skills.rest
starlink-awaken
starlink-awakenCOMMUNITY
Explore all skills by this author →
GitHub

Parser

A JSON-based content ingestion and normalization system that converts raw feeds and documents into structured, uniform data for downstream use.

1|Updated Jun 10, 2026
Search Tags:#schema#json#deduplication#parser#batch-processing#entity-extraction#content-detection
One-click install
npx skills add https://github.com/starlink-awaken/pai-universal --skill parser-starlink-awaken
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Parser
Source: https://github.com/starlink-awaken/pai-universal/tree/main/templates/packs/Utilities/src/Parser
Command: npx skills add https://github.com/starlink-awaken/pai-universal --skill parser-starlink-awaken

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires uuid.

What problem does it solve?

This skill converts URLs, files, and content into a deterministic JSON schema, extracting entities and enabling batch processing for consistent data pipelines.

Core Features & Use Cases

  • Deterministic JSON schema for diverse content types (articles, videos, PDFs, newsletters, Twitter threads)
  • Entity extraction with GUID-based deduplication across content
  • Batch processing and content-type routing to specialized workflows
  • Validation against the canonical schema and ready-to-store outputs

Quick Start

Parse a URL or list of URLs to produce deterministic JSON outputs.

Frequently Asked Questions about Parser

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

FAQPage Schema
How do I parse URLs into a deterministic JSON schema with entity extraction?▼

Batch processing URL content involves passing a list of URLs to detect content types and route them to specialized extractors. It outputs validated, deterministic JSON schema objects with globally deduplicated entities for consistent data pipelines.

How does entity deduplication work when extracting JSON from multiple URLs?▼

Entity deduplication uses a global index with GUID-based matching to cross-reference extracted entities across multiple parsed URLs. This ensures that identical entities identified in articles, PDFs, or Twitter threads are unified rather than duplicated in the final JSON output.

Can I extract structured JSON from PDFs and Twitter threads in the same batch?▼

Yes, you can extract structured JSON from PDFs and Twitter threads in the same batch. The parser detects the content type for each URL and automatically routes it to the appropriate specialized extractor, normalizing the diverse outputs against a canonical deterministic schema.

What is the best way to convert newsletters and videos into ready-to-store JSON?▼

The best way to convert newsletters and videos into ready-to-store JSON is using a parser that validates extracted content against a canonical schema. This approach detects the content type, extracts entities, and deduplicates them globally to ensure the output is immediately ready for storage.

Does the parser require any dependencies to validate extracted JSON schemas?▼

Yes, the parser requires the uuid dependency to generate globally unique identifiers for entity deduplication. This allows the system to maintain a global index that cross-references and validates extracted entities against the deterministic JSON schema.

Related Skills

Explore More Data & Analytics Skills→
AcosmiAcosmi
6

web-fetch

Fetch web pages via HTTP GET and extract readable content in markdown, text, or raw modes.

Community
Intermediate
1479089714790897
7

kwp-data-validate-data

Validate analytical reports and SQL queries for methodological soundness and calculation accuracy.

Community
Advanced
ryan-mtryan-mt
3

schema-markup

Implement schema.org JSON-LD markup and validate with Rich Results Test.

Community
Advanced
ngochuy13ngochuy13

data-research

Convert research inputs into structured, deduplicated tracker entries with raw-source archiving.

Community
Advanced