amazon-opensearch-service

An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: analytics, aws, logs, search, vector-search.

What it does

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.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add aws/agent-toolkit-for-aws --skill amazon-opensearch-service

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/aws/agent-toolkit-for-aws
cp -r agent-toolkit-for-aws/plugins/aws-data-analytics/skills/amazon-opensearch-service ~/.claude/skills/amazon-opensearch-service

Safety box score

Grade D, elevated risk: 49 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is an AWS control-plane and data-plane playbook for Amazon OpenSearch Service and Serverless: it provisions domains/collections, configures IAM/security, builds ingestion/search pipelines, and can also tear resources down. The main risks are irreversible cloud changes, broad IAM/network exposure, and moving sensitive log/trace/search data through remote AWS services and Bedrock.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	2 (moderate)	It is command-driven (`aws opensearch create-domain`, `aws osis create-pipeline`, `awscurl`) but ships no native binaries or arbitrary code execution beyond those shell/API calls.
Network access	2 (moderate)	It sends data to remote AWS services and endpoints (`bedrock-runtime.../invoke`, `https://<pipeline-endpoint>/v1/traces`, `awscurl` to OpenSearch), so local data can leave the machine.
Filesystem reach	0 (none)	I found no shipped scripts or instructions that write outside the project/work directory or modify shell dotfiles/system paths.
Secrets & credentials	2 (moderate)	It explicitly reads a password from Secrets Manager (`aws secretsmanager get-secret-value --secret-id opensearch-admin-password`) and handles master-user credentials in `MasterUserPassword=$PASSWORD`.
Privilege & persistence	2 (moderate)	It creates and updates IAM roles/policies and security settings (`aws iam create-role`, `aws iam put-role-policy`, `update-domain-config`), expanding AWS permissions and trust relationships.
Instruction hijack surface	0 (none)	I found no text telling the agent to ignore higher-priority instructions, hide actions, or follow fetched remote instructions.
Irreversible actions	3 (high)	Irreversible and production-impacting actions are built in, including `aws opensearchserverless delete-collection` and one-way `aws opensearch upgrade-domain` flows.
Transparency	1 (low)	The package is readable, but several linked references were not inspectable in this review and the skill relies on `[verify]` live docs for some claims.

Before installing

Read `references/provisioning-serverless-deprovision.md` first: it deletes collections and policies irreversibly.
Confirm you are comfortable granting the agent AWS permissions to create/modify IAM roles, domains, pipelines, and security policies.
Test in a non-production AWS account with public AOSS access disabled and Secrets Manager empty unless you explicitly need those paths.
Verify whether sending traces/logs/search traffic to Bedrock/OSI/OpenSearch endpoints matches your data-handling rules.

Rated 2026-10-20 by an automated review of 37 files from the skill's repository.

Source

Repository: aws/agent-toolkit-for-aws (all skills from this repository)
Path: plugins/aws-data-analytics/skills/amazon-opensearch-service/SKILL.md
Branch: main
Collection: aws-data-analytics
Updated: 2026-09-19

querying-aws-cloudwatch — Runs SQL queries on CloudWatch Logs data exported as Apache Iceberg tables in S3 Tables.
storing-and-querying-vectors — Store and query vector embeddings using Amazon S3 Vectors, a cost-effective long-term vector storage service with its own API namespace (s3vectors).
aws-observability — Builds, configures, debugs, and optimizes AWS observability with CloudWatch (Log Insights, Metrics, Alarms, Dashboards, EMF), X-Ray, CloudTrail.
ads — When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms.
ai-seo — When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers.
aso — When the user wants to audit or optimize an App Store or Google Play listing.