sickn33/antigravity-awesome-skills/citation-management

# Step 1: Find key papers on your topic
python scripts/search_google_scholar.py "transformer neural networks" \
  --year-start 2017 \
  --limit 50 \
  --output transformers_gs.json
 
python scripts/search_pubmed.py "deep learning medical imaging" \
  --date-start 2020 \
  --limit 50 \
  --output medical_dl_pm.json
 
# Step 2: Extract metadata from search results
python scripts/extract_metadata.py \
  --input transformers_gs.json \
  --output transformers.bib
 
python scripts/extract_metadata.py \
  --input medical_dl_pm.json \
  --output medical.bib
 
# Step 3: Add specific papers you already know
python scripts/doi_to_bibtex.py 10.1038/s41586-021-03819-2 >> specific.bib
python scripts/doi_to_bibtex.py 10.1126/science.aam9317 >> specific.bib
 
# Step 4: Combine all BibTeX files
cat transformers.bib medical.bib specific.bib > combined.bib
 
# Step 5: Format and deduplicate
python scripts/format_bibtex.py combined.bib \
  --deduplicate \
  --sort year \
  --descending \
  --output formatted.bib
 
# Step 6: Validate
python scripts/validate_citations.py formatted.bib \
  --auto-fix \
  --report validation.json \
  --output final_references.bib
 
# Step 7: Review any issues
cat validation.json | grep -A 3 '"errors"'
 
# Step 8: Use in LaTeX
# \bibliography{final_references}

# You have a text file with DOIs (one per line)
# dois.txt contains:
# 10.1038/s41586-021-03819-2
# 10.1126/science.aam9317
# 10.1016/j.cell.2023.01.001
 
# Convert all to BibTeX
python scripts/doi_to_bibtex.py --input dois.txt --output references.bib
 
# Validate the result
python scripts/validate_citations.py references.bib --verbose

# You have a messy BibTeX file from various sources
# Clean it up systematically
 
# Step 1: Format and standardize
python scripts/format_bibtex.py messy_references.bib \
  --output step1_formatted.bib
 
# Step 2: Remove duplicates
python scripts/format_bibtex.py step1_formatted.bib \
  --deduplicate \
  --output step2_deduplicated.bib
 
# Step 3: Validate and auto-fix
python scripts/validate_citations.py step2_deduplicated.bib \
  --auto-fix \
  --output step3_validated.bib
 
# Step 4: Sort by year
python scripts/format_bibtex.py step3_validated.bib \
  --sort year \
  --descending \
  --output clean_references.bib
 
# Step 5: Final validation report
python scripts/validate_citations.py clean_references.bib \
  --report final_validation.json \
  --verbose
 
# Review report
cat final_validation.json

# Find highly cited papers on a topic
python scripts/search_google_scholar.py "AlphaFold protein structure" \
  --year-start 2020 \
  --year-end 2024 \
  --sort-by citations \
  --limit 20 \
  --output alphafold_seminal.json
 
# Extract the top 10 by citation count
# (script will have included citation counts in JSON)
 
# Convert to BibTeX
python scripts/extract_metadata.py \
  --input alphafold_seminal.json \
  --output alphafold_refs.bib
 
# Verify relevance and evidence quality; citation count does not establish influence or validity.