deep-research

Gather sources, validate claims, and generate citation-backed research reports.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/samuelcastro/noter --skill deep-research-samuelcastro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/samuelcastro/noter/tree/main/.agents/skills/deep-research
Command: npx skills add https://github.com/samuelcastro/noter --skill deep-research-samuelcastro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill enables end-to-end, citation-backed multi-source research workflows by coordinating parallel source retrieval, evidence persistence, and structured report generation across multiple providers, with robust validation and provenance tracking.

Core Features & Use Cases

  • Multi-provider search and evidence triangulation to support complex questions
  • Stable citation management with sources.jsonl, evidence.jsonl, and claims.jsonl artifacts
  • Progressive report generation with bibliography and methodology appendix
  • Automated verification and quality gates to ensure claims are traceable and reproducible

Quick Start

Ask the system to perform a multi-source research task and produce a citation-backed, structured report.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I generate a research report with automated citation tracking and evidence verification?

Multi-source research with citations is a process of gathering evidence from multiple providers, triangulating perspectives, and tracking provenance to ensure claims are reproducible. This Skill automates that pipeline end-to-end with quality gates.

What's the best way to triangulate evidence from multiple sources for a complex question?

The best way to triangulate evidence is through coordinated multi-provider search and persistent evidence tracking. This Skill validates extracted claims against gathered sources to ensure traceability before generating a structured report.

Can I use this multi-source research workflow for questions requiring multiple perspectives and reproducible outputs?

Yes, this workflow is explicitly designed for complex questions requiring multiple perspectives and evidence triangulation. It applies automated verification quality gates to ensure claims are traceable and outputs are reproducible.

How does evidence persistence work during report generation?

Evidence persistence works by saving retrieved data into stable artifacts like sources.jsonl, evidence.jsonl, and claims.jsonl. This ensures that every claim extracted and validated during report generation remains traceable to its origin.

Do I need any external dependencies to run this citation-backed research pipeline?

No external dependencies are required to run this citation-backed research pipeline. The Skill operates independently using its internal scripts to coordinate source retrieval, evidence persistence, and structured report generation.