skills.rest
XWIlluDelu
XWIlluDeluCOMMUNITY
Explore all skills by this author →
GitHub

expand-references

Expand seed papers into ranked follow-up categories via Semantic Scholar.

Updated May 26, 2026
Search Tags:#literature review#semantic scholar#research planning#paper recommendations#survey discovery#citation landscape
One-click install
npx skills add https://github.com/XWIlluDelu/agent-share --skill expand-references
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: expand-references
Source: https://github.com/XWIlluDelu/agent-share/tree/main/lib/expand-references
Command: npx skills add https://github.com/XWIlluDelu/agent-share --skill expand-references

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Finding the next papers to read after you already have a few key “anchor” works can be slow and unfocused.

Core Features & Use Cases

  • Curated neighborhood expansion: Expands one to three seed papers into structured follow-ups, including the closest neighbors, bridging papers, foundational work, methodological papers, recent work, and surveys/benchmarks.
  • Field- and venue-aware scoring: Ranks candidates using similarity to the seeds, impact signals, recency, venue novelty, and textual overlap.
  • Cluster steering with negatives: Lets you push the expansion away from an unwanted subtopic by specifying negative papers.
  • Use Case: You have three anchor papers in retrieval-augmented generation and want a prioritized sequence of foundational background, methods, and the most useful recent surveys without manually searching.

Quick Start

Run the skill by providing one to three seed paper titles (quoted if multi-word) and optionally add negative seeds, then read the structured buckets from the returned JSON fields.

Frequently Asked Questions about expand-references

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

FAQPage Schema
How do I find follow-up papers to read for a literature review based on a few anchor papers?▼

A literature review reading path is generated by resolving your seed queries to concrete Semantic Scholar records, calling the recommendations engine, and returning ranked candidate papers bucketed by category.

What is the best way to get paper recommendations for research planning using Semantic Scholar?▼

This approach hydrates and scores candidate papers from Semantic Scholar, bucketing them into foundational, methodological, recent, bridge, and survey categories to guide your research planning.

Can I exclude unwanted subtopics when discovering nearby research papers?▼

Providing negative seeds pushes the expansion away from irrelevant themes, ensuring the structured output of nearby follow-up papers aligns closely with your desired research focus.

How are candidate papers scored and bucketed during citation landscape discovery?▼

This field- and venue-aware scoring mechanism ensures the returned JSON envelope contains deterministic workflow metadata with a prioritized sequence of relevant literature.

Does this literature discovery workflow require resolving seed queries to specific records?▼

Resolving your one to three seed paper titles to concrete records is a mandatory prerequisite for generating the structured, ranked set of nearby follow-up papers.

Related Skills

Explore More Education & Research Skills→
CodeAlive-AICodeAlive-AI

semantic-scholar-deep

Orchestrate Semantic Scholar discovery, batching, and citation graph traversal.

Official
Advanced
Agents2AgentsAIAgents2AgentsAI
92

paper-synthesizer

Extract structured knowledge from a research paper PDF into a staging file.

Official
Advanced
jaredcroxtonjaredcroxton

arxiv

Search arXiv by keyword, author, category, or ID and retrieve paper metadata.

Community
Basic
firecrawlfirecrawl
121

firecrawl-research-papers

Create literature reviews using Firecrawl Research semantic paper search and in-body claim verification.

Official
Advanced