Pubmed

Organization

ai4protein

pubmed

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 for downstream NLP. Honors NCBI_API_KEY env var.

Overview

Publisher	ai4protein
Repository	`VenusFactory2`
Skill name	`pubmed`
Stars	255
Forks	37
Bundled files	Instructions only
License	Unknown
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by ai4protein on GitHub. Read the source before you install it.

Installation

Install the Pubmed AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/ai4protein/VenusFactory2/tree/main/src/agent/skills/pubmed
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/ai4protein/VenusFactory2.git /tmp/VenusFactory2
mkdir -p .claude/skills
cp -r /tmp/VenusFactory2/src/agent/skills/pubmed .claude/skills/pubmed

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pubmed in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pubmed on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pubmed is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

PubMed

Overview

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).

Project Tools (VenusFactory2)

Tool	Args	Returns	Description
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.
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.

When to Use Each

Goal	Tool
"Find papers about X"	`query_pubmed`
"Get me the full abstracts for these 50 PMIDs"	`download_pubmed_abstracts_by_pmids`
Build a corpus for fine-tuning a biomedical NLP model	`query_pubmed` → collect PMIDs → batch fetch via `download_pubmed_abstracts_by_pmids`
Resolve a citation string to a PMID	(out of scope here — use the search tool with the citation text, parse hits)

Output Schema for `download_pubmed_abstracts_by_pmids`

json
{
  "requested_pmids": ["34265844", "37962427", ...],
  "articles": [
    {
      "pmid": "34265844",
      "title": "Highly accurate protein structure prediction with AlphaFold",
      "authors": ["Jumper J", "Evans R", ...],
      "journal": "Nature",
      "year": "2021",
      "doi": "10.1038/s41586-021-03819-2",
      "abstract": "Proteins are essential to life..."
    },
    ...
  ]
}

Structured abstracts (with BACKGROUND:/METHODS:/RESULTS:/CONCLUSIONS: sections) are joined with \n and each section is prefixed by its label.

Rate Limiting

Without NCBI_API_KEY: 3 req/s.
With NCBI_API_KEY (free; get at https://www.ncbi.nlm.nih.gov/account/settings/): 10 req/s.
download_pubmed_abstracts_by_pmids does ONE efetch for the whole batch — much friendlier than N individual fetches.
Hard cap: 200 PMIDs per call (split into chunks if you need more).

Common Mistakes

PMID as int: the tool accepts strings; pass "34265844", not 34265844. (Int is coerced to str internally but use string defensively.)
>200 PMIDs in one call: returns ValidationError. Split into chunks of ≤200.
Missing abstract: not all PubMed records have abstracts (older / non-research / book chapters). The abstract field will be null for those.
Confusing PMID with PMCID: PMID is a number (e.g. 34265844); PMCID is PMC<number> (e.g. PMC8371605). This tool uses PMIDs.

Frequently asked questions

What does the Pubmed AI skill do?

Why use Pubmed on TypingMind?

Because you install it once and use it with any model. Pubmed is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pubmed in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ai4protein/VenusFactory2/tree/main/src/agent/skills/pubmed. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pubmed?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pubmed?

As many as you like. As long as a model supports skills, you can use Pubmed with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pubmed AI skill free?

Yes. It is published on GitHub by ai4protein under the Unknown license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Firecrawl Build Search

firecrawl

OrganizationPopular

Integrate Firecrawl `/search` into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should…

Firecrawl Build

Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser…

Advisor Orchestrator Worker

Shubhamsaboo

CommunityPopular

Use when a task is too large for one model pass, needs parallel research or generation across many subtasks (like researching a dozen competitors at once), or the user asks to orchestrate multiple…

Openai Docs

Use for Codex models/pricing, scheduled tasks, skills, settings, setup, troubleshooting, customization, automations, and self-knowledge—including 'you,' 'your,' 'this app,' or 'this coding agent' when…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

PubMed

Overview

Project Tools (VenusFactory2)

When to Use Each

Output Schema for download_pubmed_abstracts_by_pmids

Rate Limiting

Common Mistakes

References

Frequently asked questions

Related AI Skills

Set up your own AI workspace now

Output Schema for `download_pubmed_abstracts_by_pmids`