add-lang

Integrate new tree-sitter language grammars into the CodeGraph extraction pipeline.

12|3|Updated Jun 17, 2026
One-click install
npx skills add https://github.com/phuhao00/bony-agent --skill add-lang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-lang
Source: https://github.com/phuhao00/bony-agent/tree/main/vendor/codegraph/.claude/skills/add-lang
Command: npx skills add https://github.com/phuhao00/bony-agent --skill add-lang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires node, git, gh, claude-cli, vitest, and includes scripts (resource) components.

What problem does it solve?

This skill automates the complex, multi-step process of adding new tree-sitter language support to the CodeGraph extraction pipeline, ensuring consistent grammar wiring and high-quality indexing.

Core Features & Use Cases

  • Automated Wiring: Handles the registration of new languages across types, extractors, and configuration files.
  • Quality Assurance: Performs health checks on WASM grammars and verifies extraction accuracy against real-world repositories.
  • Benchmarking: Automatically evaluates the retrieval value of the new language support using A/B testing on popular repositories.

Quick Start

Invoke the add-lang skill by providing the name of the programming language you wish to integrate into the CodeGraph system.

Frequently Asked Questions about add-lang

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

FAQPage Schema
How do I add a new tree-sitter grammar to a codebase extraction pipeline?

To automate tree-sitter language support integration, wire new grammars across types, extractors, and configurations, then run health checks on WASM grammars and verify extraction accuracy against real-world repositories.

What is automated tree-sitter language integration for codebase analysis?

Automated tree-sitter language integration is the process of autonomously registering new programming language grammars into an extraction pipeline. It handles wiring, testing, and benchmarking to expand codebase analysis capabilities for diverse languages.

Do I need node and git to automate CodeGraph language support?

Yes, you need node and git to execute the full verification and evaluation workflow. You also need gh and a configured claude CLI to autonomously wire new tree-sitter language grammars into the extraction pipeline.

How does benchmarking evaluate new tree-sitter language support?

Benchmarking evaluates new tree-sitter language support by automatically running A/B testing on popular repositories. This testing assesses the retrieval value of the newly integrated language grammar within the codebase extraction pipeline.

What's the best way to verify extraction accuracy for a new tree-sitter grammar?

The best way to verify extraction accuracy is to perform health checks on WASM grammars and test the extraction against real-world repositories. This quality assurance ensures the new language support indexes codebases correctly.

What are the limitations of autonomously integrating tree-sitter language support?

The automation requires specific dependencies including node, git, gh, claude CLI, and vitest. Without this exact environment configured, the full verification, benchmarking, and wiring workflow for new language grammars cannot execute.