deep-research

Locate scholarly papers from sparse clues and output title and DOIs in markdown.

3|Updated Jan 14, 2022
One-click install
npx skills add https://github.com/bingran-you/bingran-you --skill deep-research-bingran-you
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/bingran-you/bingran-you/tree/main/repo-skills/deep-research
Command: npx skills add https://github.com/bingran-you/bingran-you --skill deep-research-bingran-you

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deep web research benchmark — given partial clues about authors and topic, find the exact paper and produce a structured answer.

Use when the user wants to test or demonstrate an agent's ability to do multi-hop, citation-aware web research from sparse input. Originally authored as a SkillsBench task by Bingran You; copied here as a discoverable, self-contained reference.

Core Features & Use Cases

  • Instruction and task config for multi-hop web research that locates the exact paper and emits a structured answer containing the title and DOIs.
  • Supports verification by returning a markdown file with required fields.

Quick Start

Locate the exact paper given sparse author/topic hints and output a structured answer containing title and DOIs.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I find a specific academic paper from sparse author and topic clues?

Multi-hop web research locates the exact paper from sparse clues by applying citation-aware search to retrieve the title and DOIs, outputting the structured result in a markdown file.

What is multi-hop citation-aware web research for scholarly papers?

Multi-hop citation-aware web research is a benchmark task that tests an agent's ability to trace sparse clues through multiple search steps to find a specific scholarly paper and extract its title and DOIs.

Does deep web research return DOIs for papers found through partial hints?

Yes, deep web research retrieves the exact paper from sparse clues and ensures the output includes the title and DOIs formatted within a structured markdown file for verification.

What are the limitations of locating papers using sparse clues?

Locating papers from sparse clues requires sufficient initial hints to perform multi-hop web research; if the partial author or topic information is too vague, the citation-aware search may fail to identify the exact paper and DOIs.