nature-academic-search
yuan1z0825/nature-skills
Multi-source academic literature search, citation verification, and reference management via PubMed, CrossRef, arXiv, Scopus, and ScienceDirect.
What is nature-academic-search?
Routes literature search requests to the appropriate workflow (multi-source search, citation verification, MeSH strategy, citation file conversion, or reference management) and executes coordinated multi-step academic workflows. Use when you need integrated literature discovery, citation validation, or reference file handling beyond single-tool lookups.
- Search literature across PubMed, CrossRef, arXiv, Scopus, and ScienceDirect simultaneously
- Verify citations extracted from documents against authoritative sources
- Build and refine MeSH-based search strategies for PubMed
- Convert and manage citation files (.nbib, .ris, .bib formats)
- Discover related articles and convert between citation ID formats
- Deduplicate and parse citation metadata from multiple sources
How to install nature-academic-search
npx skills add https://github.com/yuan1z0825/nature-skills --skill nature-academic-search- Access to MCP tools for PubMed, CrossRef, arXiv, Scopus, and ScienceDirect
- Python environment (for optional format conversion and deduplication scripts)
- Citation files in .nbib, .ris, or .bib format (for file management workflows)
How to use nature-academic-search
- 1.Describe your literature need (search, verify, convert, or manage citations)
- 2.The skill detects the workflow type (multi-source search, citation verification, MeSH strategy, file conversion, or reference management)
- 3.Load the relevant workflow fragment and core tools from the static layer
- 4.Execute the workflow using the appropriate MCP tools in the T1→T2→T3 fallback chain
- 5.Apply shared modules (dedup, citation parser, format converter) as needed for your specific task
- 6.Review results and export in your preferred format (.bib, .ris, .nbib, or plain text)
Use cases
- Conduct a comprehensive literature review by searching multiple academic databases at once
- Verify that citations in a manuscript are accurate and properly formatted
- Develop a systematic PubMed search strategy using MeSH terms for a clinical research question
- Convert a downloaded .nbib file from PubMed into BibTeX format for LaTeX documents
- Find related articles to a known paper and export results in a standardized format
- Academic researchers conducting literature reviews
- Graduate students writing theses or dissertations
- Clinical researchers building systematic review protocols
- Authors verifying citations during manuscript preparation
- Librarians and information specialists managing reference collections
nature-academic-search FAQ
PubMed, CrossRef, arXiv, Scopus, and ScienceDirect. The skill routes to the most appropriate source(s) based on your query and falls back through a T1→T2→T3 chain if the primary source has no results.
Yes. The citation-file-mgmt workflow handles conversion between .nbib (PubMed), .ris (generic), and .bib (BibTeX) formats using the format-converter script.
The skill extracts citations from your document and cross-references them against PubMed, CrossRef, and other sources to confirm accuracy, DOI validity, and metadata consistency.
The skill broadens search terms and falls back through the source chain (T1→T2→T3). If all sources fail, you can generate citations manually from MCP-fetched metadata.
Ensure you have access to the MCP tools (PubMed, CrossRef, arXiv, Scopus, ScienceDirect) and Python installed if you plan to use format conversion or deduplication scripts.
Full instructions (SKILL.md)
Source of truth, from yuan1z0825/nature-skills.
name: nature-academic-search description: >- Multi-source literature search, citation verification, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related articles, ID conversion) via MCP tools (PubMed, CrossRef, arXiv, Scopus, ScienceDirect). Use when the user needs coordinated multi-step literature workflows beyond a single MCP call. Also trigger on general literature-search needs during academic writing even without the word "Nature", such as searching for papers/literature, doing a literature review, verifying a citation, converting citation files, and Chinese phrasings like 文献检索、查文献、找文献、 文献综述检索、查论文、引文核对、参考文献管理、文献去重. version: 2.0.0 author: Community contribution, refactored into static/dynamic layers
Academic Search — Router
This skill is split into two layers:
- A static layer under
static/that holds versioned, reusable content fragments (the MCP tool inventory and shared modules, and source routing plus operational rules). - A dynamic layer (this file plus
manifest.yaml) that detects which workflow the user needs and loads that workflow, reaching for shared modules and scripts only when a step needs them.
Do not try to apply the search logic from memory or from this router. Always load fragments from disk as described below.
Routing protocol
Follow these five steps every time the skill is invoked.
1. Load the manifest and the core layer
Read manifest.yaml. It declares the workflow axis, the allowed values, and the file paths each value maps to.
Also read every file listed under always_load:
static/core/tools.md— the MCP tool inventory (core search, extended search, PubMed utilities) and the shared-module map.static/core/routing-and-ops.md— the T1→T2→T3 source routing quick guide, environment setup, error handling, and limitations.
2. Detect the workflow
Map the user's need to one or more workflow values:
multi-source-search— find literature across sources.citation-verification— verify citations extracted from a document.mesh-strategy— build a MeSH/PubMed search strategy.citation-file-mgmt— convert/manage.nbib/.ris/.bibfiles.reference-mgmt— BibTeX, related-article discovery, ID conversion.
A combined request (for example search then export) may need more than one. State the detected workflow(s) in one short line before proceeding.
3. Load the matching workflow fragment(s)
Read the file mapped for each detected workflow (under references/workflows/). Do not read every workflow. Each workflow file links to the shared modules it needs.
4. Run the workflow using the loaded material
Apply the loaded material in this order:
- Core tools and routing (
core/tools.md,core/routing-and-ops.md) — which MCP tool for which need, and the T1→T2→T3 fallback chain that is the standard execution order across all workflows. - The workflow fragment — its specific steps.
- Shared modules and scripts on demand (dedup, citation parser, search strategy, RIS/BibTeX format, format converter).
Report specific tool failures and continue with remaining tools; broaden terms when there are no results; fall back to manual generation from MCP-fetched metadata if a script fails twice.
5. Reach for references only when needed
The files under references/ (and scripts/) are deep references, not defaults. Open them on demand per the references.on_demand table in the manifest — for example references/source-tiers.md for the full reliability classification, references/dedup-engine.md / references/citation-parser.md / references/search-strategy.md / references/ris-bibtex-format.md for the shared modules, and scripts/academic_search.py (no-MCP fallback discovery search) / scripts/format-converter.py / scripts/preflight.py for the tooling.
Why this split
- The static layer is versioned and reviewable; the workflow files and shared modules were already factored this way.
- The dynamic layer keeps each invocation cheap: only the workflow the user needs enters context, instead of all five plus every module.
- The router itself is short on purpose. Update fragments and references, not this file, when adding scope.
- This structure mirrors the other nature-* skills (
nature-writing,nature-polishing,nature-reader,nature-paper2ppt,nature-figure,nature-citation,nature-response,nature-data).
Related skills
More from yuan1z0825/nature-skills and the wider catalog.

nature-citation
Add strict Nature/CNS citations to manuscript text by searching flagship journals and exporting reference-manager-ready outputs.

nature-data
Prepare Nature-ready data availability statements, repository plans, and FAIR metadata for academic manuscripts.

nature-figure
Submission-grade Nature/high-impact journal figure workflow for Python or R.

nature-paper2ppt
Convert research papers into polished Nature-style Chinese PPTX presentations with figures, speaker notes, and self-review.

nature-polishing
Polish academic manuscripts into Nature-style English with section-specific guidance and LaTeX layout fixes.

nature-reader
Full-paper Chinese-English bilingual Markdown reader for PDFs, DOI, arXiv, and HTML papers with figures and tables preserved.