publication-trust
Assess the scientific integrity and trustworthiness of publications before relying on their findings. Use this skill whenever evaluating a paper for a workflow, citing a study, building an analysis on published methods, or when a user asks about the reliability of a study. Checks for formal retractions, corrections, expressions of concern, and — critically — informal contradictions where subsequent studies failed to reproduce key findings. Integrates with PubMed, bioRxiv, and Consensus to provide a trust assessment. Use this skill for ANY publication evaluation, retraction checking, author rel
npx skills add majiayu000/claude-skill-registry --skill publication-trust-ammawla-encode-toolkit --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Evaluate the scientific integrity and reliability of publications before building analyses on their findings.
How it works
- Step 1: Gather Publication Metadata using get_article_metadata(pmids=["PMID"]) or convert_article_ids(ids=["DOI"], id_type="doi"). Record article_types, authors, journal, publication_date.
- Step 2: Check Formal Integrity Markers
- 2a. Retraction Status: search PubMed for retraction notices with a query (PMID[PMID] AND (Retracted Publication[pt] OR Retraction of Publication[pt])). If article_types include "Retracted Publication" or retraction is found, mark Trust Level 1 (Compromised).
- 2b. Errata and Corrections: search PubMed for (Published Erratum[pt] OR Correction[pt]). Distinguish Minor (trust level unchanged) from Major (trust level 3).
- 2c. Expression of Concern: search PubMed for Expression of Concern[pt]. Mark Trust Level 2 until resolved.
- Step 3: Check for Contradicting Publications
- 3a. Find Citing Articles via find_related_articles(pmids=["PMID"], link_type="pubmed_pubmed", max_results=50).
- 3b. Search for Contradiction Signals using terms like fail to replicate, does not support, contradicts, etc.
- 3c. Use Consensus with consensus_search(query="does [key claim from paper] replicate? contradiction evidence").
- 3d. Check bioRxiv for Preprints via search_preprints(category=[relevant category], date_from=[pub date], date_to=[today]).
- 3e. Evaluate Contradictions considering factors like independent lab involvement, sample size, methodology, specificity, and mechanism.
- Step 4: Author and Group Assessment
- 4a. Check Author Track Record with queries on Retracted Publication for SeniorAuthor.
- 4b. Contextual Notes with careful language and prohibition on unfounded terms.
- Step 5: Generate Trust Report
- Produce a structured report including formal markers, contradicting evidence, author context, and a clear Recommendation.
- Step 6: Integration with Other Skills
- When issues are found, propagate signals to cite-encode, quality-assessment, variant-annotation, disease-research, regulatory-elements, and data-provenance.
When to use it
- User wants to evaluate reliability and reproducibility of a genomics publication
- User asks about publication quality, reproducibility, trust assessment, or paper evaluation
- User needs to verify ENCODE data standards or that cited datasets/tools meet community standards
What it can touch
- Tools: claude-code
- It coordinates checks against PubMed, bioRxiv, Consensus, and related metadata and reports
Caveats
- Trust levels depend on presence of retractions, corrections, expressions of concern, and contrary evidence from independent replication; not all issues may be found if sources are not indexed or updated
- Interpretation notes emphasize measured language and avoid speculative conclusions
# Publication Trust Assessment Evaluate the scientific integrity and reliability of publications before building analyses on their findings. ## When to Use - User wants to evaluate the reliability and reproducibility of a genomics publication - User asks about "publication quality", "reproducibility", "trust assessment", or "paper evaluation" - User needs to check if a paper follows ENCODE data standards and best practices - User wants to verify that cited datasets, tools, and methods meet community standards - Example queries: "is this paper's ChIP-seq analysis trustworthy?", "evaluate the methods in this genomics paper", "check if this study follows ENCODE standards" ## Why This Matters Not all published findings are reliable. Problems range from formal retractions (data fabrication, image manipulation) to informal contradictions where independent groups fail to reproduce key claims. In genomics and computational biology, building pipelines or analyses on unreliable findings wastes resources and propagates errors. **The problem is not always obvious.** Formal retractions are rare compared to the number of problematic papers. More commonly: - A subsequent study contradicts the key
- When to Use
- Why This Matters
- Trust Assessment Framework
- Trust Levels
- Step 1: Gather Publication Metadata
- Step 2: Check Formal Integrity Markers
- 2a. Retraction Status
- 2b. Errata and Corrections
- 2c. Expression of Concern
- Step 3: Check for Contradicting Publications
- 3a. Find Citing Articles
- 3b. Search for Contradiction Signals
- 3c. Search Academic Databases
- 3d. Check bioRxiv for Preprints
What does the publication-trust skill do?
Assess the scientific integrity and trustworthiness of publications before relying on their findings. Use this skill whenever evaluating a paper for a workflow, citing a study, building an analysis on published methods, or when a user asks about the reliability of a study. Checks for formal retractions, corrections, expressions of concern, and — critically — informal contradictions where subsequent studies failed to reproduce key findings. Integrates with PubMed, bioRxiv, and Consensus to provide a trust assessment. Use this skill for ANY publication evaluation, retraction checking, author rel
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill publication-trust-ammawla-encode-toolkit --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.