Amazon Opensearch Service

Five capabilities in one: migration from Solr or Elasticsearch into managed OpenSearch, provisioning domains and serverless collections, vector and hybrid search with Bedrock connectors, log analytics as a Splunk alternative, and distributed tracing with OpenTelemetry. Routes your question to the right capability up front, then walks you through sizing math, shard counts, query DSL examples, and CLI commands. Built around AWS CLI with optional MCP integration. Good when you need concrete instance classes and cutover plans instead of generic advice. Explicitly refuses to estimate costs or leak credentials, which is the right call for a public skill.

skills.sh installs: 6K
GitHub stars: 3.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add aws/agent-toolkit-for-aws --skill amazon-opensearch-service --agent claude-code

Installs into .claude/skills of the current project.

Files

Amazon OpenSearch Service — the unified skill

This skill answers anything about Amazon OpenSearch Service or Serverless across six capabilities. Step 0 below routes the question to ONE capability and points at that capability's entry-point reference. Everything else — when to dispatch, sub-references, capability-specific facts, cross-capability links — lives in the entry-point reference for that capability.

AWS MCP server is recommended, not required. Capability references show standard AWS CLI commands as the primary syntax (e.g., aws opensearch describe-domain, aws opensearchserverless create-collection). Where the AWS MCP server is available, its call_aws tool offers a streamlined alternative — but every operation in this skill MUST work via the AWS CLI alone. Data-plane HTTP calls against AOS / AOSS use awscurl for SigV4-signed requests; this works in both contexts.