skills.rest
mqzkim
mqzkimCOMMUNITY
Explore all skills by this author →
GitHub

data-transformer

Convert unstructured PDF, image, and HTML data into structured JSON.

Updated Mar 1, 2026
Search Tags:#ocr#data transformation#schema validation#pdf parsing#data normalization#html to json
One-click install
npx skills add https://github.com/mqzkim/trading --skill data-transformer-mqzkim
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-transformer
Source: https://github.com/mqzkim/trading/tree/main/.agents/skills/data-transformer
Command: npx skills add https://github.com/mqzkim/trading --skill data-transformer-mqzkim

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the conversion of unstructured data from various formats like PDFs, images, and HTML into structured JSON, making data easily processable.

Core Features & Use Cases

  • Data Conversion: Transforms PDFs, images, and HTML into structured JSON.
  • Data Normalization: Cleans and maps data to a defined schema.
  • Use Case: Convert a scanned PDF report into a JSON object that can be directly imported into a database.

Quick Start

Use the data-transformer skill to convert the file at '/path/to/document.pdf' to JSON using the schema defined in '/path/to/schema.json'.

Frequently Asked Questions about data-transformer

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

FAQPage Schema
How do I convert a PDF to JSON using a schema?▼

To convert a PDF to JSON, the Skill extracts text using OCR and normalizes the unstructured data against a defined Zod schema, outputting structured JSON ready for database ingestion.

Can I extract data from scanned images and normalize it?▼

Yes, you can extract data from scanned images by leveraging the Codex Vision API for OCR, which reads the visual media and normalizes the extracted text into a structured JSON format.

Does this approach support HTML to JSON conversion?▼

HTML to JSON conversion is fully supported, allowing you to transform unstructured HTML content into structured JSON objects mapped directly to your defined Zod schema.

What is the best way to validate extracted data from documents?▼

The best way to validate extracted document data is by mapping the normalized text output against Zod schemas during the transformation pipeline to ensure structural compliance.

Do I need a Zod schema to transform unstructured data?▼

Yes, a Zod schema is required to map and validate the extracted unstructured data, ensuring the final JSON output conforms strictly to your expected data structure.

Are there limitations when parsing visual media for data ingestion?▼

Limitations include dependency on the Codex Vision API for accurate OCR text extraction from visual media, meaning poor image quality can directly impact the final structured JSON output.

Related Skills

Explore More Data & Analytics Skills→
PoBrunoPoBruno
6

mcp-tool-schema

Define and validate MCP tool schemas with Zod inputs and ToolResult contracts.

Community
Advanced
JosephWoodallJosephWoodall
1

gene-database

Retrieve gene metadata from NCBI Gene databases by symbol or ID.

Community
Intermediate
urivauriva

p2b-document-pipeline

Optimize document ingestion with OCR and text parsing for multi-page PDFs.

Community
Advanced
manuelbrandner85manuelbrandner85

pdf

Extracts text, tables, and images from PDFs with OCR support.

Community
Advanced