Verified:GitHub

deep-research

Conduct citation-backed research with source verification and multi-source synthesis.

280|30|Updated Mar 30, 2026

Search Tags:#source verification #deep research #citation tracking #research reports #credibility scoring #multi-source synthesis #HTML and PDF

Ready to run

npx skills add https://github.com/Undertone0809/rudder --skill deep-research-undertone0809

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/Undertone0809/rudder/tree/main/server/resources/community-skills/deep-research
Command: npx skills add https://github.com/Undertone0809/rudder --skill deep-research-undertone0809

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires weasyprint, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Deep Research turns ambiguous questions into enterprise-grade, citation-backed reports with verification loops, reducing the risk of weak sourcing or unsupported claims.

Core Features & Use Cases

Citation-backed research reporting: Builds reports grounded in 10+ sources with immediate inline citations.
Credibility scoring & validation: Uses citation and structure validators to detect fabricated or suspicious references.
Concrete, case-grounded synthesis: Translates abstract findings into mini-cases, counterexamples, and applied scenarios (clearly labeled when hypothetical).
HTML + PDF packaging: Produces Markdown plus McKinsey-style HTML and WeasyPrint-ready PDF outputs.

Quick Start

Ask for a report by saying: deep research in ultradeep mode: compare PostgreSQL vs Supabase for our stack.

Frequently Asked Questions about deep-research

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

FAQPage Schema

How do I generate research reports with inline citations and source verification?▼

To generate research reports with inline citations, this Skill conducts multi-source synthesis and credibility scoring across 10+ sources, validating references to detect fabricated or suspicious citations before outputting Markdown, HTML, and PDF files.

Can I export Markdown research reports into HTML and PDF formats?▼

Yes, you can export Markdown research reports into HTML and PDF formats. The Skill packages verified, citation-backed findings into McKinsey-style HTML and WeasyPrint-ready PDF outputs alongside the base Markdown file.

What is source credibility scoring and how does it validate citations?▼

Source credibility scoring evaluates the quality and persistence of references during multi-source synthesis. Citation and structure validators run verification loops to detect fabricated or suspicious references, ensuring evidence triangulation for complex decision-making.

Does WeasyPrint support PDF generation for multi-source synthesis reports?▼

WeasyPrint supports PDF generation for multi-source synthesis reports. It is a required dependency for packaging the verified, citation-backed research findings into the final WeasyPrint-ready PDF output format.

How do I compare technologies or analyze trends using citation-backed research?▼

To compare technologies or analyze trends using citation-backed research, the Skill applies structured multi-phase execution to your topic, translating abstract findings into mini-cases and applied scenarios with immediate inline citations from 10+ sources.

What are the limitations of automated citation tracking in research reports?▼

Automated citation tracking limitations include potential gaps in evidence triangulation for highly niche topics. While validators detect suspicious references, users must still review synthesized mini-cases and counterexamples, especially when applied scenarios are labeled as hypothetical.