deep-research

Automate multi-source research and generate citation-backed reports with provenance.

Updated Apr 17, 2026
One-click install
npx skills add https://github.com/hackfest-dev/HF26-24 --skill deep-research-hackfest-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/hackfest-dev/HF26-24/tree/main/.agents/skills/deep-research
Command: npx skills add https://github.com/hackfest-dev/HF26-24 --skill deep-research-hackfest-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Deep Research delivers citation-tracked reports with an evidence store and provenance tracking, enabling rigorous multi-source analysis and decision-grade outputs.

Core Features & Use Cases

  • Parallel retrieval, triangulation, synthesis, critique, and packaging of reports across academic, industry, and technical sources.
  • Append-only evidence storage, stable source identities, and claim-level verification for reproducible research.
  • Generates comprehensive artifacts including Markdown, HTML, and PDF outputs with full bibliography and methodology appendix.

Quick Start

On invocation, provide a research question and the engine will generate a citation-backed report with provenance and a complete bibliography.

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 citation-backed research report from multiple sources?

Multi-source research triangulation works by applying parallel retrieval across academic and technical sources, verifying claims, and storing evidence in an append-only repository for traceable synthesis.

Can I use evidence provenance tracking for academic and industry analysis?

You can export research reports in Markdown, HTML, and PDF formats, each including a comprehensive bibliography and a methodology appendix to document the triangulation process.

What is the best way to manage source citations during complex analytical research?

Claim-level verification is necessary for decision-grade outputs because it ensures reproducible research by cross-referencing evidence against multiple sources before synthesis into the final report.

Does the research engine support parallel retrieval and critique for technical domains?

The research engine supports parallel retrieval and critique across technical domains, automating the end-to-end workflow from evidence collection to structured report packaging.