By yy
Assists with academic manuscript preparation and submission workflows: verifies LaTeX document quality, manages references and bibliographies, critiques figures and manuscripts, fetches metadata from arXiv and OpenAlex, and generates accessible PDFs.
Make a LaTeX document produce accessible tagged PDFs (PDF/UA-1, PDF/A-2b). Creates a non-destructive copy and Makefile target. Use when the user needs accessible or tagged PDFs.
Fetch structured metadata for an arXiv paper. Use when you have an arXiv ID or URL and need title, authors, date, categories, and DOI.
Prepare an arXiv submission package from a LaTeX paper. Cleans the source, builds a tarball, and extracts metadata for the submission form. Use before uploading to arXiv.
Toggle DOI, URL, eprint, and ISBN display in a biblatex bibliography. Use when the user asks to show or hide identifiers or make bibliography identifiers available as links.
Match references in a LaTeX paper against academic databases, flag entries that need review, and suggest missing DOIs or URLs. Use when checking citations or preparing a paper for submission.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Academic research tools for Claude Code. Literature search, citation management, LaTeX checks, math verification, manuscript critique, and submission preparation. These tools assist with formatting and verification—they do not generate original research content. Please check your venue's AI use policy for guidance on whether and how to use these tools.
Note: These skills are early-stage and not comprehensively tested. Proceed with caution!
Privacy: Some skills send manuscript content, figures, or bibliographic data to AI model providers and external APIs. Read PRIVACY.md to understand what data goes where, and discuss with your co-authors before using this plugin on shared work.
Don't overbuild. Foundation models and agent harnesses are getting better fast, and overbuilt structure becomes a maintenance burden that constrains the base model rather than helping it. These skills exist only where they add something Claude can't quickly or easily do on its own: calling external APIs, running programmatic verification, or encoding multi-step checklists that are easy to forget. No skill for something Claude already handles well out of the box or will likely handle with minimal guidance or conversation.
Single-purpose data retrieval from external sources.
| Skill | Description |
|---|---|
arxiv-metadata | Fetch structured metadata for arXiv papers (title, authors, date, categories, DOI) |
doi-bibtex | Fetch BibTeX entries from DOIs and add to .bib files |
openalex | Query and analyze scholarly works via the OpenAlex API |
Inspect, verify, or critique artifacts — from programmatic checks to structured review.
| Skill | Description |
|---|---|
check-refs | Verify citation references in LaTeX papers against academic databases using bibsleuth |
latex-cleanup | Review LaTeX documents for common issues, style consistency, typography, cross-references, and draft artifacts |
verify-math | Verify mathematical derivations step-by-step using SymPy |
critique-figures | Critique figures for format, colorblind safety, legibility, overplotting, and chart choice |
critique-manuscript | Structured self-review of your manuscript |
Multi-step workflows — coordinating checks, preparing submissions, or transforming documents.
| Skill | Description |
|---|---|
presubmit-checks | Pre-submission checklist — references, LaTeX cleanup, build, figure format, and front matter |
bib-doi-toggle | Toggle DOI/URL display in a biblatex bibliography so refs are clickable in the compiled PDF |
arxiv-prep | Prepare an arXiv submission package — clean source, compile, extract metadata, create tarball |
accessible-pdf | Make LaTeX documents produce accessible tagged PDFs (PDF/UA-1, PDF/A-2b) — non-destructive copy + LuaLaTeX build |
arxiv-metadataFetches structured metadata from arXiv given an arXiv ID or URL — title, authors, date, categories, DOI. Handles multiple ID formats (new and old-style). Mainly used by other skills and agents rather than invoked directly.
doi-bibtexGiven a DOI (bare or full URL), fetches the BibTeX entry and appends it to the project's .bib file, checking for duplicates. Simple utility — mainly invoked by Claude when adding references.
openalexQueries the OpenAlex API for literature searches, citation analysis, and bibliometric queries. The helper script handles authentication, rate limiting, retries, and pagination. Set OPENALEX_API_KEY for normal use; limited no-key requests are supported.
check-refsVerifies that every citation in a LaTeX paper exists in academic databases, flags suspicious entries, and suggests missing DOIs/URLs. Uses bibsleuth. Can run standalone or as part of presubmit-checks.
latex-cleanupSystematic review of LaTeX documents for common issues: style consistency, typography, cross-references, draft artifacts, debugging code. Identifies all .tex files in the project (including \input/\include targets) and flags problems.
verify-mathStep-by-step verification of mathematical derivations using SymPy. Each derivation step is validated programmatically — useful for catching algebra and calculus errors in proofs and equations.
critique-figuresnpx claudepluginhub yy/claude-scholar --plugin claude-scholarAcademic literature search, citation management, PDF retrieval, and literature review synthesis
Production-grade academic research pipeline for Claude Code: research → write → review → revise → finalize. 4 skills, 27 modes, 39-agent ensemble, v3.7.3 + v3.8 L3 claim-faithfulness gate, v3.9.0 cross-index triangulation, v3.10 triangulation policy layer, v3.11 deterministic citation verification gate (#182).
Verify academic paper citations: extract references from LaTeX/PDF, check formatting, verify existence via Crossref/Semantic Scholar, and score thematic/semantic relevance.
Multi-agent orchestrator for academic writing: 12 specialist agents and 30 writing principles for review, research, drafting, polishing, bibliography auditing, and literature surveys.
ARC paper, research-domain, and report typesetting tools.
A research infrastructure for AI agents. Search, read, and analyze papers from your local knowledge base while coding. Includes arXiv discovery, layered reading, ingestion, topic modeling, citation graphs, insights analytics, Office document inspection, scientific tool docs, and academic writing workflows. Requires Python 3.10+ and pip install.