retraction-watcher

Scan reference lists and detect retracted, corrected, or flagged papers via Crossref and PubMed APIs.

Updated Sep 15, 2026
One-click install
npx skills add https://github.com/mrsonord2240/openscience-specialists --skill retraction-watcher-mrsonord2240
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: retraction-watcher
Source: https://github.com/mrsonord2240/openscience-specialists/tree/main/specialists/critical-appraisal-specialist/versions/1.0.0/package/skills/retraction-watcher
Command: npx skills add https://github.com/mrsonord2240/openscience-specialists --skill retraction-watcher-mrsonord2240

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires PyPDF2, and includes scripts (resource) and references (resource) components.

What problem does it solve? Citing retracted or corrected papers undermines research credibility, but manually checking every reference against retraction databases is slow and error-prone. This Skill automates that verification before submission, peer review, or evidence synthesis. ## Core Features & Use Cases - Citation Parsing: Extracts DOIs, PMIDs, titles, authors, and years from PDF, BibTeX, RIS, and plain-text reference lists across multiple citation styles. - Multi-Database Checking: Cross-checks citations against Open Retractions, the Crossref API, and PubMed E-utilities, with rate limiting and caching. - Structured Reports: Generates summary, detailed, or JSON reports classifying each reference as retracted, expression of concern, corrected, or clear, with recommended actions. - Use Case: Before submitting a manuscript, run the script on your references.bib file to receive a report flagging any retracted citations that must be removed. ## Quick Start Ask the assistant to check the references in your manuscript PDF or BibTeX file for retracted papers and produce a detailed report.

Frequently Asked Questions about retraction-watcher

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check my references for retracted papers?▼

Run the script with your reference file as input, for example a BibTeX or PDF file, and it parses each citation and checks it against retraction databases. The output report flags retracted, corrected, or concerning papers with recommended actions.

What databases are used to detect retracted papers?▼

The checker queries Open Retractions first, then the Crossref API for retraction metadata, and PubMed E-utilities for retraction publication types. Results are cached and rate-limited to avoid excessive API calls.

Which file formats can I scan for citations?▼

Supported inputs include PDF files (requiring PyPDF2), BibTeX (.bib), RIS, plain text files, raw pasted text, and URLs. The parser detects numbered references, blank-line-separated entries, and BibTeX entries automatically.

What happens when a citation has no DOI or PMID?▼

The parser falls back to extracting the article title, authors, and year for matching. However, title-only matching can produce false positives with similar titles, so results without identifiers should be verified manually.

What are the limitations of automated retraction checking?▼

It requires an internet connection, and very recent retractions under 48 hours may not be indexed yet. Preprints like arXiv and bioRxiv are typically not tracked, and non-English papers may have limited database coverage.