evo-citation-scorer
SkillDev toolsCompares parsed BibTeX citation metadata against API results using fuzzy string matching and multi-factor scoring to classify citations as real or fake, then outputs the final JSON report.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the evo-citation-scorer skill
What this skill tells your AI
The instructions your AI receives, as published by openlair/openskill in tasks-evolved/citation-check/environment/skills/evo-citation-scorer/SKILL.md and read by ahel’s review.
Scores and classifies citations as real or fake.
Key Functions
normalize_string(text)- Normalize for comparison (lowercase, no punctuation)calculate_title_similarity(title1, title2)- Token-based title similarity (0-100)compute_composite_score(citation, api_result)- Multi-factor score (title 50%, author 30%, year 20%)classify_citation(verification_result)- Classify as Real/Fake based on scoresexport_fake_citations_json(fake_titles, output_file)- Write sorted JSON output
Classification Logic
- DOI resolves via CrossRef → Real
- No DOI or DOI fails → search CrossRef by title
- Best composite score >= 70 → Real
- Below 70 → Fake
Usage
import sys
sys.path.insert(0, '/app/environment/skills/evo-citation-scorer/scripts')
from utils import classify_citation, export_fake_citations_json
# After verification
status = classify_citation(verification_result)
if status == 'Fake':
fake_titles.append(verification_result['title'])
export_fake_citations_json(fake_titles, '/root/answer.json')
Signals
- GitHub stars
- 89
- Forks
- 4
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
evo-citation-scorer- Source
- github.com/openlair/openskill