Citation Management

A comprehensive BibTeX workflow tool that borrows from AI-Scientist's iterative harvesting approach. The validate script catches missing citations, duplicate keys, and even undefined references before compilation. The harvest action runs up to 20 rounds of automatically finding and inserting citations from Semantic Scholar, searching for gaps in your draft and adding properly formatted entries. It's opinionated about key naming (lastNameYearWord format) and won't let you fabricate citations. Also handles the usual housekeeping: deduplication, formatting, converting JSONL paper databases to BibTeX. If you've ever spent an afternoon manually fixing citation keys or hunting down BibTeX entries, this handles the entire loop from draft to clean bibliography.

skills.sh installs: 2.2K
GitHub stars: 459
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add lingzhi227/agent-research-skills --skill citation-management --agent claude-code

Installs into .claude/skills of the current project.

Files

Citation Management

Manage the full lifecycle of citations in a LaTeX paper.

Input

$0 — Action: harvest, validate, add, format
$1 — Path to .tex or .bib file

Scripts

Validate citations (check all cite keys resolve)

python ~/.claude/skills/citation-management/scripts/validate_citations.py \
  --tex paper/main.tex --bib paper/references.bib --check-figures --figures-dir paper/figures/

Reports: missing citations, unused bib entries, duplicate keys, duplicate sections, duplicate labels, undefined references, missing figures.

Generate BibTeX from paper database

python ~/.claude/skills/deep-research/scripts/bibtex_manager.py \
  --jsonl paper_db.jsonl --output references.bib

Search for a specific paper to add

python ~/.claude/skills/deep-research/scripts/search_semantic_scholar.py \
  --query "attention is all you need" --max-results 5 \
  --api-key "$(grep S2_API_Key /Users/lingzhi/Code/keys.md 2>/dev/null | cut -d: -f2 | tr -d ' ')"

SKILL.md on GitHub