Amazon Opensearch Service

AWSOfficialPublished by AWS

Skill
Workflow
Cloud and DevOps
Apache-2.0
Low risk

From the author

Guides migration, provisioning, search, log-analytics, trace-analytics, and Agentic AI Assistant workflows for Amazon OpenSearch Service and Serverless across six capabilities — migration (Solr/ES/self-managed into AOS/AOSS, schema/query translation, sizing, cutover); provisioning (domain + AOSS lifecycle, upgrades, FGAC, monitoring); search (vector / semantic / hybrid / RAG with Bedrock); log-analytics (PPL, OSI, anomaly detection, Dashboards); trace-analytics (OTel spans, service maps, Data Prepper); ai-assistant (natural language data exploration, incident investigation, root cause analysis). Triggers on OpenSearch, AOS, AOSS, Elasticsearch, Solr, vector/k-NN/semantic/hybrid search, RAG, log analytics, PPL, trace analytics, ISM, FAISS, HNSW, Migration Assistant, UltraWarm, OR1, query my data, analyze logs, investigate errors, root cause analysis.

— the description by AWS

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a unified framework for interacting with Amazon OpenSearch Service (AOS) and OpenSearch Serverless (AOSS). It covers the full lifecycle of OpenSearch operations, including migration from legacy systems like Solr or Elasticsearch, infrastructure provisioning, advanced search implementation (including vector and RAG), and observability through log and trace analytics. It also features an Agentic AI Assistant for natural language data exploration and incident investigation, ensuring users can navigate complex cluster management and data analysis tasks without manual query crafting.

What it does

Guides migration workflows from Solr, Elasticsearch, or self-managed OpenSearch to AOS/AOSS.
Assists with provisioning, lifecycle management, and monitoring of domains and collections.
Facilitates implementation of vector, semantic, and hybrid search, including RAG with Bedrock.
Supports log and trace analytics using PPL, OpenTelemetry, and anomaly detection.
Provides an Agentic AI Assistant for natural language querying and automated incident root cause analysis.
Enforces operational best practices for sharding, storage tiering, and security configurations.

When to use it

When planning a migration from legacy search engines to Amazon OpenSearch Service.
When setting up or optimizing search capabilities, including vector search and RAG.
When troubleshooting cluster health, performance, or shard allocation issues.
When performing log or trace analysis to investigate system incidents.
When you need to generate optimized PPL or DSL queries using natural language.

Advantages

Centralizes complex operational knowledge across six distinct OpenSearch capabilities.
Reduces manual query complexity by leveraging the Agentic AI Assistant.
Provides clear, actionable guidance on production failure modes and migration blockers.
Standardizes interactions through consistent CLI and data-plane patterns.
Promotes architectural best practices for scaling and cost-effective storage tiering.

Usage examples

“How do I migrate my existing Solr index to Amazon OpenSearch Service?”: The agent identifies the migration capability, explains that Solr to OpenSearch is a refactor migration, and guides you through using the Migration Assistant for data backfill.
“Why is my cluster status yellow and how can I fix it?”: The agent uses the AI Assistant capability to analyze cluster health, check shard allocation, and provide specific commands or steps to resolve unassigned shards.
“Help me set up a RAG pipeline using Bedrock and my OpenSearch domain.”: The agent routes to the search capability, providing instructions on configuring Bedrock connectors and vector index mappings for semantic retrieval.
“Find the root cause of the 503 errors in my application logs from the last hour.”: The agent utilizes the AI Assistant to query logs, perform time-series analysis, and correlate findings to identify the likely root cause of the errors.

Install

Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/aws/amazon-opensearch-service/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip amazon-opensearch-service.zip -d .agents/skills

Documentation by AWS

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.

Step 0: detect the capability — first thing you do

Pick one of the six capabilities below. State the detected capability in your first sentence (e.g., "Detected capability: SEARCH — semantic search setup with Bedrock embeddings."). Then load the entry-point reference; that file describes when to dispatch, indexes the rest of the capability's files, and routes you to the next step.

Capability	Entry-point reference
migration — Solr / Elasticsearch / self-managed OpenSearch into AOS or AOSS. Schema/query translation, sizing, cutover.	`references/assessment-workflow.md`
provisioning — Provisioning and managing AOS domains and AOSS collections. Lifecycle, upgrades, storage tiers, FGAC, monitoring.	`references/provisioning-reference.md`
search — Vector / semantic / hybrid / sparse / dense / RAG retrieval. Bedrock connectors, FAISS HNSW vs Lucene.	`references/search-semantic-search-guide.md`
log-analytics — Log search, observability, PPL, OSI ingestion, anomaly detection, OpenSearch Dashboards. Splunk/Datadog/ELK alternatives.	`references/log-analytics-guide.md`
trace-analytics — Distributed traces with OpenTelemetry. Span queries, service maps, Data Prepper.	`references/trace-analytics-trace-queries.md`
ai-assistant — Agentic AI Assistant: auto-discovers indices, generates optimized PPL/DSL queries, summarizes results, and investigates incidents end-to-end. No manual query crafting needed.	`references/ai-assistant.md`

If a prompt spans capabilities (e.g., "migrate from Solr AND set up RAG on the new domain"), pick the dominant capability for the response and close with a one-line handoff to the other capability's entry-point ref.

Universal rules (apply to ALL capabilities)

These rules apply to every response, regardless of capability. Capability-specific rules (sizing math, shape detection, Migration Assistant for Amazon OpenSearch Service capability matrix, k-NN engine selection) live in the entry-point references, not here.

Report header (every multi-section response). Begin every multi-section response with a single fenced metadata block: > Generated: <ISO 8601 timestamp> | Skill: amazon-opensearch-service v<N>. Get the time by calling the current_time tool (returns ISO 8601 in UTC). Read the skill version from this file's frontmatter version: field. For one-line answers (terse FOCUSED_OPERATIONAL replies, anti-pattern refusals) the header is optional; for any multi-section deliverable it is REQUIRED. Place it immediately after the report title and before the first ## heading.
No dollar estimates (HARD CONSTRAINT). Never produce $X/month, ~$1,500, or any dollar figure. Route every cost question to https://calculator.aws and stop. If a sub-reference contains dollar figures, treat them as informational context only and do NOT pass them through to the user.
No credential leakage (HARD CONSTRAINT). Never include master usernames, KMS key ARNs, VPC endpoint URLs, instance IPs, or account IDs in generated output.
Pick one for every A-vs-B decision. Name a primary recommendation in one line with a one-sentence reason. A "go with B if..." caveat is allowed AFTER the primary; never lead with conditional-only guidance.
Source restatement. The first 2–3 sentences must restate the source (engine + version + scale) when known, or restate the customer's question in concrete terms. The very first text the user sees must NOT be tool narration, meta-commentary, the report title, or simply restating the question verbatim.
No marketing tone. Do NOT use "seamless", "robust", "best-in-class", "production-hardened", "enterprise-grade", "world-class", "cleanly", "elegant". Do NOT stack 3+ vague hedges ("typically", "generally", "usually", "in most cases") in a single recommendation — be specific about when it does and does not apply.
Cross-capability handoff. When a user prompt spans capabilities (e.g., "migrate from Solr AND set up RAG on the new domain"), pick the dominant capability for the response, then close with a one-line handoff: "For <other capability>, see references/<other-capability>-<entry>.md."

Cross-cutting references (used across multiple capabilities)

These references are not capability-prefixed because they apply across capabilities. Capability entry-point references load them when relevant; SKILL.md never loads them directly.

references/sizing.md — sizing math, instance family details, OR1 trade-offs, watermarks, JVM heap rules.
references/vector-knn.md — k-NN engines, memory math, RAG ingestion patterns, ELSER alternatives.
references/observability.md — log analytics patterns, ISM, UltraWarm/Cold tiering, Splunk/Datadog migration playbooks.
references/security.md — FGAC, encryption, VPC patterns, audit logs, compliance posture.
references/personas.md — communication style per persona.
references/assessment-gotchas.md — production gotcha catalog (cite by number in Migration specifics or Risks/blockers tables; each gotcha carries a Category: tag that determines its lane).
references/assessment-knowledge-retrieval.md — topic → tool → URL recipe for batched verification.

Assets (assets/): report templates for FULL_ASSESSMENT renderings (Solr-source, ES-source, executive summary).

What this skill does NOT do

Estimate dollar costs. Pricing changes monthly and account-specific (RI, Savings Plan, EDP) discount math is outside this skill's reliable scope. Use https://calculator.aws.
Move data. Use Migration Assistant for Amazon OpenSearch Service (Historical Data Migration for backfill, Live Traffic Migration for live cutover).
Build embedding models. Use Amazon Bedrock or SageMaker.
Replace Splunk SPL or Datadog APM 1:1. Some queries / detectors / dashboards need rewriting.
Tune relevance for a specific catalog. Use OpenSearch Benchmark big5 workload + your own judgment list.

Guardrail — where this skill's own files live (MCP vs local install)

This skill can be loaded two ways, and they resolve the skill's own bundled files from different places. Determine how the skill was loaded before reading a reference or running a script:

Loaded through the AWS MCP server's retrieve_skill tool: The skill is not installed on the local filesystem. You MUST fetch each reference or script via retrieve_skill with the file parameter (e.g. file="references/architecture.md" or file="scripts/deploy.py"), and run the script from the returned content. Do NOT file_read these paths locally — they do not exist on disk.
Installed locally (e.g. .kiro/skills/your-skill/ or ~/.claude/skills/your-skill/): Read and run files from the local skill directory using relative paths.

This distinction applies only to the skill's own packaged files. User data and session artifacts are always read from and written to the user's working directory. Never fetch or write customer data through retrieve_skill.

Files

ATTRIBUTION.mdAdded by AutoGineer930 B
LICENSELicence file added by AutoGineer9.9 KiB
NOTICELicence file added by AutoGineer67 B
SKILL.md9.2 KiB
assets/elasticsearch-gap-register.md5.1 KiB
assets/elasticsearch-index-template-skeleton.md4.2 KiB
assets/elasticsearch-report-template.md7.8 KiB
assets/executive-summary-template.md3.0 KiB
assets/report-template.md12.9 KiB
assets/solr-gap-register.md3.8 KiB
assets/solr-index-template-skeleton.md3.7 KiB
assets/solr-report-template.md5.9 KiB
assets/tech-deepdive-template.md6.2 KiB
references/ai-assistant.md18.0 KiB
references/assessment-gotchas.md17.1 KiB
references/assessment-knowledge-retrieval.md9.3 KiB
references/assessment-shape-anti-pattern-pushback.md10.4 KiB
references/assessment-shape-comparative-decision.md12.9 KiB
references/assessment-shape-focused-operational.md9.9 KiB
references/assessment-shape-full-assessment.md20.7 KiB
references/assessment-shape-overview.md12.1 KiB
references/assessment-shape-schema-conversion.md8.9 KiB
references/assessment-shape-sizing-only.md9.4 KiB
references/assessment-shape-translation.md12.3 KiB
references/assessment-workflow.md48.4 KiB
references/compatibility-rubric.md5.9 KiB
references/log-analytics-guide.md18.0 KiB
references/log-analytics-osi-pipelines.md8.6 KiB
references/log-analytics-troubleshooting.md1.6 KiB
references/observability-ppl-reference.md15.1 KiB
references/observability.md14.5 KiB
references/personas.md10.4 KiB
references/provisioning-agentic-setup.md4.8 KiB
references/provisioning-domain-deploy-search.md2.2 KiB
references/provisioning-domain-provision.md3.4 KiB
references/provisioning-monitoring.md3.4 KiB
references/provisioning-reference.md6.8 KiB
references/provisioning-serverless-agentic-setup.md14.9 KiB
references/provisioning-serverless-deploy-search.md6.7 KiB
references/provisioning-serverless-deprovision.md4.0 KiB
references/provisioning-serverless-provision.md8.8 KiB
references/provisioning-storage-tiers.md2.1 KiB
references/provisioning-troubleshooting.md8.0 KiB
references/provisioning-upgrades.md5.4 KiB
references/readiness-rubric.md3.4 KiB
references/search-bedrock-connectors.md3.8 KiB
references/search-dense-vector-models.md5.5 KiB
references/search-document-processing-guide.md7.7 KiB
references/search-evaluation-guide.md5.3 KiB
references/search-index-config.md2.4 KiB
references/search-recipes.md12.9 KiB
references/search-semantic-search-guide.md18.2 KiB
references/search-sparse-vector-models.md4.9 KiB
references/search-troubleshooting.md1.9 KiB
references/security.md9.3 KiB
references/sizing.md12.2 KiB
references/source-elasticsearch.md6.7 KiB
references/source-opensearch.md4.8 KiB
references/trace-analytics-trace-ingestion.md3.3 KiB
references/trace-analytics-trace-queries.md13.9 KiB
references/trace-analytics-troubleshooting.md1.6 KiB
references/vector-knn.md12.9 KiB

references/provisioning-serverless-provision.md

Amazon OpenSearch Serverless — Provision Collection

The AWS MCP server is recommended for executing these commands but is not required — all steps use standard AWS CLI syntax.

Prerequisites

Confirm AWS credentials: aws sts get-caller-identity
Save AWS account ID and principal ARN

Step 1: Create Encryption Policy

Required before collection creation:

aws opensearchserverless create-security-policy \
  --name <collection-name>-encryption --type encryption \
  --policy '{"Rules":[{"ResourceType":"collection","Resource":["collection/<collection-name>"]}],"AWSOwnedKey":true}'

For compliance workloads (PCI-DSS, HIPAA), use customer-managed keys: set AWSOwnedKey:false and provide a CMK ARN.

Step 2: Create Network Policy

Production (recommended): Use VPC endpoint for secure private access:

aws opensearchserverless create-security-policy \
  --name <collection-name>-network --type network \
  --policy '[{"Rules":[{"ResourceType":"collection","Resource":["collection/<collection-name>"]},{"ResourceType":"dashboard","Resource":["collection/<collection-name>"]}],"VpceIds":["<vpce-id>"]}]'

Last-resort dev/test (NOT for production): AllowFromPublic: true exposes the collection to the entire internet — there is no IP scoping or auth gate at the network layer. AWS Security Code Scanner flags this as an open-network default. Prefer one of:

VPC endpoint (the production pattern shown above) — recommended for any non-throwaway environment.
VPC endpoint with IP-allowlist via SecurityGroup — when you need broader connectivity than a single VPC.
Only when neither is feasible (e.g. ad-hoc lab account with no VPC), use the public form below — and tear down the collection within hours, not days.

# ⚠️ Public access — entire internet can reach the endpoint. Dev/test ONLY,
# and even then prefer VPC endpoint with SG-scoped CIDR (see Step 5 below).
aws opensearchserverless create-security-policy \
  --name <collection-name>-network --type network \
  --policy '[{"Rules":[{"ResourceType":"collection","Resource":["collection/<collection-name>"]},{"ResourceType":"dashboard","Resource":["collection/<collection-name>"]}],"AllowFromPublic":true}]'

Step 3: Create Data Access Policy

Base policy (BM25 — least-privilege default). Grants no model access. Use this as-is for plain keyword/BM25 collections:

aws opensearchserverless create-access-policy \
  --name <collection-name>-data --type data \
  --policy '[{"Rules":[{"ResourceType":"index","Resource":["index/<collection-name>/*"],"Permission":["aoss:CreateIndex","aoss:DescribeIndex","aoss:UpdateIndex","aoss:DeleteIndex","aoss:ReadDocument","aoss:WriteDocument"]},{"ResourceType":"collection","Resource":["collection/<collection-name>"],"Permission":["aoss:CreateCollectionItems","aoss:DescribeCollectionItems"]}],"Principal":["<principal_arn>"]}]'

ML addendum (neural-sparse / agentic only). Only when the collection uses ML, append this rule to the Rules array above — do NOT include it in BM25-only collections, because it grants every AOSS action on every model in the account:

{"ResourceType":"model","Resource":["model/*/*"],"Permission":["aoss:*"]}

Note: AOSS data access policies do not support IAM condition keys. Use network policies (VPC endpoints) and principal scoping for access control.
Tip: Remove permissions not needed for your use case. For read-only collections, remove aoss:WriteDocument, aoss:UpdateIndex, aoss:DeleteIndex.
For neural-sparse (semantic enrichment) or agentic strategies, the data access policy MUST also grant the model and agent ResourceTypes, and the model resource MUST be model/*/* (not model/<collection-name>/*), because semantic enrichment registers ML connectors at the account level rather than under the collection name. Omit these rules for plain BM25 collections, because BM25 uses no ML resources. For the full agentic data access policy, see provisioning-serverless-agentic-setup.md.
Least-privilege warning: aoss:* on model/*/* grants every AOSS action on every model in the account — broader than least-privilege ideally allows. AOSS does not expose scoped per-model ML actions for data access policies, so aoss:* is the narrowest functional grant here. Track it and tighten the Permission list if AOSS exposes granular model actions. See the fuller discussion in provisioning-serverless-agentic-setup.md.

Step 4a: Create Collection Group (NextGen — default)

NextGen is the default serverless target for all strategies except conversational agentic search. A NextGen collection MUST belong to a collection group, so create the group before the collection. Because generation defaults and per-strategy support change over time, verify the current default generation and supported strategies against the AWS docs or aws opensearchserverless API capabilities before relying on this.

aws opensearchserverless create-collection-group \
  --name <collection-name>-group \
  --standby-replicas ENABLED \
  --generation NEXTGEN

--generation NEXTGEN is REQUIRED, because omitting it creates a Classic group and NextGen-only features are unavailable and the generation cannot be changed after creation. Verify the current NextGen feature set against the AWS docs (serverless-overview.html) rather than relying on a hardcoded list.
--standby-replicas ENABLED is required for NextGen — NextGen groups reject DISABLED, which is a Classic-only dev/test option. This constraint is generation-specific and may be relaxed — verify whether DISABLED is supported for the chosen generation via the AWS docs, or attempt creation and handle any validation error (same pattern used for OCU values below).
Capacity limits are optional. When set, each OCU value must be one of a service-defined set of allowed steps, and AOSS rejects any other value with an Invalid value for maxIndexingCapacityInOCU error. The allowed steps are service-specific limits that change over time — fetch the allowed values from the AWS docs (serverless-scaling.html), or attempt creation and parse the validation error message, rather than hardcoding a specific value:
```
aws opensearchserverless create-collection-group \
  --name <collection-name>-group --standby-replicas ENABLED --generation NEXTGEN \
  --capacity-limits '{"minIndexingCapacityInOCU":4,"maxIndexingCapacityInOCU":16,"minSearchCapacityInOCU":4,"maxSearchCapacityInOCU":16}'
```

Then create the collection into the group instead of standalone:

aws opensearchserverless create-collection \
  --name <collection-name> --type <SEARCH|VECTORSEARCH> \
  --collection-group-name <collection-name>-group

SEARCH and VECTORSEARCH are supported on NextGen while TIMESERIES is Classic-only (see assessment-gotchas.md §9). Supported collection types are generation-specific — verify the valid types against the AWS docs (serverless-overview.html) at creation time, or attempt creation and handle the validation error, rather than relying on this list.

Add a collection to an existing group

aws opensearchserverless list-collection-groups          # find the group name + capacityLimits
aws opensearchserverless create-collection --name <new-name> --type <TYPE> \
  --collection-group-name <existing-group-name>

Before creating, verify an encryption policy and network policy already cover <new-name> (or a collection/* wildcard), because a collection cannot be created if no encryption policy matches its name.

Step 4b: Create Collection (Classic — standalone fallback)

Use the Classic standalone flow only when Classic is explicitly required (e.g. a TIMESERIES collection, or a feature not yet on NextGen), because NextGen is the default target everywhere else in this runbook.

Choose type based on strategy:

VECTORSEARCH: Dense vector search (semantic with dense embeddings)
SEARCH: All other strategies (BM25, neural sparse, hybrid with neural sparse)

Neural sparse requires SEARCH type, not VECTORSEARCH.

aws opensearchserverless create-collection \
  --name <collection-name> \
  --type SEARCH \
  --description "Search application collection"

Step 5: Wait for Collection Active

aws opensearchserverless batch-get-collection --names <collection-name>

Typically 1-3 minutes.

Next Step

Proceed to provisioning-serverless-deploy-search.md.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs an MCP server

Security

What our scanner noticed· Low risk

Instructions that use the network

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by

AWS

Publisher

AWS (Official)

Source

aws/agent-toolkit-for-aws · plugins/aws-data-analytics/skills/amazon-opensearch-service · commit 0a218f8

Licence

Apache License 2.0 (redistribution allowed)

LICENSE (added by AutoGineer from LICENSE)
NOTICE (added by AutoGineer from NOTICE)
ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-08

Also distributed in

aws/agent-toolkit-for-aws

AutoGineer is not affiliated with or endorsed by AWS.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download amazon-opensearch-service.zip