skills.rest
ArdurAI
ArdurAIOFFICIAL
Explore all skills by this author →
GitHub

god-search-engineering

Engineer search systems across Elasticsearch, OpenSearch, Typesense, and Apache Solr.

1|Updated Apr 23, 2026
Search Tags:#vector search#elasticsearch#opensearch#solr#typesense#search engineering#relevance engineering
One-click install
npx skills add https://github.com/ArdurAI/god-skill-suite --skill god-search-engineering
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: god-search-engineering
Source: https://github.com/ArdurAI/god-skill-suite/tree/main/skills/god-search-engineering
Command: npx skills add https://github.com/ArdurAI/god-skill-suite --skill god-search-engineering

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires elasticsearch, opensearch, typesense, solr, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill unit offers a comprehensive suite of AI-powered search and relevance engineering skills, solving complex challenges in information retrieval, data management, and user experience enhancement.

Core Features & Use Cases

  • Search Engineering Expertise: Covers Elasticsearch, OpenSearch, Typesense, Apache Solr, and more, with deep knowledge in indexing, query processing, relevance, and performance tuning.
  • Vector Search: Integrates vector search capabilities for semantic similarity and approximate nearest neighbor search.
  • Hybrid Search: Combines keyword and vector search for improved relevance.
  • Relevance Tuning: Offers techniques for BM25 scoring, function score queries, and learning to rank.
  • Aggregations: Provides capabilities for complex analytics and insights from search data.
  • Performance Engineering: Covers sharding strategies, replica management, indexing performance, JVM tuning, and node roles.
  • ILM/ISM: Automates the lifecycle management of indices for efficient data storage and retrieval.
  • Typesense Integration: Offers integration with Typesense for typo-tolerant search.
  • Relevance Evaluation: Includes offline and online metrics for evaluating search quality.
  • Cross-Domain Connections: Explores the intersection of search engineering with AI, machine learning, and data analytics.

Quick Start

Use the god-search-engineering skill to analyze the relevance of search results for the 'products' collection in Typesense.

Frequently Asked Questions about god-search-engineering

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I implement vector search for semantic similarity in Elasticsearch?▼

Vector search in Elasticsearch enables semantic similarity and approximate nearest neighbor matching. You can combine it with keyword search to create hybrid search, significantly improving query relevance across large document collections.

What is the best way to tune BM25 scoring and relevance in OpenSearch?▼

Relevance tuning in OpenSearch involves adjusting BM25 scoring parameters and utilizing function score queries. You can further optimize search quality by implementing learning to rank models and evaluating both offline and online relevance metrics.

Does Typesense support typo-tolerant search out of the box?▼

Typesense provides built-in typo-tolerant search capabilities for fast, error-corrected queries. You can integrate it directly within your search engineering stack to handle user spelling mistakes and improve overall search user experience.

How do I manage indexing performance and sharding strategies in Apache Solr?▼

Performance engineering in Apache Solr requires optimizing sharding strategies, replica management, and JVM tuning. Proper node role configuration and indexing performance enhancements ensure efficient data storage and high-throughput query processing.

When do I need Index Lifecycle Management (ILM) for my search indices?▼

Index Lifecycle Management (ILM) automates index retention and storage transitions as your data ages. You need ILM to efficiently manage storage costs, delete obsolete indices, and maintain retrieval performance across large time-series datasets.

Can I combine keyword and vector search to improve search relevance?▼

Hybrid search combines traditional keyword matching with vector search semantic similarity. This approach maximizes search relevance by leveraging both exact term matching and contextual meaning, yielding more accurate search results.

Related Skills

Explore More Software Engineering Skills→
patrykkopycinskipatrykkopycinski
6

zero-to-elastic

Provision Elasticsearch infrastructure and generate client connection snippets.

Community
Advanced
ContextJet-aiContextJet-ai
29

add-llm-evals

Add offline and online evaluation scoring to LLM and agent applications.

Official
Advanced
peteknowsaipeteknowsai

stoolap

Organize and query local structured data with embedded SQL and vector embeddings.

Community
Advanced
RepairYourTechRepairYourTech
6

meilisearch

Integrates Meilisearch engine for typo-tolerant full-text search with index management, filtering, faceting, relevancy tuning, and geo search support.

Community
Advanced