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). Use when the user needs coordinated multi-step literature workflows beyond a single MCP call.
How this skill is triggered — by the user, by Claude, or both
Slash command
/nature-academic-search:nature-academic-searchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Multi-source literature search, citation verification, citation format conversion,
README.mdconfig/mcp-snippet.jsonconfig/settings-snippet.jsonconfig/triggers-academic-search.tomlinstall.shmcp-server/README.mdmcp-server/academic_search_server.pymcp-server/config.tomlmcp-server/requirements.txtmcp-server/sources/__init__.pymcp-server/sources/arxiv.pymcp-server/sources/crossref.pymcp-server/sources/pubmed.pymcp-server/tests/__init__.pymcp-server/tests/test_sources.pymcp-server/utils/__init__.pymcp-server/utils/config.pymcp-server/utils/errors.pymcp-server/utils/logging.pyreferences/citation-parser.mdMulti-source literature search, citation verification, citation format conversion, and reference management via MCP tools.
| Tool | Source | Best For |
|---|---|---|
pubmed_search_articles | PubMed MCP | Biomedical, MeSH, clinical trials |
search_crossref | paper-search MCP | Cross-disciplinary, citation counts |
search_arxiv | paper-search MCP | Preprints (physics, math, CS, biology) |
| Tool | Source | Best For |
|---|---|---|
search_google_scholar | paper-search MCP | Broad academic search (scraped) |
search_semantic_scholar | paper-search MCP | Citation graph, field-of-study filters |
search_biorxiv | paper-search MCP | Biology preprints |
search_medrxiv | paper-search MCP | Medical preprints |
search_webofscience | paper-search MCP | Curated index, citation reports |
search_scopus | paper-search MCP | Broad scholarly database |
| Tool | Purpose |
|---|---|
pubmed_fetch_articles | Full metadata by PMID |
pubmed_find_related | Related article discovery |
pubmed_format_citations | APA / MLA / BibTeX / RIS formatting |
pubmed_convert_ids | DOI ↔ PMID ↔ PMCID conversion |
pubmed_lookup_mesh | MeSH term exploration and hierarchy |
pubmed_lookup_citation | Bibliographic citation → PMID lookup |
See Source Tiers & Reliability for the complete reliability classification and fallback routing rules. The T1→T2→T3 fallback chain is the standard execution order across all workflows.
Quick guide:
| User need | Primary (T1) | Secondary (T2) | Last Resort (T3) |
|---|---|---|---|
| Medical / clinical | PubMed | Semantic Scholar | Google Scholar |
| Cross-disciplinary | CrossRef | Semantic Scholar | Scopus |
| Preprints / CS / physics | arXiv | bioRxiv / medRxiv | — |
| Exhaustive review | PubMed + CrossRef + arXiv | Semantic Scholar + bioRxiv/medRxiv | WoS / Scopus |
| Citation count sensitive | Semantic Scholar | CrossRef | — |
| Chinese literature | — | — | CNKI / 万方 (manual) |
| # | Workflow | Reference |
|---|---|---|
| 1 | Multi-Source Literature Search | wf1 |
| 2 | Citation Verification | wf2 |
| 3 | MeSH Search Strategy | wf3 |
| 4 | Citation File Management | wf4 |
| 5 | Reference Management | wf5 |
| Module | Purpose |
|---|---|
| Dedup Engine | Unified deduplication (WFs 1, 2, 5a) |
| Citation Parser | Extract citations from documents (WF 2) |
| Search Strategy | Query construction, source selection, ranking |
| RIS/BibTeX Format | Format specifications and field mappings |
| Format Converter | Multi-source .nbib/.ris/.bib downloader |
| Service | Env Var | Register At | Free Tier |
|---|---|---|---|
| Semantic Scholar | SEMANTIC_SCHOLAR_API_KEY | api.semanticscholar.org | 100 req/s with key (1/s without) |
| NCBI E-utilities | NCBI_API_KEY | ncbi.nlm.nih.gov/account | 10 req/s with key (3/s without) |
Set via export or .env file.
export http_proxy=http://127.0.0.1:7890
export https_proxy=http://127.0.0.1:7890
python scripts/preflight.py
Run before batch operations to verify API endpoints are reachable.
The format converter (scripts/format-converter.py) uses Python stdlib only — no extra dependencies. Run python scripts/format-converter.py --test to verify the conversion pipeline.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub yuanyuanma03/academic-research-skills --plugin nature-academic-search