jta

🥈Silver

Jta is an AI-powered JSON translation tool that uses agentic reflection with OpenAI, Anthropic, and Gemini APIs. It enables operations teams to automate JSON data translation for localization and i18n workflows. Connects to CLI tools and supports Go 1.25+.

12850Updated 4d ago

Intermediate30min to implementautomation

Saves ~135 min per use

Quick InstallView Source

git clone https://github.com/hikanner/jta.git

Works with:

Claude

Overview

About This Skill

How to Use

["Prepare your JSON file: Ensure the input JSON file is structured correctly and contains all the keys and values that need translation. Use a naming convention like `en.json` for English source files.","Run JTA via CLI: Execute the JTA command in your terminal, specifying the input file, source language, target language, and output file path. Example: `jta translate --input en.json --source en --target fr --output fr.json`","Review and validate: After translation, review the output JSON for any warnings or untranslatable strings. Use a JSON validator (e.g., `jq` or an online tool) to ensure the output is syntactically correct.","Integrate into workflow: Merge the translated JSON file into your i18n localization pipeline. Tools like `i18next` or `gettext` can consume these files directly.","Automate with CI/CD: Add JTA to your CI/CD pipeline (e.g., GitHub Actions, GitLab CI) to automate JSON translation for localization updates. Example: Trigger JTA on every push to the `main` branch for supported languages."]

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/hikanner/jta

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Use JTA to translate the JSON data in [INPUT_FILE_PATH] from [SOURCE_LANGUAGE] to [TARGET_LANGUAGE] for i18n localization. Ensure the output maintains the original structure, handles nested objects, and preserves all keys. Validate the translated JSON for syntax errors and output the result to [OUTPUT_FILE_PATH]. Include a summary of translation statistics (e.g., word count, character count) and any warnings for untranslatable strings.

Example Output

```json
{
  "app": {
    "welcome": "Bienvenue dans notre application!",
    "description": "Cette application vous aide à gérer vos tâches quotidiennes avec facilité.",
    "features": {
      "tasks": "Gestion des tâches",
      "reminders": "Rappels automatiques",
      "reports": "Rapports détaillés"
    },
    "errors": {
      "invalid_input": "Entrée invalide. Veuillez vérifier vos données.",
      "network_error": "Erreur de réseau. Veuillez réessayer plus tard."
    }
  },
  "metadata": {
    "translation_stats": {
      "total_words": 45,
      "translated_words": 43,
      "untranslatable_strings": ["app.welcome"]
    },
    "warnings": ["The string 'app.welcome' contains a proper noun that may not translate well."]
  }
}
```

Translation Summary:
- Source Language: English
- Target Language: French
- Total Words: 45
- Translated Words: 43
- Untranslatable Strings: 1 (app.welcome)
- Warnings: 1 (proper noun detected)

The JSON structure has been preserved, and all nested objects have been correctly translated. The output is valid JSON and ready for integration into the i18n workflow.