pubmed

Name: pubmed
Author: ai4protein

244stars35forks

How to install pubmed?

ai4protein/venusfactory2/pubmed

$npx -y skills add ai4protein/VenusFactory2 --skill pubmed

Installs into the current project.

Summary

PubMed — NCBI's biomedical literature database (>35M citations). Keyword search inline, or batch-fetch full title + structured abstract + authors + DOI for a known list of PMIDs. Use for medical / biological literature lookup, citation resolution, or building an abstract corpus f

Files · 1

View on GitHub

SKILL.md

1	# PubMed
2
3	## Overview
4
5	Two complementary tools: existing `query_pubmed_tool` (keyword search, returns small JSON inline) + new `download_pubmed_abstracts_by_pmids` (batch-fetch full abstracts by PMID list, one efetch XML call, saves normalized JSON to disk).
6
7	## Project Tools (VenusFactory2)
8
9	\| Tool \| Args \| Returns \| Description \|
10	\|------\|------\|---------\|--------------\|
11	\| query_pubmed \| `query` (text), `max_results` (default 5, max 50), `max_content_length` \| JSON list of paper records inline \| Keyword search; small payload to agent. \|
12	\| download_pubmed_abstracts_by_pmids \| `pmids` (list of PMID strings, max 200 per call), `out_path` (JSON file path), `timeout` (default 60s) \| rich JSON envelope; saved file is `{requested_pmids, articles[]}` where each article has `pmid, title, authors, journal, year, doi, abstract` (structured abstracts join `Label: body` segments with newlines) \| Batch-fetch full abstracts + metadata by PMID via efetch. \|
13
14	## When to Use Each
15
16	\| Goal \| Tool \|
17	\|---\|---\|
18	\| "Find papers about X" \| `query_pubmed` \|
19	\| "Get me the full abstracts for these 50 PMIDs" \| `download_pubmed_abstracts_by_pmids` \|
20	\| Build a corpus for fine-tuning a biomedical NLP model \| `query_pubmed` → collect PMIDs → batch fetch via `download_pubmed_abstracts_by_pmids` \|
21	\| Resolve a citation string to a PMID \| (out of scope here — use the search tool with the citation text, parse hits) \|
22
23	## Output Schema for `download_pubmed_abstracts_by_pmids`
24
25	```json
26	{
27	"requested_pmids": ["34265844", "37962427", ...],
28	"articles": [
29	{
30	"pmid": "34265844",
31	"title": "Highly accurate protein structure prediction with AlphaFold",
32	"authors": ["Jumper J", "Evans R", ...],
33	"journal": "Nature",
34	"year": "2021",
35	"doi": "10.1038/s41586-021-03819-2",
36	"abstract": "Proteins are essential to life..."
37	},
38	...
39	]
40	}
41	```
42
43	Structured abstracts (with `BACKGROUND:`/`METHODS:`/`RESULTS:`/`CONCLUSIONS:` sections) are joined with `\n` and each section is prefixed by its label.
44
45	## Rate Limiting
46
47	- Without `NCBI_API_KEY`: 3 req/s.
48	- With `NCBI_API_KEY` (free; get at https://www.ncbi.nlm.nih.gov/account/settings/): 10 req/s.
49	- `download_pubmed_abstracts_by_pmids` does ONE efetch for the whole batch — much friendlier than N individual fetches.
50	- Hard cap: 200 PMIDs per call (split into chunks if you need more).
51
52	## Common Mistakes
53
54	- PMID as int: the tool accepts strings; pass `"34265844"`, not `34265844`. (Int is coerced to str internally but use string defensively.)
55	- >200 PMIDs in one call: returns `ValidationError`. Split into chunks of ≤200.
56	- Missing abstract: not all PubMed records have abstracts (older / non-research / book chapters). The `abstract` field will be `null` for those.
57	- Confusing PMID with PMCID: PMID is a number (e.g. `34265844`); PMCID is `PMC<number>` (e.g. `PMC8371605`). This tool uses PMIDs.
58
59	## References
60
61	- [PubMed E-utilities](https://www.ncbi.nlm.nih.gov/books/NBK25501/)
62	- [Get an NCBI API key](https://www.ncbi.nlm.nih.gov/account/settings/) (free)
63	- [PMID vs PMCID](https://www.nlm.nih.gov/bsd/policy/dla_FAQ.html)

People who liked this also viewed

6 picks

Type

pubmed

244stars35forks

View on GitHub

How to install pubmed?

ai4protein/venusfactory2/pubmed

$npx -y skills add ai4protein/VenusFactory2 --skill pubmed

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# PubMed
2
3	## Overview
4
5	Two complementary tools: existing `query_pubmed_tool` (keyword search, returns small JSON inline) + new `download_pubmed_abstracts_by_pmids` (batch-fetch full abstracts by PMID list, one efetch XML call, saves normalized JSON to disk).
6
7	## Project Tools (VenusFactory2)
8
9	\| Tool \| Args \| Returns \| Description \|
10	\|------\|------\|---------\|--------------\|
11	\| query_pubmed \| `query` (text), `max_results` (default 5, max 50), `max_content_length` \| JSON list of paper records inline \| Keyword search; small payload to agent. \|
12	\| download_pubmed_abstracts_by_pmids \| `pmids` (list of PMID strings, max 200 per call), `out_path` (JSON file path), `timeout` (default 60s) \| rich JSON envelope; saved file is `{requested_pmids, articles[]}` where each article has `pmid, title, authors, journal, year, doi, abstract` (structured abstracts join `Label: body` segments with newlines) \| Batch-fetch full abstracts + metadata by PMID via efetch. \|
13
14	## When to Use Each
15
16	\| Goal \| Tool \|
17	\|---\|---\|
18	\| "Find papers about X" \| `query_pubmed` \|
19	\| "Get me the full abstracts for these 50 PMIDs" \| `download_pubmed_abstracts_by_pmids` \|
20	\| Build a corpus for fine-tuning a biomedical NLP model \| `query_pubmed` → collect PMIDs → batch fetch via `download_pubmed_abstracts_by_pmids` \|
21	\| Resolve a citation string to a PMID \| (out of scope here — use the search tool with the citation text, parse hits) \|
22
23	## Output Schema for `download_pubmed_abstracts_by_pmids`
24
25	```json
26	{
27	"requested_pmids": ["34265844", "37962427", ...],
28	"articles": [
29	{
30	"pmid": "34265844",
31	"title": "Highly accurate protein structure prediction with AlphaFold",
32	"authors": ["Jumper J", "Evans R", ...],
33	"journal": "Nature",
34	"year": "2021",
35	"doi": "10.1038/s41586-021-03819-2",
36	"abstract": "Proteins are essential to life..."
37	},
38	...
39	]
40	}
41	```
42
43	Structured abstracts (with `BACKGROUND:`/`METHODS:`/`RESULTS:`/`CONCLUSIONS:` sections) are joined with `\n` and each section is prefixed by its label.
44
45	## Rate Limiting
46
47	- Without `NCBI_API_KEY`: 3 req/s.
48	- With `NCBI_API_KEY` (free; get at https://www.ncbi.nlm.nih.gov/account/settings/): 10 req/s.
49	- `download_pubmed_abstracts_by_pmids` does ONE efetch for the whole batch — much friendlier than N individual fetches.
50	- Hard cap: 200 PMIDs per call (split into chunks if you need more).
51
52	## Common Mistakes
53
54	- PMID as int: the tool accepts strings; pass `"34265844"`, not `34265844`. (Int is coerced to str internally but use string defensively.)
55	- >200 PMIDs in one call: returns `ValidationError`. Split into chunks of ≤200.
56	- Missing abstract: not all PubMed records have abstracts (older / non-research / book chapters). The `abstract` field will be `null` for those.
57	- Confusing PMID with PMCID: PMID is a number (e.g. `34265844`); PMCID is `PMC<number>` (e.g. `PMC8371605`). This tool uses PMIDs.
58
59	## References
60
61	- [PubMed E-utilities](https://www.ncbi.nlm.nih.gov/books/NBK25501/)
62	- [Get an NCBI API key](https://www.ncbi.nlm.nih.gov/account/settings/) (free)
63	- [PMID vs PMCID](https://www.nlm.nih.gov/bsd/policy/dla_FAQ.html)

People who liked this also viewed

6 picks

Type