Search Services skills for AI agents
13 practitioner-grade search services skills, each a focused Markdown document your agent loads into context on demand. Search them from Claude Desktop, Cursor or any MCP client, or pull one with the CLI.
All 13 skills
- Algolia
Algolia: instant search, faceted search, InstantSearch.js/React, indexing, ranking, search analytics
257 lines - Elasticsearch
Elasticsearch: full-text search, aggregations, mapping, bulk indexing, Node.js client, relevance tuning
356 lines - Fuse Js
Fuse.js is a lightweight, powerful fuzzy-search library for JavaScript that runs entirely client-side. It's ideal for quickly adding flexible, typo-tolerant search capabilities to web applications without server-side infrastructure.
257 lines - Lunr
Lunr is a small, fast JavaScript search library for browsers and Node.js. It allows you to build a search index directly within your application, providing full-text search capabilities without a backend API or external service. It's ideal for static sites, documentation, or client-side applications requiring offline-capable search.
228 lines - Manticore Search
Manticore Search: open-source full-text search, SQL-based queries, real-time indexes, columnar storage, Elasticsearch-compatible API
247 lines - Meilisearch
Meilisearch: self-hosted search engine, typo tolerance, faceting, filtering, sorting, REST API, JavaScript SDK
291 lines - Opensearch
OpenSearch is a community-driven, open-source search and analytics suite derived from Elasticsearch. It's ideal for powering full-text search, log analytics, security monitoring, and real-time application monitoring, offering powerful scalability and flexibility for diverse data needs.
242 lines - Orama
Orama: client-side/edge full-text search engine, TypeScript-native, schema, search with filters, vector search, runs in browser/Node/edge
393 lines - Pagefind
Pagefind is a static search library that indexes your site at build time and provides a lightweight, client-side search UI. It's ideal for adding fast, serverless search to documentation, blogs, and static websites without external services.
237 lines - Quickwit
Quickwit: cloud-native search engine, log search, distributed tracing, sub-second search on object storage, Elasticsearch-compatible API
238 lines - Trieve
Trieve is an AI-native search and retrieval platform that offers hybrid search capabilities (semantic and full-text) and robust RAG (Retrieval Augmented Generation) infrastructure. Use Trieve when building AI applications that require accurate, context-aware information retrieval from custom data sources to ground LLM responses.
211 lines - Typesense
Typesense: open-source search, typo tolerance, faceting, curation, geo search, InstantSearch adapter
279 lines - Zinc Search
Zinc Search: lightweight Elasticsearch alternative, full-text search, log search, REST API, minimal resource usage
219 lines