source-intake

Standardize research sources into deduplicated Markdown records with provenance.

5|Updated Apr 13, 2026
One-click install
npx skills add https://github.com/caozx1110/ResearchLab --skill source-intake
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: source-intake
Source: https://github.com/caozx1110/ResearchLab/tree/main/skills/source-intake
Command: npx skills add https://github.com/caozx1110/ResearchLab --skill source-intake

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill solves the fragmentation of research materials by providing a unified, safe, and structured staging area for papers, repositories, datasets, and blogs before they are formally ingested into the knowledge base.

Core Features & Use Cases

  • Atomic Staging & Deduplication: Safely captures raw sources and performs identity-based deduplication to prevent redundant records.
  • Canonical Materialization: Converts heterogeneous sources into standardized, readable Markdown documents with preserved assets and metadata.
  • Use Case: When you discover a new paper or code repository, use this skill to create a stable, versioned record that is ready for deep analysis by the unit-analyst without manually managing file paths or parsing formats.

Quick Start

Use the source-intake skill to add the paper located at kb/raw/paper.pdf to the knowledge base as a complete unit.

Frequently Asked Questions about source-intake

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

FAQPage Schema
How do I standardize research papers and datasets into Markdown for knowledge management?

To standardize research intake, this skill captures heterogeneous sources like papers, repositories, and datasets, converting them into canonical Markdown documents with preserved metadata for your knowledge base.

What is the best way to deduplicate research sources in a local workspace?

Deduplicating research sources in a local workspace requires identity-based governance; this skill performs atomic staging to prevent redundant records and ensure immutable source capture.

Can I use this for staging raw PDF papers before deep analysis?

Yes, you can stage raw PDF papers by adding them to the local research workspace; the skill creates stable, versioned records ready for routing to specialized unit analyzers.

How does provenance governance work during research material ingestion?

Provenance governance during research material ingestion works by maintaining strict source identity tracking and routing prepared Markdown units to specialized analyzers while preserving original asset metadata.

Do I need a dedicated local research workspace for archiving research materials?

Yes, you need a dedicated local research workspace for archiving research materials; this skill operates within that environment to ensure immutable source capture and structured record creation.