ingest

Ingest URLs and local files into structured research notes with deduplication.

2|Updated Apr 17, 2026
One-click install
npx skills add https://github.com/jameswong2011/InvestmentVault --skill ingest-jameswong2011
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ingest
Source: https://github.com/jameswong2011/InvestmentVault/tree/main/.claude/skills/ingest
Command: npx skills add https://github.com/jameswong2011/InvestmentVault --skill ingest-jameswong2011

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the process of adding diverse content types—web URLs, local files, or inbox batches—into a structured research vault, reducing manual effort and ensuring consistency.

Core Features & Use Cases

  • Content Collection: Fetches web pages or reads local files (Markdown, PDF, CSV, TXT), preparing content for analysis.
  • Deduplication & Validation: Checks for duplicate sources within the same day or across days, blocking redundant ingestions.
  • Structured Research Note Creation: Generates research notes with detailed metadata, including summaries, evidence, and key segments.
  • Use Case: For analysts regularly capturing research from online articles or papers, this Skill automates ingestion, validation, and note structuring, saving hours of manual formatting.

Quick Start

Provide a URL, a local file path, or run the skill without arguments to process all inbox files automatically.

Frequently Asked Questions about ingest

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

FAQPage Schema
How do I automate content ingestion from web URLs and local files into structured research notes?

To automate content ingestion into structured research notes, provide a URL or local file path to fetch web pages or read Markdown, PDF, CSV, or TXT files. The system validates content, applies metadata tagging, and generates notes with summaries and evidence for research organization.

Can I prevent duplicate research sources when ingesting content from multiple files?

Yes, you can prevent duplicate research sources during content ingestion using built-in deduplication validation. The system checks for redundant sources within the same day or across days, actively blocking duplicate ingestions to maintain content validity.

What file formats are supported for automated ingestion into a research vault?

Supported file formats for automated ingestion into a research vault include Markdown, PDF, CSV, and TXT. The system reads these local files or fetches web pages, preparing the diverse content types for analysis and structured note generation.

Does the content ingestion tool work without specifying individual file paths?

Yes, the content ingestion tool works without specifying individual file paths. You can run it without arguments to automatically process all files currently sitting in your inbox, preparing them for analysis and note structuring.

What metadata is included when generating structured notes from ingested content?

When generating structured notes from ingested content, the metadata includes detailed summaries, evidence, and key segments. This comprehensive tagging enhances research organization and retrieval across your structured research vault.