skills.rest
Ar9av
Ar9avCOMMUNITY
Explore all skills by this author →
Website𝕏@_ar9avGitHub

literature-review-agent

Discover and verify academic citations via web search and Semantic Scholar.

635|88|Updated Apr 9, 2026
Search Tags:#deduplication#latex#bibtex#web-search#literature-review#citation-verification#semantic-scholar
One-click install
npx skills add https://github.com/Ar9av/PaperOrchestra --skill literature-review-agent-ar9av
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: literature-review-agent
Source: https://github.com/Ar9av/PaperOrchestra/tree/main/skills/literature-review-agent
Command: npx skills add https://github.com/Ar9av/PaperOrchestra --skill literature-review-agent-ar9av

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python-Levenshtein, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Helps researchers and coding agents discover, verify, and integrate relevant academic papers into a manuscript by automating parallel web discovery, sequential Semantic Scholar verification, deduplication, BibTeX generation, and a constrained writing loop for Introduction and Related Work.

Core Features & Use Cases

  • Outline-driven discovery: run many search queries (host web search or optional Exa backend) to gather candidate papers tagged by discovery cluster.
  • Robust verification: sequential Semantic Scholar title-search with fuzzy Levenshtein matching, strict temporal cutoff checks, abstract presence enforcement, caching, and deduplication by S2 paperId.
  • Publication-ready outputs: deterministic BibTeX formatting, sync of citation keys into LaTeX, and a drafting recipe that enforces the ≥90% citation integration rule for Intro + Related Work.
  • Degraded and host-friendly modes: supports degraded mode when no web search is available and provides script helpers for caching, pre-dedup, and S2 rate-limit handling.

Quick Start

Use the literature-review-agent to find and verify citations for my paper, generate workspace/refs.bib, and draft the Introduction and Related Work sections into workspace/drafts/intro_relwork.tex.

Frequently Asked Questions about literature-review-agent

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

FAQPage Schema
How do I automate literature review and verify citations using Semantic Scholar?▼

Automate literature review by running parallel web searches to discover candidate papers, then sequentially verify them through Semantic Scholar using fuzzy Levenshtein title matching to build a verified citation pool for your manuscript.

Can I generate a BibTeX file and draft related work sections from web search results?▼

Yes, you can generate BibTeX files and draft related work sections by executing web-search-driven literature discovery, verifying results via Semantic Scholar, and applying an outline-driven drafting loop that enforces a ≥90% citation integration rule.

How does fuzzy title matching handle deduplication when building a citation pool?▼

Fuzzy title matching uses Levenshtein distance to compare search results against Semantic Scholar entries, then deduplicates verified papers by their unique S2 paperId to ensure a clean, non-redundant citation pool.

Do I need python-Levenshtein to run the literature review pipeline?▼

Yes, python-Levenshtein is a required dependency for executing fuzzy title matching against Semantic Scholar entries during the citation verification and deduplication process.

What happens to citation verification when web search is unavailable?▼

When web search is unavailable, the pipeline operates in a degraded mode that utilizes script helpers for caching, pre-deduplication, and Semantic Scholar rate-limit handling to continue processing existing candidate papers.

How do I enforce a temporal cutoff for academic paper discovery and citation integration?▼

You can enforce strict temporal cutoffs during the Semantic Scholar verification phase, ensuring that only papers published before your specified date are integrated into the final BibTeX output and LaTeX drafts.

Related Skills

Explore More Education & Research Skills→
raja21068raja21068
2

literature-review-agent

Discover and verify candidate papers via Semantic Scholar, then draft LaTeX Introduction and Related Work sections.

Community
Advanced
chrisliu298chrisliu298
1

citation-assistant

Automate citation lookup and verification for LaTeX documents across multiple sources.

Community
Advanced
HosungYouHosungYou
5

i1

Automate academic paper retrieval across Semantic Scholar, OpenAlex, and arXiv with deduplication and PDF extraction.

Community
Advanced
woodfishhhhwoodfishhhh
32

literature-review-agent

Automate literature discovery and verification with Semantic Scholar for BibTeX-backed paper sections.

Community
Advanced