Skill UI

Use this helper to search ten academic paper databases via their REST APIs whenever you need research papers, preprints, citation data, metadata, or open-access PDFs; it routes DOI/PMID/author/topic queries to the right endpoints and returns raw JSON plus the queried databases/paths.

This skill integrates 10 major academic literature APIs (including PubMed, arXiv, OpenAlex, Crossref, etc.). It guides users on converting complex research intents into reproducible, verifiable lookups for papers, preprints, citations, and open-access full texts. It ensures results include verifiable provenance and follows a rigorous workflow for maximum accuracy in scholarly research.

A powerful tool for deterministic and reproducible retrieval of evidence from specialized academic and policy corpora. It supports searching arXiv (preprints), PubMed/PMC (biomedical literature), and US policy documents. Users can check corpus freshness, retrieve stable metadata, and fetch full-document Markdown for high-reliability research tasks.

This guide offers advanced methodological advice for structuring the 'Related Work' section for top-tier theoretical computer science conferences (like FOCS). It teaches researchers how to treat research history as 'lineage engineering,' requiring precise citation of specific preprints (arXiv version pinning), distinguishing between conference and journal versions, and transparently addressing concurrent results. This ensures the bibliography is rigorous, consistent, and withstands expert review.

A comprehensive guide for structuring the "Related Work" section for top-tier computer vision conferences (ICCV, CVPR, ECCV). It covers best practices for citing intervening-cycle literature, managing concurrent preprints, ensuring double-blind anonymity, and correctly attributing source venues to maximize novelty perception and score highly with reviewers.

A detailed methodology guide for authors submitting to highly competitive software engineering venues (like ICSE). It teaches how to structure the Related Work section not as a bibliography, but as a 'delta statement' that explicitly outlines the unique differences and contributions compared to the state-of-the-art across multiple publication lanes (journals, preprints, flagship venues).

Provides comprehensive guidelines for authors submitting to major AI conferences. It helps authors audit originality, properly cite prior art (including preprints, workshop papers, and rejected versions), manage dual-submission risks, and transform the related work section from a mere list into a compelling, novel argument that clearly positions the contribution.

This guide details the crucial rules for structuring a scientific paper submitted to conferences like ITCS. It dictates how content—including main theorems, proofs, and motivation—must be distributed across three locations: the main body, the submitted appendix, and the external full version (arXiv). The core principle ensures that all decision-critical evidence for accepting the paper resides within the submitted PDF, preventing reviewers from relying on external or unread preprints.

This guide provides a comprehensive overview of the editorial and review process for the Journal of Public Economics (JPubE). It details the single anonymized review model, expectations regarding multiple specialist reviewers, the use of Editorial Manager, and strategic advice for SSRN preprints and appeals. Use this skill when planning a submission, understanding review outcomes, or managing academic publication expectations.

This comprehensive guide equips authors with a structured framework for writing the Related Work section for top-tier NLP conferences (e.g., NAACL). It emphasizes tracking methodological, data, and task lineages, ensuring citation precision across Findings, workshops, and preprints, and culminating in a single, falsifiable "delta sentence" to precisely position the novel contribution.

This skill guides authors on how to strategically position their machine learning research against complex academic landscapes. It covers comparing work to neighboring conferences (ICML, ICLR), analyzing contemporaneous preprints, and defining the exact technical delta from prior methods to minimize novelty risk for top-tier AI venues.

A comprehensive guide for maintaining consistency and completeness of references for PNAS Nexus submissions. It details the critical differences between the format-neutral requirements at submission time and the final numbered style required for publication, emphasizing the proper citation of datasets, software, and preprints.