skills.rest
anortham
anorthamCOMMUNITY
Explore all skills by this author →
GitHub

smart-search

Select semantic, text, or symbol search based on query intent.

3|Updated May 29, 2026
Search Tags:#search#semantic#text#symbols#cross-language
One-click install
npx skills add https://github.com/anortham/miller --skill smart-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: smart-search
Source: https://github.com/anortham/miller/tree/main/.claude/skills/smart-search
Command: npx skills add https://github.com/anortham/miller --skill smart-search

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automatically selects the optimal search strategy (semantic for concepts, text for exact terms, symbols for definitions) to quickly surface relevant code, reducing wasted time and token usage.

Core Features & Use Cases

  • Semantic search for conceptual understanding across languages
  • Text search for exact API names and strings
  • Symbol search for definitions and API contracts
  • Hybrid mode when unsure to maximize coverage

Quick Start

Ask it to find "authentication logic" and watch it choose semantic search, then refine with a precise term if needed.

Frequently Asked Questions about smart-search

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

FAQPage Schema
How do I search for code across repositories without manually choosing between semantic and text search?▼

Smart search automatically selects the optimal strategy—semantic for concepts, text for exact terms, symbols for definitions—based on your query intent, eliminating manual mode selection and reducing token waste.

Can I search for code concepts across multiple programming languages at once?▼

Yes. Semantic search works cross-language, letting you find conceptual matches regardless of whether code is written in Python, JavaScript, Java, or other languages in your repositories.

What's the best way to find API definitions and symbol locations in large codebases?▼

Use symbol search mode, which locates function and class definitions directly. Smart search routes symbol queries automatically, surfacing exact definitions with file context and line numbers.

How does smart search decide between semantic, text, and symbol modes?▼

Smart search analyzes your query intent using a decision tree. Queries mentioning behavior or concepts trigger semantic search; exact API names or strings trigger text search; definition requests trigger symbol search.

Can I refine search results or explore file structures after getting initial matches?▼

Yes. Results include options to refine your search with additional terms and reveal full file structures, letting you drill down or broaden coverage based on what you find.

Related Skills

Explore More Software Engineering Skills→
AradotsoAradotso
7

codebase-memory-mcp-intelligence

Index source code into a persistent knowledge graph for structural queries.

Official
Advanced
pchalasanipchalasani
2.0k

session-search

Search past code agent sessions and summarize matching results with references.

Community
Advanced
massgenmassgen
1.1k

serena

Locate symbol definitions and references across multi-file codebases using LSP-powered analysis.

Official
Advanced
matt-rileymatt-riley
1

code-intelligence

Select LSP, rg, or semantic search for code analysis tasks.

Community
Advanced