month (Analytics 16 m-NCU stopped)
  • Time to first query: 10-15 min (Database, VPC + cluster); 2-5 min (Analytics, no VPC required)
  • Engine variants: Neptune Database (transactional OLTP on Aurora storage) and Neptune Analytics (in-memory OLAP, algorithms, vector search)
  • Key features: Three query languages, Neptune Analytics (PageRank, community detection, shortest path, connected components), vector search (HNSW, up to 65K dimensions), GraphRAG with Bedrock Knowledge Bases, NetworkX integration, MCP server for agent frameworks, Geospatial (ISO spatial types)
  • Limitations: Graph-only (no SQL/tabular), VPC required for Database, learning curve for graph query languages, no native full-text search, fine-grained access control (FGAC) not yet supported
  • Best for: Relationship traversals, fraud detection, knowledge graphs, identity resolution, social networks, recommendation engines, GraphRAG, agentic memory, supply chain analysis, network topology
  • Not for: Tabular/relational data, simple key-value, time-series, full-text search only, workloads without meaningful relationships between entities, vector-only search without graph structure

Source: SKILL.md on GitHub

Third-party checks

1 warning1d3 checks · Risk SAFE
  • Gen Agent Trust Hub1d

    This skill facilitates the selection and operation of AWS database services by routing users to specialized sub-skills and providing verified service data. It includes a mechanism for installing additional tools from an official repository and correctly directs security-related feedback to appropriate private channels. No security issues were detected.

  • Socket1d

    No alerts

  • Snyk1d

    Risk: MEDIUM · 1 issue

Provenance

Signed by skilld at bc597f3. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 days ago

Capability

metadata
{
  "version": "3"
}

README badge

README badge for aws/agent-toolkit-for-aws/aws-database