skills.rest
scooter-lacroix
scooter-lacroixCOMMUNITY
Explore all skills by this author →
Website𝕏@scooter_lacroixGitHub

leann-search

Search codebases semantically using the LEANN vector index.

8|1|Updated Jan 4, 2026
Search Tags:#codebase#search#semantic#ai coding#vector index#leann
One-click install
npx skills add https://github.com/scooter-lacroix/Maestro --skill leann-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: leann-search
Source: https://github.com/scooter-lacroix/Maestro/tree/main/maestro/skills/leann-search
Command: npx skills add https://github.com/scooter-lacroix/Maestro --skill leann-search

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables users to perform semantic, meaning-based searches across a codebase, going beyond simple keyword matching to understand conceptual queries.

Core Features & Use Cases

  • Conceptual Queries: Understand code related to abstract concepts like "authentication flow" or "provider architecture".
  • Pattern Discovery: Identify implementations of design patterns or recurring functionalities.
  • Related Code Identification: Find code snippets that are semantically similar, even if they use different terminology.
  • Use Case: When trying to understand how a complex system handles user sessions, you can ask "how does session management work" and get relevant code snippets.

Quick Start

Use leann search to find code related to authentication in the current project.

Frequently Asked Questions about leann-search

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

FAQPage Schema
How do I search a codebase for conceptual patterns instead of exact text?▼

Semantic code search enables conceptual queries by using a LEANN vector index to find code snippets matching the meaning of natural language requests, rather than exact text matches.

What is the best way to find implementation patterns like authentication flow in a large project?▼

Using semantic search allows you to discover implementation patterns by querying abstract concepts like "authentication flow," returning code snippets that are conceptually similar even if they use different terminology.

Do I need a pre-built vector index to perform semantic search on my codebase?▼

Yes, semantic search requires a pre-built LEANN vector index to look up related code snippets based on natural language queries and configurable result limits.

How does semantic code search identify related code when terminology differs?▼

Semantic code search identifies related code by comparing the conceptual similarity of code snippets against a natural language query, matching intent and meaning beyond exact keyword overlap.

Can I limit the number of results returned by a semantic code search query?▼

Yes, semantic search supports configurable result limits, allowing you to specify the maximum number of conceptually similar code snippets returned for a natural language query.

When should I use semantic search over exact keyword matching in a codebase?▼

Use semantic search when you need to understand abstract concepts, discover design patterns, or identify related code snippets where exact keyword matching fails due to differing terminology.

Related Skills

Explore More Software Engineering Skills→
parcadeiparcadei
3.9k

leann-search

Perform semantic search across a codebase using a vector index.

Community
Intermediate
ruskibeatsruskibeats

zoom-out

Summarize software module interactions for high-level system architecture review.

Community
Intermediate
sputnikussputnikus

karpathy-guidelines

Apply behavioral guidelines for AI coding assistants to reduce common LLM mistakes.

Community
Basic
BEKO2210BEKO2210
15

search

Search knowledge bases semantically with vector embeddings and keyword fallback.

Community
Advanced