research-process-source

Create structured research notes from URLs, PDFs, and documents.

Updated Jun 6, 2026

Search Tags:#research automation #document analysis #source processing #structured notes #evidence tagging

Ready to run

npx skills add https://github.com/kenziecreative/kenzie-creative --skill research-process-source

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: research-process-source
Source: https://github.com/kenziecreative/kenzie-creative/tree/main/researcher/skills/research-process-source
Command: npx skills add https://github.com/kenziecreative/kenzie-creative --skill research-process-source

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires tvly, firecrawl-cli, playwright, pdftotext, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the process of creating structured research notes from various sources like URLs, PDFs, or documents, streamlining the research workflow.

Core Features & Use Cases

Source Processing: Ingests and processes URLs, PDFs, or documents.
Structured Notes: Generates structured research notes with key findings, credibility assessments, and origin chains.
Use Case: For a researcher who needs to process multiple sources quickly and accurately, this Skill can save time by automating the creation of detailed research notes.

Quick Start

Run the 'research-process-source' skill with the URL or file path of the source you want to process.

Frequently Asked Questions about research-process-source

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

FAQPage Schema

How do I automate research note creation from PDFs and URLs?▼

Structured research notes are documents generated by extracting key findings, claims with evidence-quality tags, and origin chains from URLs, PDFs, or documents. They provide a standardized format for organizing information and assessing source credibility during research workflows.

How do I extract claims and tag evidence quality from source documents?▼

To extract claims and tag evidence quality, you process your source documents through an automated extraction pipeline that identifies key findings and applies credibility assessments. The system registers sources in a registry and writes structured notes to a designated directory.

Do I need playwright and pdftotext to process research sources?▼

Yes, you need extraction dependencies like playwright for web URLs and pdftotext for PDF documents to process research sources effectively. These tools enable the automated content ingestion required before generating structured notes.

Can I process multiple URLs and PDFs into a structured research registry?▼

Yes, you can process multiple URLs and PDFs into a structured research registry. The tool ingests various source types, registers each source in a central registry, and outputs structured notes with credibility assessments under a designated directory.

What is the best way to organize research findings from multiple document types?▼

The best way to organize research findings from multiple document types is using an automation tool that standardizes output into structured notes. It extracts key findings, applies evidence-quality tags, and maintains a source registry to track origin chains across URLs and PDFs.