Literature Search

Orchestrates parallel searches across Semantic Scholar, arXiv, OpenAlex, and CrossRef, then merges and deduplicates results into structured JSONL with BibTeX entries. The real workflow here is query expansion into 2-4 variants, followed by citation-weighted ranking that balances recency, venue quality, and relevance. Semantic Scholar is treated as primary for ML/AI papers since it includes proper BibTeX, while arXiv catches the last three months of preprints. Nice touch: it can download arXiv source LaTeX files directly. The venue tier system is opinionated but sensible, clearly marking NeurIPS/ICML as top tier and flagging preprints. Use this when you need a proper literature survey with mergeable citations, not just Google Scholar copypasta.

skills.sh installs: 2.7K
GitHub stars: 459
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add lingzhi227/agent-research-skills --skill literature-search --agent claude-code

Installs into .claude/skills of the current project.

Files

Literature Search

Search multiple academic databases to find relevant papers.

Input

$ARGUMENTS — The search query (natural language)

Scripts

Semantic Scholar (primary — best for ML/AI, has BibTeX)

python ~/.claude/skills/deep-research/scripts/search_semantic_scholar.py \
  --query "QUERY" --max-results 20 --year-range 2022-2026 \
  --api-key "$(grep S2_API_Key /Users/lingzhi/Code/keys.md 2>/dev/null | cut -d: -f2 | tr -d ' ')" \
  -o results_s2.jsonl

Key flags: --peer-reviewed-only, --top-conferences, --min-citations N, --venue NeurIPS ICML

arXiv (latest preprints)

python ~/.claude/skills/deep-research/scripts/search_arxiv.py \
  --query "QUERY" --max-results 10 -o results_arxiv.jsonl

OpenAlex (broadest coverage, free, no API key)

python ~/.claude/skills/literature-search/scripts/search_openalex.py \
  --query "QUERY" --max-results 20 --year-range 2022-2026 \
  --min-citations 5 -o results_openalex.jsonl

Merge & Deduplicate

python ~/.claude/skills/deep-research/scripts/paper_db.py merge \
  --inputs results_s2.jsonl results_arxiv.jsonl results_openalex.jsonl \
  --output merged.jsonl

SKILL.md on GitHub