tree-sitter-language-pack

Parse and analyze code across 306 languages using tree-sitter grammars.

26|2|Updated Jun 8, 2026
One-click install
npx skills add https://github.com/xberg-io/plugins --skill tree-sitter-language-pack
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tree-sitter-language-pack
Source: https://github.com/xberg-io/plugins/tree/main/plugins/tree-sitter-language-pack/.cursor-plugin/skills/tree-sitter-language-pack
Command: npx skills add https://github.com/xberg-io/plugins --skill tree-sitter-language-pack

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tree-sitter-language-pack, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill simplifies the process of parsing and analyzing code from a vast array of programming languages, enabling efficient handling of code intelligence for various applications.

Core Features & Use Cases

  • Polyglot Code Parsing: Supports parsing of 306 programming languages using tree-sitter grammars.
  • Code Intelligence: Extracts structure, imports/exports, symbols, docstrings, comments, and performs language detection.
  • Use Case: Ideal for scenarios where syntax trees or structured code metadata is required, such as building code indexes, feeding code to LLMs, linting syntax across multiple languages, or detecting file languages.

Quick Start

Parse a file 'example.py' using the 'tree-sitter-language-pack' skill.

Frequently Asked Questions about tree-sitter-language-pack

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

FAQPage Schema
How do I parse code and extract syntax trees across multiple programming languages?

You can parse code and extract syntax trees across 306 programming languages using tree-sitter grammars. This approach extracts structure, imports, exports, symbols, docstrings, and comments for efficient code intelligence.

What's the best way to build a code index for feeding source files to LLMs?

Building a code index for LLMs is best done by parsing source files with tree-sitter grammars to extract structured metadata. This provides syntax-aware analysis across 306 languages, ideal for feeding structured code to large language models.

Does tree-sitter support language detection and syntax analysis for Python, Node.js, and Rust?

Tree-sitter supports language detection and syntax analysis for Python, Node.js/TypeScript, Rust, and CLI environments. It parses 306 programming languages to extract symbols, imports, exports, and comments.

Can I use tree-sitter for linting syntax and detecting file languages across a large codebase?

Yes, you can use tree-sitter for linting syntax and detecting file languages across a large codebase. It parses 306 programming languages to perform syntax-aware tasks and extract structured code metadata.

How do I extract imports, exports, and docstrings from source code files?

To extract imports, exports, and docstrings from source code files, parse them using tree-sitter grammars. This enables syntax-aware extraction of structured code metadata across 306 programming languages.

Why use tree-sitter grammars instead of other code parsing tools for multi-language code intelligence?

Tree-sitter grammars provide efficient polyglot code parsing across 306 languages, extracting structure and symbols for code intelligence. This makes it ideal for building code indexes and performing syntax-aware tasks where multi-language support is required.