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

search-router

Route search queries to TLDR Search, AST-grep, or Grep based on query type.

8|1|Updated Jan 4, 2026
Search Tags:#search#token efficiency#code exploration#router#ast-grep#tldr
One-click install
npx skills add https://github.com/scooter-lacroix/Maestro --skill search-router
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: search-router
Source: https://github.com/scooter-lacroix/Maestro/tree/main/maestro/skills/research/search-router
Command: npx skills add https://github.com/scooter-lacroix/Maestro --skill search-router

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill intelligently selects the most efficient search tool based on the query type, optimizing for token usage and accuracy in code exploration and information retrieval.

Core Features & Use Cases

  • Dynamic Tool Selection: Routes queries to specialized search tools like TLDR Search, AST-grep, or Grep based on whether the query is for code exploration, structural patterns, semantic meaning, or literal text.
  • Token Efficiency: Prioritizes token-efficient tools like TLDR Search for code symbol and call graph searches, significantly reducing LLM context window usage.
  • Use Case: When asked to "find all usages of the DataPoller class," the router directs the query to TLDR Search, saving tokens compared to a general grep.

Quick Start

Use the search-router skill to find where 'spawn_agent' is implemented in the codebase.

Frequently Asked Questions about search-router

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

FAQPage Schema
How do I optimize token usage when searching for code symbols and call graphs?▼

To optimize token usage for code symbol and call graph searches, route queries to specialized tools like TLDR Search instead of general grep, significantly reducing LLM context window consumption while maintaining search accuracy.

What is the best way to search for structural code patterns without writing complex regex?▼

The best way to search for structural code patterns is using AST-grep, which matches Abstract Syntax Tree structures directly, enabling accurate structural queries without relying on brittle regular expressions.

How do I route code exploration queries to the most appropriate search tool?▼

Route code exploration queries by evaluating query type: direct code symbols to TLDR Search, structural pattern matching to AST-grep, and reserve Grep strictly for literal text matches as a last resort.

Does grep work for semantic code understanding and finding class implementations?▼

Grep does not work well for semantic code understanding because it only matches literal text. Finding class implementations like 'DataPoller' is more token-efficient when routed to TLDR Search.

When should I use AST-grep instead of TLDR Search for code exploration?▼

Use AST-grep instead of TLDR Search when your query specifically targets structural pattern matching within the Abstract Syntax Tree, whereas TLDR Search is prioritized for locating code symbols and analyzing call graphs.

Why does my literal text search return too many irrelevant code matches?▼

Literal text search returns irrelevant matches because it lacks semantic understanding. Routing structural or semantic queries to AST-grep or TLDR Search filters results by code structure and symbol meaning rather than raw text.

Related Skills

Explore More Software Engineering Skills→
parcadeiparcadei
3.9k

search-router

Route search queries to the most token-efficient tool by query type.

Community
Intermediate
IndianBoy42IndianBoy42

ast-grep-explore

Search codebases using AST patterns to reveal structural code relationships.

Community
Intermediate
tianzecntianzecn
2

deep-analysis

Automate deep code analysis across multi-file codebases with semantic search.

Community
Advanced
ArchitectVS7ArchitectVS7

AgentDB Vector Search

Implements semantic vector search with AgentDB for document retrieval and similarity matching.

Community
Advanced