← Explore all skills

SEARCH AND RETRIEVAL / elastic

Elasticsearch Search Relevance

Choose deterministic query rules or organic ranking changes from mappings and example searches.

“Improve Elasticsearch search relevance for content and catalog indices: pin or promote results with query rules (correct rule type, criteria, and rule-query wiring) and tune organic ranking with multi_match, field boosts, and analysis grounded in the index mapping. Use when search results rank poorly, a specific document must appear first for a query, or the user asks to tune full-text matching — not for ES|QL analytics, index ingest, or cluster health.”

01 / THE REASONING

Why this made the selection.

  • The decision table separates pinned/excluded documents from multi_match and analyzer tuning and warns against simulating deterministic pinning with extreme boosts.
  • Pin an explicitly requested document while preserving normal full-text ranking for other queries.

02 / THE REVIEW RECORD

What we actually inspected.

Source review has boundaries.
A clear record is more useful than a “safe” badge.

Material inspected

  • skills/elasticsearch/elasticsearch-search-relevance/SKILL.md
  • LICENSE
  • README.md

Our findings

  • The decision table separates pinned/excluded documents from multi_match and analyzer tuning and warns against simulating deterministic pinning with extreme boosts.
  • Creating a ruleset alone does not pin a document; the search must include a rule query with the ruleset identifier and matching criteria.

Not established by this review

  • Third-party instructions and helpers were not executed; service access, host compatibility and outcomes remain untested.
  • Not executed: it was not installed or run.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

Add a skill to your workflow.

Upstream setup instructions ↗

DOCUMENTED COMMAND

npx skills add elastic/agent-skills/skills/elasticsearch/elasticsearch-search-relevance

Run in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above.

Optional: install the reviewed revision

Keeps the original source and installer version where recorded, while leaving your AI tools and installation scope for you to choose.

npx skills add https://github.com/elastic/agent-skills/tree/baa511126ba2dc37b52e273b52734f8e4e0d323c/skills/elasticsearch/elasticsearch-search-relevance
  1. Install the pinned directory interactively and retain its referenced files; inspect the source before granting tool access.
  2. Collect representative queries and judged results, inspect mapped text fields, choose pin/exclude versus organic boosts and evaluate the full query set.

Before you start

  • Configured elastic CLI with stack es support, compatible Elasticsearch deployment and scoped credentials; query-rule permissions for managed promotion

04 / FOLLOW THE EVIDENCE

The source trail.

Our notes are separate from the original resource.
Check upstream before adopting a new version.

  1. https://github.com/elastic/agent-skills/blob/baa511126ba2dc37b52e273b52734f8e4e0d323c/skills/elasticsearch/elasticsearch-search-relevance/SKILL.md

    Supports: summary, review, install, access, limitations

  2. Pinned LICENSE ↗Checked

    https://github.com/elastic/agent-skills/blob/baa511126ba2dc37b52e273b52734f8e4e0d323c/LICENSE

    Supports: license

  3. Pinned README.md ↗Checked

    https://github.com/elastic/agent-skills/blob/baa511126ba2dc37b52e273b52734f8e4e0d323c/README.md

    Supports: summary, review, install, access, limitations

  4. https://raw.githubusercontent.com/elastic/agent-skills/baa511126ba2dc37b52e273b52734f8e4e0d323c/skills/elasticsearch/elasticsearch-search-relevance/SKILL.md

    Supports: upstreamDescription, review.notTested, review.reviewedAt, review.findings

Evidence & Ask