ast-grep

Converts natural language queries into ast-grep rules for structural code search.

6|2|Updated Jan 11, 2026
One-click install
npx skills add https://github.com/trotsky1997/My-Claude-Agent-Skills --skill ast-grep-trotsky1997
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ast-grep
Source: https://github.com/trotsky1997/My-Claude-Agent-Skills/tree/main/ast-grep
Command: npx skills add https://github.com/trotsky1997/My-Claude-Agent-Skills --skill ast-grep-trotsky1997

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps translate natural language queries into ast-grep rules for structural code search, enabling precise matching of code patterns across large codebases.

Core Features & Use Cases

  • Generate ast-grep rules from natural language queries to locate code patterns based on structure rather than text.
  • Provide example rules and a workflow to test them against sample code with the ast-grep CLI.
  • Use Case: Quickly identify all async functions that contain await expressions in a JavaScript project to assess async patterns.

Quick Start

Use the ast-grep skill to generate a rule that finds all async functions containing await in a sample file and verify it with the ast-grep tool.

Frequently Asked Questions about ast-grep

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

FAQPage Schema
How do I find specific code patterns using AST instead of plain text search?

Structural code search uses Abstract Syntax Trees to match code constructs based on syntax rather than text. By translating natural language queries into ast-grep rules, you can precisely locate patterns like async functions containing await across large codebases.

What is the best way to generate structural code search rules from natural language?

Generating structural code search rules involves translating natural language queries into ast-grep patterns, inside/has relations, and metavariables. This approach enables structural code intelligence and auditing workflows to locate code constructs across multiple programming languages.

Can I use tree-sitter based AST search to audit large codebases?

Yes, you can audit large codebases by generating testable ast-grep rules from natural language queries. This workflow allows you to validate the structural code search results against your real codebase using the ast-grep CLI tool.

How does AST-based code analysis handle different programming languages?

AST-based code analysis leverages tree-sitter to parse and locate code constructs across different languages. The generated ast-grep rules use structural patterns and metavariables to enable precise code intelligence independent of specific programming language syntax.

Do I need the ast-grep CLI installed to test generated code search rules?

Yes, you need the ast-grep CLI installed to test generated code search rules. The skill provides a workflow to test the generated structural rules against sample code and validate the matching results in your actual codebase.