- Home
- Skills
- Data & Databases
- json-to-types
Json to Types
Automatically transform JSON files or raw strings into production-ready TypeScript interfaces or Python dataclasses.
$12
Works with the AI Agents you already use
json-to-types
Example session with this skill installed
Please convert the data/api_response.json file into TypeScript interfaces and save the result to types.ts.
- Read your context and instructions
- Compiled the json-to-types
// Generated from: data/api_response.json
export interface User {
id: number;
userName: string;
email: string;
age?: number; // optional — not always present
roles: string[];
}
export type UserList = User[];
Output saved: ./types.ts (5 interfaces generated)
Connects securely to your tools. The creator never sees your data.
About this skill
What it does
The JSON to Types Converter handles the tedious task of manually defining data structures for API responses or JSON datasets. It recursively analyzes any JSON source—whether a local file or a raw string—and generates production-ready TypeScript interfaces or Python dataclasses.
Why use this skill
While you can ask a standard LLM to "convert this JSON," this skill provides a structured developer workflow that an LLM alone often misses. It auto-detects your project's language environment, handles singularization of array roots (e.g., turning users.json into a User interface), manages complex union types for mixed arrays, and follows language-specific best practices like snake_case conversion for Python and Record<string, unknown> for dynamic objects.
Supported tools
- TypeScript: Generates exported interfaces with optional property support and type aliases.
- Python: Generates @dataclass definitions using the
typingmodule and__future__annotations. - Project Detection: Uses Glob to automatically check for
tsconfig.jsonorpyproject.tomlto choose the right language.
The Output
It generates a clean, well-commented types.ts or models.py file and provides a summary report of the inferred schema, including which fields were marked as optional based on property presence across array items.
- Does not support recursive self-referencing types.
- Remote URL fetching is not supported; files must be local or raw text.
- Limited to basic primitive inference for dates.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 7 months ago
Requires
Permissions
No special permissions declared or detected