citation-harvest

star 0

Query Semantic Scholar to collect citations and generate a deduplicated BibTeX file. Offline by default.

alexj11324 By alexj11324 schedule Updated 2/6/2026

name: citation-harvest description: Query Semantic Scholar to collect citations and generate a deduplicated BibTeX file. Offline by default.

Citation Harvest

Overview

Collect citations from Semantic Scholar using query strings and output a JSON bundle plus a BibTeX file.

Workflow

  1. Prepare queries (one per line)
  2. Run the harvester
    UV_CACHE_DIR=/tmp/uv-cache XDG_CACHE_HOME=/tmp uv run -s scripts/citation_harvest.py \
      --online --in queries.txt --out-json citations.json --out-bib citations.bib
    

Inputs

  • --in: text file with one query per line (optional)
  • --query: repeatable query strings
  • --limit: results per query (default 5)
  • --online: enable network calls (required)

Outputs

  • citations.json
  • citations.bib

Safeguards

  • Offline by default; --online required.
  • No uploads; only queries sent to Semantic Scholar.
  • API key must be provided via S2_API_KEY env var if needed.

References

  • Safeguards: references/safeguards.md
Install via CLI
npx skills add https://github.com/alexj11324/AI-Scientist-v2 --skill citation-harvest
Repository Details
star Stars 0
call_split Forks 0
navigation Branch main
article Path SKILL.md
More from Creator