How do I install the Opensearch Schema Review skill?

Run npx skillmds@latest add ch4570/opensearch-schema-review in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Opensearch Schema Review safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Opensearch Schema Review?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Opensearch Schema Review free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Opensearch Schema Review?

ch4570 (@ch4570) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Opensearch Schema Review by ch4570 — Agent Skill

Name: Opensearch Schema Review
Author: ch4570

Opensearch Schema Review

Review OpenSearch 3.5 index mappings/schemas. Check the dynamic policy, text/keyword, multi-field, index/doc_values, _source/derived source, nested cost, knn_vector fields (dimension/ space_type/engine/method/mode), and the Korean nori analyzer. Use when designing/modifying a mapping or reviewing an index schema. Grounds findings in a KB based on the official OpenSearch docs.

ch4570 8f06ec3 8 files · 23.0 KB Updated Sep 17, 2026

File contents

OpenSearch Schema/Mapping Review (Schema Review)

The grounding principles are in reference/principles.md. For facts, prefer reference/kb/ (the official docs).

Review order (proceed in this order)

What index does this index? — Identify the domain, language (Korean?), time-series nature, and scale (N).
Mapping in general — Check the review hooks in reference/kb/field-types.md · reference/kb/dynamic-mapping-risks.md.
Analyzers — Check reference/kb/analyzers-tokenizers.md (search vs index analyzer, normalizer, nori). If the nori grep returns 0 hits, state "not applicable".
Vector fields — Check reference/kb/knn-vector-field.md (dimension/space_type/engine/mode consistency, immutability).
Templates — reference/kb/index-templates.md. Along with the severity, provide a fix (mapping JSON diff) + a zero-downtime reindex/alias strategy.

Quick checklist

Is dynamic set to strict/false on production indexes (to prevent mapping explosion)?
Is sorting/aggregation/exact on keyword and full-text search on text? Are unused fields index:false/doc_values:false?
Does the knn_vector dimension match the model output, and is the space_type consistent with normalization?
Is the engine faiss/lucene (migrate if nmslib)? Are the core fields explicit in the mapping (to prevent dynamic inference)?
Are large vectors duplicated in _source → derived source (beware that nested/copy_to are unsupported)?
(Korean) Is nori configured with decompound_mode, a user dictionary, parts of speech, and a search-time synonym_graph?

KB (read and cite first)

From reference/kb/INDEX.md, read the following, check against the "review hooks", and cite via the source URL:

reference/kb/field-types.md · reference/kb/analyzers-tokenizers.md · reference/kb/knn-vector-field.md · reference/kb/index-templates.md · reference/kb/dynamic-mapping-risks.md

Deliverable

For each finding: problem → violated principle (principles.md §)/KB source → mapping diff → verification (_mapping/_analyze). Because mappings are immutable, accompany any change with a zero-downtime reindex/alias strategy.

---name: opensearch-schema-reviewdescription: Review OpenSearch 3.5 index mappings/schemas. Check the dynamic policy, text/keyword, multi-field, index/doc_values, _source/derived source, nested cost, knn_vector fields (dimension/ space_type/engine/method/mode), and the Korean nori analyzer. Use when designing/modifying a mapping or reviewing an index schema. Grounds findings in a KB based on the official OpenSearch docs.---# OpenSearch Schema/Mapping Review (Schema Review)The grounding principles are in `reference/principles.md`. For facts, prefer `reference/kb/` (the official docs).## Review order (proceed in this order)1. **What index does this index?** — Identify the domain, language (Korean?), time-series nature, and scale (N).2. **Mapping in general** — Check the review hooks in `reference/kb/field-types.md` · `reference/kb/dynamic-mapping-risks.md`.3. **Analyzers** — Check `reference/kb/analyzers-tokenizers.md` (search vs index analyzer, normalizer, nori). **If the nori grep returns 0 hits, state "not applicable"**.4. **Vector fields** — Check `reference/kb/knn-vector-field.md` (dimension/space_type/engine/mode consistency, immutability).5. **Templates** — `reference/kb/index-templates.md`. Along with the severity, provide a fix (mapping JSON diff) + a zero-downtime reindex/alias strategy.## Quick checklist- [ ] Is `dynamic` set to `strict`/`false` on production indexes (to prevent mapping explosion)?- [ ] Is sorting/aggregation/exact on `keyword` and full-text search on `text`? Are unused fields `index:false`/`doc_values:false`?- [ ] Does the `knn_vector` `dimension` match the model output, and is the `space_type` consistent with normalization?- [ ] Is the `engine` faiss/lucene (**migrate if nmslib**)? Are the core fields explicit in the mapping (to prevent dynamic inference)?- [ ] Are large vectors duplicated in `_source` → derived source (beware that nested/copy_to are unsupported)?- [ ] (Korean) Is nori configured with `decompound_mode`, a user dictionary, parts of speech, and a search-time `synonym_graph`?## KB (read and cite first)From `reference/kb/INDEX.md`, read the following, check against the "review hooks", and cite via the `source` URL:- `reference/kb/field-types.md` · `reference/kb/analyzers-tokenizers.md` · `reference/kb/knn-vector-field.md` · `reference/kb/index-templates.md` · `reference/kb/dynamic-mapping-risks.md`## DeliverableFor each finding: problem → violated principle (principles.md §)/KB source → mapping diff → verification (`_mapping`/`_analyze`). Because mappings are immutable, accompany any change with a zero-downtime reindex/alias strategy.

Frequently asked questions