skills.rest
SpillwaveSolutions
SpillwaveSolutionsOFFICIAL
Explore all skills by this author →
WebsiteGitHub

vector-search

Perform semantic vector search over agent-memory with hybrid BM25+vector fusion.

14|3|Updated Jan 29, 2026
Search Tags:#BM25#semantic-search#agent-memory#hybrid-search#vector-embeddings#search-query
One-click install
npx skills add https://github.com/SpillwaveSolutions/agent-memory --skill vector-search-spillwavesolutions
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vector-search
Source: https://github.com/SpillwaveSolutions/agent-memory/tree/main/plugins/memory-query-plugin/skills/vector-search
Command: npx skills add https://github.com/SpillwaveSolutions/agent-memory --skill vector-search-spillwavesolutions

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Semantic vector search enables retrieving conceptually related discussions from the agent-memory store by evaluating semantic similarity between queries and stored content.

Core Features & Use Cases

  • Semantic vector search for memory retrieval: surface related discussions based on meaning rather than exact keywords.
  • Hybrid BM25 + vector fusion: combine keyword precision with semantic similarity for robust results.
  • Use Case: when users need to discover related topics or similar conversations that keyword search misses, or while exploring tangential topics.

Quick Start

To begin, ensure the memory daemon is running and then execute a vector-search query, for example: memory-daemon teleport vector-search -q "authentication patterns"

Frequently Asked Questions about vector-search

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

FAQPage Schema
How does semantic vector search work for finding related discussions?▼

Semantic vector search retrieves conceptually related discussions by evaluating semantic similarity between search queries and stored content, surfacing topics based on meaning rather than exact keyword matches.

How do I perform a hybrid search combining BM25 and vector embeddings?▼

Hybrid BM25 and vector fusion combines keyword precision with semantic similarity to deliver robust search results, configurable through specific search modes, top-k values, and targets.

When should I use semantic search instead of traditional keyword search?▼

Semantic search is necessary when keyword results are weak, allowing you to discover related topics or similar conversations that exact keyword matching misses while exploring tangential topics.

Can I configure the top-k results and search targets in vector search?▼

Vector search provides configurable search modes with a range of options for top-k results and targets, allowing you to customize the retrieval of related discussions.

Do I need a memory daemon running to execute a vector search query?▼

Yes, you must ensure the memory daemon is running before executing a vector search query to successfully retrieve conceptually related discussions from the agent-memory store.

Related Skills

Explore More Software Engineering Skills→
Pr0fe5s0rPr0fe5s0r
74

stixdb-cli-memory

Load, store, and retrieve AI agent memory via StixDB.

Community
Intermediate
justrachjustrach

emdb-search

Search EmergentDB for similar vectors and rank documents by similarity.

Community
Intermediate
NotysotyNotysoty
9

Hybrid Search Architect

Design hybrid retrieval pipelines combining dense vector search with BM25 keyword matching.

Community
Advanced
mwathibenmwathiben

hybrid-search-implementation

Design hybrid retrieval fusing vector similarity with keyword matching.

Community
Advanced