CtrlK
BlogDocsLog inGet started
Tessl Logo

amazon-opensearch-service

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.

72

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-architected router skill: lean, capability-routed, with real one-level-deep references and strong guardrails. The main gaps are minor verbosity in the MCP/local-install guardrail and validation detail being delegated to references for destructive migration workflows.

Suggestions

Tighten the "Guardrail — where this skill's own files live" section; the trailing paragraph about user data/session artifacts restates context Claude can infer.

Surface one explicit validation checkpoint in the body for destructive migration/cutover (e.g., a dry-run or cutover-rollback gate) rather than deferring all validation to the entry-point references.

The illustrative paths `references/architecture.md` and `scripts/deploy.py` in the guardrail do not exist as bundle files; either mark them clearly as placeholders or replace with real example paths to avoid a dead-reference impression.

DimensionReasoningScore

Conciseness

The body is a lean router that assumes Claude's competence — it never explains what OpenSearch is — but the AWS-MCP note and the MCP-vs-local guardrail section carry some explanatory padding ("This distinction applies only to the skill's own packaged files...") that could be trimmed, keeping it just below a 5.

4 / 5

Actionability

Routing guidance is concrete and executable — "Pick one... State the detected capability in your first sentence... Then load the entry-point reference", an exact report-header fenced-block format, and named commands (`aws opensearch describe-domain`, `awscurl`) — but copy-paste code lives in the references rather than the body, leaving minor gaps for an instruction-only router.

4 / 5

Workflow Clarity

Step 0 gives a clear sequenced entry (detect capability → state it → load entry-point ref → ref routes onward) and the universal rules act as guardrail checkpoints, but explicit validation/feedback loops for the destructive migration/cutover path are delegated to the references rather than present in this overview body.

4 / 5

Progressive Disclosure

Clear overview with six entry-point references in a table and eight cross-cutting references one level deep, all verified to exist as real bundle files; content is appropriately split with capability-prefixed naming and easy navigation, and the entry-point refs carry real content rather than empty chained indirection.

5 / 5

Total

17

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that pairs a comprehensive concrete "what" with an explicit, keyword-rich "Triggers on ..." "when" clause. It is product-specific, covers synonyms and natural user phrasings, and avoids vague fluff.

DimensionReasoningScore

Specificity

Names the domain plus multiple concrete actions per capability — "schema/query translation, sizing, cutover", "domain + AOSS lifecycle, upgrades, FGAC, monitoring", "vector / semantic / hybrid / RAG with Bedrock", "PPL, OSI, anomaly detection", "OTel spans, service maps, Data Prepper" — giving comprehensive concrete coverage rather than vague verbs.

5 / 5

Completeness

It explicitly answers both "what" (six capabilities each with concrete sub-actions) and "when" via an explicit "Triggers on ..." clause with concrete trigger phrases, satisfying the Use-when requirement rather than capping at 3.

5 / 5

Trigger Term Quality

The "Triggers on" clause spans product names and acronyms (OpenSearch, AOS, AOSS, Elasticsearch, Solr), technical terms (vector/k-NN/semantic/hybrid search, RAG, PPL, ISM, FAISS, HNSW, UltraWarm, OR1) and natural user phrases ("query my data", "analyze logs", "investigate errors", "root cause analysis"), covering synonyms and natural wording comprehensively.

5 / 5

Distinctiveness Conflict Risk

The niche is product-specific (Amazon OpenSearch Service / Serverless) with distinct product triggers (AOS, AOSS, Migration Assistant, UltraWarm, OR1), so overlap with other skills is minimal and conflict risk is low.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

14

/

16

Passed

Repository
aws/agent-toolkit-for-aws
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.