source-normalization

Normalize files, URLs, and pasted text into citation-ready metadata with checksums.

1|2|Updated Dec 3, 2025
One-click install
npx skills add https://github.com/jayhjenkins/ProductOSv0.2 --skill source-normalization
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: source-normalization
Source: https://github.com/jayhjenkins/ProductOSv0.2/tree/main/.claude/skills/context-assembly/source-normalization
Command: npx skills add https://github.com/jayhjenkins/ProductOSv0.2 --skill source-normalization

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Normalize diverse inputs (files, URLs, and pasted text) into stable citations with IDs, checksums, and metadata to support reliable research workflows.

Core Features & Use Cases

  • Citeable normalization: Convert inputs into structured citation entries with a stable ID and checksum.
  • Deduplication and registry: Maintain a central sources.json registry preventing duplicates and enabling change detection.
  • Frontmatter-driven metadata: Extract and harmonize metadata from source files, or fetch metadata from URLs when available.

Quick Start

Normalize a mix of a local file, a URL, and pasted text to produce canonical citations in inputs/ and update citations/sources.json.

Frequently Asked Questions about source-normalization

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

FAQPage Schema
How do I normalize mixed input files and URLs into structured citations?

To normalize mixed inputs into structured citations, apply hash-based IDs and checksum calculations to local files, URLs, and pasted text. This process extracts frontmatter-driven metadata to produce stable, cite-ready entries in a central registry.

What is a sources.json registry and how does it handle citation deduplication?

A sources.json registry is a centralized metadata store that prevents duplicate citations by applying hash-based IDs and checksum calculations. It detects changes and deduplicates entries across diverse inputs like files, URLs, and pasted text.

Can I extract metadata from files and URLs for research workflows?

Yes, you can extract metadata from files and URLs for research workflows. The normalization process harmonizes frontmatter-driven metadata from local source files and fetches available metadata from URLs to create structured citation entries.

How do I generate stable IDs and checksums for pasted text and local files?

You generate stable IDs and checksums for pasted text and local files by applying hash-based normalization techniques. This converts diverse input formats into structured, citation-ready metadata within a deduplicated sources.json registry.

Does source normalization work without external dependencies?

Yes, source normalization works without external dependencies. The process uses built-in hash-based IDs, checksum calculations, and frontmatter extraction to normalize local files, URLs, and pasted text into a sources.json registry.

When do I need checksum calculations for knowledge management citations?

You need checksum calculations for knowledge management citations when maintaining a central sources.json registry. Checksums enable deduplication and change detection across mixed inputs, ensuring stable metadata for research workflows.