Parser

Parse URLs, files, videos, and newsletters into deterministic JSON.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/larsboes/pai-marketplace --skill parser-larsboes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Parser
Source: https://github.com/larsboes/pai-marketplace/tree/main/marketplace/plugins/utilities/skills/Parser
Command: npx skills add https://github.com/larsboes/pai-marketplace --skill parser-larsboes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Parser converts disparate content sources (URLs, articles, PDFs, videos, newsletters) into a single, deterministic JSON structure that can be ingested by databases, newsletters, and analytics pipelines.

Core Features & Use Cases

  • Universal content handling: parse web pages, PDFs, videos, newsletters, and other formats into a canonical JSON schema.
  • Entity extraction, topic classification, link analysis, and extraction metadata to support downstream workflows, searchability, and segmentation.
  • Batch processing: process multiple items in one run for scalable data pipelines.
  • Validation: outputs adhere to the canonical schema and include extraction_metadata for traceability and quality control.

Quick Start

Submit a URL to parse and receive a deterministic JSON document ready for ingestion.

Frequently Asked Questions about Parser

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

FAQPage Schema
How do I convert web pages and PDFs into JSON for database ingestion?

To convert web pages and PDFs into JSON, you can use a parser to extract content and output a deterministic JSON document. This process ensures disparate sources adhere to a canonical schema, making them ready for reliable database ingestion and search.

Can I extract entities and classify topics from videos into a structured format?

Yes, you can extract entities and classify topics from videos by routing the content through domain-specific extractors. The parser performs topic classification, link analysis, and deduplicates entities with a global index to support downstream workflows.

Does batch processing work for parsing multiple URLs and newsletters at scale?

Batch processing does work for parsing multiple URLs and newsletters at scale. You can process multiple items in a single run to build scalable data pipelines, outputting validated JSON files suitable for analytics ingestion.

How are parsed JSON outputs validated to ensure reliable ingestion?

Parsed JSON outputs are validated against a canonical JSON schema to ensure deterministic structure. The validation process includes extraction metadata for traceability and quality control, confirming that the extracted content meets required specifications.

What is the best way to normalize disparate content sources into a single JSON schema?

The best way to normalize disparate content sources into a single JSON schema is to route them through domain-specific extractors. This approach transforms URLs, files, videos, and newsletters into a unified, deterministic JSON structure for consistent analytics.

Can I parse newsletters to extract content and links for segmentation?

Yes, you can parse newsletters to extract content and links for segmentation. The parser handles newsletter formats by performing link analysis and entity extraction, outputting deterministic JSON that supports downstream searchability and audience segmentation.