K-Dense-AI/scientific-agent-skills / skills/paper-lookup
paper-lookup
FlaggedSearches 18 scholarly APIs for papers, preprints, citations, open-access full text, repository records, and journal OA status, and returns results with reproducible provenance. Covers PubMed, PMC, Europe PMC, bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall, OpenCitations, PubTator3, Zenodo, Figshare, ROR, BioStudies, and DOAJ. Use when searching for papers, citations, DOI/PMID/arXiv lookups, abstracts, full text, open-access PDFs, preprints, citation graphs, author publications, biomedical entity annotations, deposited records (Zenodo, Figshare, BioStudies), institution ROR IDs, or any scholarly literature query. Triggers on mentions of any supported database or requests like "find papers on X", "look up this DOI", "who cites this paper", or "get me the PDF".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 25.5 KB |
| references/arxiv.md | markdown | 11.9 KB |
| references/biorxiv.md | markdown | 6.7 KB |
| references/biostudies.md | markdown | 4.0 KB |
| references/core.md | markdown | 4.6 KB |
| references/crossref.md | markdown | 5.5 KB |
| references/doaj.md | markdown | 4.2 KB |
| references/europepmc.md | markdown | 9.0 KB |
| references/figshare.md | markdown | 3.1 KB |
| references/medrxiv.md | markdown | 5.0 KB |
| references/openalex.md | markdown | 5.5 KB |
| references/opencitations.md | markdown | 4.6 KB |
| references/pmc.md | markdown | 7.1 KB |
| references/pubmed.md | markdown | 4.5 KB |
| references/pubtator.md | markdown | 4.5 KB |
| references/ror.md | markdown | 4.2 KB |
| references/semantic-scholar.md | markdown | 7.1 KB |
| references/unpaywall.md | markdown | 3.5 KB |
| references/zenodo.md | markdown | 3.8 KB |
| scripts/_common.py | script | 8.2 KB |
| scripts/arxiv_atom.py | script | 8.0 KB |
| scripts/jats_to_text.py | script | 11.0 KB |
| scripts/openalex_abstract.py | script | 6.3 KB |
| scripts/paginate.py | script | 19.2 KB |
references/pmc.md
View on GitHub# PMC (PubMed Central)
PMC is a **full-text archive** of biomedical and life sciences articles. It is separate from PubMed -- PubMed has citations/abstracts, PMC has full text. Not all PubMed articles are in PMC, and vice versa.
## E-utilities for PMC
### Base URL
```
https://eutils.ncbi.nlm.nih.gov/entrez/eutils/
```
Same E-utilities as PubMed, but with `db=pmc`.
### eSearch -- Search PMC
```
GET /esearch.fcgi?db=pmc&term={query}&retmode=json
```
Same parameters as PubMed eSearch. PubMed and PMC ESearch are both limited to the first 10,000 matching IDs; partition larger searches or use an appropriate bulk workflow. Returns PMC UIDs (numeric, e.g., `13033346`). You need to prepend "PMC" to get a PMCID (e.g., `PMC13033346`).
### eFetch -- Get Full Text XML
```
GET /efetch.fcgi?db=pmc&id={pmcid}&retmode=xml
```
| rettype | retmode | Returns |
|---------|---------|---------|
| *(omit)* | `xml` | JATS XML -- full text for **eligible OA and Author Manuscript articles**; metadata only otherwise, with no error. See the hazard below before using this. |
**Example:**
```
https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pmc&id=7029759&retmode=xml
```
The XML uses JATS (Journal Article Tag Suite) format:
- `<front>` -- journal metadata, article metadata, author info
- `<body>` -- full article text with `<sec>` sections, `<p>` paragraphs, `<fig>` figures
- `<back>` -- `<ref-list>` with all references
Pass numeric IDs only (not "PMC7029759", just "7029759").
### Hazard: eFetch returns metadata-only XML for non-OA articles, with HTTP 200
This is the most dangerous failure in this skill, because nothing about the response says it failed.
When the publisher does not permit XML redistribution, eFetch returns a **well-formed
`<pmc-articleset>`** containing `<front>` metadata, **no `<body>`**, and the reason as an XML
*comment* -- which every standard parser discards. Verified 2026-07-27 on PMCID 1500000:
```
HTTP/1.1 200 OK
<pmc-articleset><article article-type="obituary" ...>
<!--The publisher of this article does not allow downloading of the full text in XML form.-->
<front>...</front>
</article></pmc-articleset>
```
An agent that fetches this, parses it, and reports "retrieved full text" has retrieved only the
title, journal, and author list. An article being readable on the PMC website does not establish that its XML is available through this API. The absence of a body is a retrieval limitation, not evidence about the article contents.
**Always confirm `<body>` exists before claiming you have full text.** Two ways, in order of
preference:
1. **Use `scripts/jats_to_text.py`**, which exits non-zero with `no <body> element` when the article
is metadata-only and surfaces the publisher-restriction comment instead of dropping it.
2. **Fall back to Europe PMC** (`references/europepmc.md`), whose `fullTextXML` endpoint returns a
clean **404** for the same article rather than a 200 with no body -- an honest failure is easier to
handle than a plausible one.
If full text is unavailable, say so explicitly and offer the abstract (PubMed eFetch) or an OA copy
elsewhere (Unpaywall, CORE) rather than presenting `<front>` metadata as the article.
## Retired OA Web Service
The PMC OA Web Service (`oa.fcgi`) was retired on **2026-08-25**. Do not use it
as an availability preflight, retraction check, or source of FTP package links.
The old OA-package FTP workflow is no longer the supported retrieval path.
For a targeted paper, fetch via E-utilities, BioC, or Europe PMC and validate
that the response actually contains article text. For bulk access consult
[PMC Article Datasets](https://pmc.ncbi.nlm.nih.gov/tools/textmining/) and the
[PMC Cloud Service](https://pmc.ncbi.nlm.nih.gov/tools/cloud/).
Use the article's current license for reuse decisions. For retractions inspect
PubMed/publisher notices and Crossref update relationships; a missing OA copy
says nothing about retraction status.
## BioC API -- Structured Full Text
An alternative way to get full text in a structured passage format.
### Base URL
```
https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/
```
### Endpoint
```
GET /BioC_{format}/{id}/{encoding}
```
| Parameter | Values |
|-----------|--------|
| `format` | `json` or `xml` |
| `id` | PMID (e.g., `17299597`) or PMCID (e.g., `PMC7029759`) |
| `encoding` | `unicode` or `ascii` |
**Example:**
```
https://www.ncbi.nlm.nih.gov/research/bionlp/RESTful/pmcoa.cgi/BioC_json/PMC7029759/unicode
```
**Response structure (JSON):** a list of BioC collections. Read `[0].documents`, not a top-level `documents` object.
```json
[{
"source": "PMC",
"documents": [{
"id": "PMC7029759",
"infons": {"license": "...", "doi": "..."},
"passages": [
{
"offset": 0,
"infons": {"section_type": "TITLE"},
"text": "Article title..."
},
{
"offset": 42,
"infons": {"section_type": "ABSTRACT"},
"text": "Abstract text..."
},
{
"offset": 500,
"infons": {"section_type": "INTRO"},
"text": "Introduction text..."
}
]
}]
}]
```
Section types: `TITLE`, `ABSTRACT`, `INTRO`, `METHODS`, `RESULTS`, `DISCUSS`, `CONCL`, `REF`, `SUPPL`, `FIG`, `TABLE`
**Coverage:** PMC Open Access and eligible Author Manuscript articles; not all PMC records. Do not use the count in the 2019 BioC paper as a current coverage total.
## PMC ID Converter API
Converts between PMID, PMCID, DOI, and Manuscript ID.
### Base URL
```
https://pmc.ncbi.nlm.nih.gov/tools/idconv/api/v1/articles/
```
### Parameters
| Parameter | Required | Description |
|-----------|----------|-------------|
| `ids` | Yes | Up to 200 comma-separated IDs, all of the same identifier type |
| `idtype` | No | `pmcid`, `pmid`, `mid`, `doi` (default: auto-detect) |
| `format` | No | `json`, `xml`, `csv`, `html` (default: xml) |
| `tool` | Recommended | Your application name |
| `email` | Recommended | Your contact email |
**Example:**
```
https://pmc.ncbi.nlm.nih.gov/tools/idconv/api/v1/articles/?ids=PMC7029759&format=json
```
**Response:**
```json
{
"status": "ok",
"records": [{
"pmcid": "PMC7029759",
"pmid": "32117569",
"doi": "10.12688/f1000research.22211.2"
}]
}
```
The JSON `pmid` may be numeric; normalize identifiers to strings before joining across APIs. Inspect per-record errors/availability as well as top-level `status`. Only returns related identifiers for articles that are in PMC. If an article is in PubMed but not PMC, no PMCID will be returned.
## Rate Limits
| Service | Limit |
|---------|-------|
| E-utilities (`db=pmc`) | 3/sec without key, 10/sec with key |
| BioC API | Serialize conservatively; an E-utilities API key does not establish a higher BioC quota |
| ID Converter | Follow general NCBI policy |
Include `tool` and `email` parameters on E-utility requests. Large batch jobs should run outside peak hours (Mon-Fri 5AM-9PM ET).
## Official sources reviewed 2026-09-30
- https://pmc.ncbi.nlm.nih.gov/tools/developers/
- https://pmc.ncbi.nlm.nih.gov/tools/oa-service/
- https://pmc.ncbi.nlm.nih.gov/tools/id-converter-api/
- https://www.ncbi.nlm.nih.gov/research/bionlp/APIs/BioC-PMC/
- https://pmc.ncbi.nlm.nih.gov/tools/textmining/
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |