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://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/assessment-shape-overview.md

Shape recipe: OVERVIEW_REQUEST

What this shape is

OVERVIEW_REQUEST is the response shape for "what's the path?" questions — the user wants a high-altitude tour of the migration journey, not a forensic 9-section assessment and not a technical intake form. They want to leave the response knowing what phases happen, in what order, what the named tool is, and what the next concrete step is.

This is the most-mis-shaped ask in the suite. The two failure modes to avoid:

Bloat. Producing a full FULL_ASSESSMENT (Executive Summary / Source / Target / Migration Path / Sizing / Readiness / Risks / Citations) when the user pasted no artifacts and asked one sentence. The response feels generic because every section has to invent its inputs.
Intake stall. Replying with a 6-question Business Stakeholder intake when the user actually wanted substance. "What's the path?" is a substantive request — answer it. Save intake questions for explicit Business Stakeholder framing ("I'm a director, what do you need from me?").

OVERVIEW_REQUEST sits between those two failure modes: a real, named, sequenced phase walk-through that any persona can read and act on, with one inline doc URL and one named gotcha so the user knows which rock to look under first.

Detection signals

Trigger this shape when the prompt matches any of these without pasted artifacts:

Phase phrases: "what's the path?", "high-level overview", "walk me through it", "what's involved?", "how does this work end to end", "give me the migration overview"
Generic source mention with no specifics: "moving off Solr", "thinking about migrating from Elasticsearch", "we're on ES 7.x and want to look at OpenSearch" with no schema.xml, no _cat/indices, no doc count, no QPS
Stakeholder framing without intake invitation: "what does it take to migrate?", "what's the journey?"

If the user pasted a schema.xml, _cat/indices output, doc counts, traffic numbers, or asked a specific operational question ("cheapest path", "smallest reindex window") — switch shape. SCHEMA_CONVERSION, FULL_ASSESSMENT, or FOCUSED_OPERATIONAL is correct, not OVERVIEW_REQUEST.

If the user explicitly says "I'm a product manager / director / TPM" AND asks "what do you need from me?", switch to the Business Stakeholder six-question intake — that's a different output and lives outside the case-shape suite.

Required output template

The response must contain, in order:

1. Source restatement (1–2 sentences, mandatory)

Restate what the user said: source engine, version (or "version unspecified"), target. Example:

Solr 8.11 SolrCloud → Amazon OpenSearch Service. Here's the path at a glance — four phases, primary tool is Migration Assistant for Amazon OpenSearch Service Historical Data Migration.

2. Three to four named, sequenced phases

Each phase needs:

A name (Discovery / Schema & Query Translation / Backfill / Cutover, or similar — see exemplar)
One paragraph (1–3 sentences) of what happens in it
The named tool if one applies in that phase (_reindex.remote, Migration Assistant for Amazon OpenSearch Service Historical Data Migration, Migration Assistant for Amazon OpenSearch Service Live Traffic Migration, OSI, in-place blue/green)

Three phases is the floor. Four is typical. Five+ means you're drifting into FULL_ASSESSMENT — stop.

3. One named migration specific or risk

Pick the single highest-impact item for this source engine and call it out by name. Frame it as a migration specific when the item has a clean, prescribed remediation that the migration plan already includes (q.op=AND translation, fielddata strip, etc.) — "this is how the migration handles X". Frame it as a risk only when there is no known fix, when it constrains the target choice, or when it gates capacity / decisions late in the path (Lucene 8 → 10 segment wall, custom JARs not supported on Serverless NextGen, etc.). Examples:

Solr → OpenSearch (migration specific): q.op=AND operator divergence — when the source solrconfig.xml sets q.op=AND, OpenSearch's query_string defaults to OR, so set default_operator: AND on every translated handler (top cause of result divergence in Solr migrations).
Cite ONE relevant gotcha by number from assessment-gotchas.md (see #2 fork rule, #3 Lucene segment wall, #10 NMSLIB removal, #32 OS 1.x version trap).

Special rule — when the target is OS 3.x crossing from any 1.x or 2.x source: the named gotcha MUST be the Lucene 8 → 10 segment wall — phrase it as "Lucene 10 cannot read Lucene 8 segments — segment format is forward-only, so every pre-2.x index must be reindexed before reaching 3.x". Add a one-line tail naming at least one other OS 3.x breaking change: JDK 21 minimum runtime, Security Manager → Java agent plugin migration, NMSLIB removal (forces FAISS reindex), or renamed k-NN settings. A 2-sentence callout is sufficient — but both items are required on 1.x→3.x or 2.x→3.x crossings.

4. One inline AWS doc URL

A single link in the body, near the closing sentence — NOT a Citations section. Pick the canonical entry point for the migration tool you named:

Migration Assistant for Amazon OpenSearch Service (any source): https://docs.aws.amazon.com/opensearch-service/latest/developerguide/migration-assistant.html
_reindex from remote: https://docs.aws.amazon.com/opensearch-service/latest/developerguide/remote-reindex.html
In-place upgrade: https://docs.aws.amazon.com/opensearch-service/latest/developerguide/version-migration.html

5. Clear next step

End with one sentence telling the user the most useful concrete thing they can do next: typically share the artifact that lets us go from generic to specific. Examples:

"Share your schema.xml and a _cat/indices?v dump and I'll produce a field-by-field mapping plus sizing."
"Spin up Migration Assistant for Amazon OpenSearch Service on a non-prod target and run Historical Data Migration against a single low-stakes index first."
"Confirm your ES version (GET / against the cluster) — the path forks hard at 7.11."

NOT REQUIRED — explicitly omit

Do not include the following in an OVERVIEW_REQUEST response:

Timeline & Resourcing — removed from the suite entirely. No "8–12 engineer-weeks", no "Phase 1: 2 weeks", no resourcing language anywhere.
9-section structure (Source / Target / Migration Path / Sizing / Readiness / Risks / Timeline / Citations / Executive Summary). That's FULL_ASSESSMENT.
Readiness score (the 0–100 / GREEN-YELLOW-RED tier). Save for FULL_ASSESSMENT.
Citations section. One inline URL is the rule — no References block.
Sizing math (instance class, shard count, storage formulas). Save for SIZING_ONLY or FULL_ASSESSMENT.
Math derivations (heap math, segment math, watermark calculations).
Customer-specific trade-offs. Without artifacts you don't have the inputs — stay path-generic. Don't invent "your 6-node cluster will need…".
Six-question Business Stakeholder intake. That's a different shape.
Gap register tables (BLOCKING / HIGH / MEDIUM / LOW). FULL_ASSESSMENT only.

Worked exemplar — Solr 8.11 → Amazon OpenSearch

Prompt: "We're running SolrCloud 8.11 and starting to look at moving to Amazon OpenSearch. What's the path?"

Response:

Detected shape: OVERVIEW_REQUEST. Solr 8.11 SolrCloud → Amazon OpenSearch Service — four named phases, primary tool is Migration Assistant for Amazon OpenSearch Service Historical Data Migration (Migration Assistant for Amazon OpenSearch Service Historical Data Migration). Solr → OpenSearch is a refactor, not a lift-and-shift: schema, queries, and configs all need translation. There is no segment-level path between Solr and OpenSearch.
Phase 1 — Discovery & schema translation. Inventory your collections, schema.xml, solrconfig.xml, and the queries your application sends. Translate <field> definitions into an OpenSearch mapping (StrField → keyword, TextField → text with the matching analyzer, <copyField> → "copy_to", <uniqueKey> → bind to _id on _bulk and map as keyword). This is design work — no data moves yet.
Phase 2 — Query translation & shadow validation. Convert eDisMax/standard handlers to OpenSearch DSL: qf field^boost → multi_match type: best_fields, mm passes UNCHANGED as minimum_should_match. Stand up an empty target domain and replay a representative query set against both engines. Compare top-K results before any cutover plan is locked in.
Phase 3 — Backfill with Migration Assistant for Amazon OpenSearch Service Historical Data Migration, cut over with Migration Assistant for Amazon OpenSearch Service Live Traffic Migration. Solr → OpenSearch: target must be OS 3.x or Serverless (architectural rule). Tool eligibility per current Migration Assistant for Amazon OpenSearch Service versions: source-and-target-versions. Take a Solr backup to S3, point Migration Assistant for Amazon OpenSearch Service at the snapshot for Historical Data Migration, then enable Live Traffic Migration for the cutover window.
Phase 4 — Cutover & decommission. Final delta backfill (rerun Historical Data Migration over the most recent shard of changes), DNS/app-config flip to the OpenSearch endpoint, monitor for 1–2 release cycles, then retire the Solr cluster.
Top migration note: Many Solr deployments configure q.op=AND (Solr's own default is OR, but the AND override is common in production). OpenSearch's query_string defaults to OR. If your source uses q.op=AND, set default_operator: AND on every translated query handler — otherwise relevance regresses dramatically. This is the #1 cause of result divergence in Solr → OpenSearch migrations. See the Migration Assistant for Amazon OpenSearch Service docs at https://docs.aws.amazon.com/opensearch-service/latest/developerguide/migration-assistant.html.
Next step: share your schema.xml and a sample of the queries your app issues (top 10 by volume is enough). With those I can produce a field-by-field mapping and a query-translation reference so Phases 1 and 2 are fully concrete.

That's ~340 words and hits every required slot: source restated, four named phases with the tool, one gotcha named, one inline URL, one concrete next step. No timeline. No sizing math. No citations section. No 9-section scaffold.

Pre-emit checklist (OVERVIEW_REQUEST-specific)

Tick every box before sending. If any fails, revise — do not ship.

[ ] First sentence restates source engine + version (or "version unspecified") + target.
[ ] Detected shape stated explicitly (Detected shape: OVERVIEW_REQUEST.).
[ ] Exactly 3 or 4 named phases (not 2, not 5+). Each has a noun-phrase name, not just "Step 1".
[ ] Each phase names the tool used in it (or explicitly says "design work, no data moves").
[ ] Exactly one named gotcha appears, sourced from the always-true facts in SKILL.md.
[ ] Exactly one inline AWS doc URL — and there is NO Citations section.
[ ] Final paragraph ends with a concrete next step (typically: ask for the artifact that unlocks the next shape).
[ ] NO Timeline & Resourcing. Search the response for "week", "month", "engineer-week", "sprint", "timeline", "resourcing" — if any appear, delete them.
[ ] NO sizing math. Search for instance class names (r7g, m7g), shard counts, GB/heap math — if any appear, you've drifted into SIZING_ONLY.
[ ] NO readiness score / tier color. Search for "GREEN", "YELLOW", "RED", "/100" — delete if present.
[ ] NO 9-section scaffold. If your response has headings like "Executive Summary" / "Risks" / "Citations" — you're in the wrong shape; delete or switch to FULL_ASSESSMENT.
[ ] No dollar figures anywhere (universal rule).
[ ] No marketing words: "seamless", "robust", "best-in-class", "production-hardened", "enterprise-grade".
[ ] Total length 200–500 words. If you're over 600, you've drifted toward FULL_ASSESSMENT — trim.

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

2026-11-09

Also distributed in

aws/agent-toolkit-for-aws

AutoGineer is not affiliated with or endorsed by AWS or AWS.

Download ZIP

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