Openalex

Organization

ai4protein

openalex

OpenAlex — free, comprehensive scholarly graph (works, authors, sources/journals, institutions, topics, concepts, funders). Search papers by keyword/filter/sort, fetch a single entity by ID, look up author profiles, institutions, citation networks. Use whenever the user asks about papers, citation counts, author publications, institution outputs, or research topics. Lower-friction alternative to Semantic Scholar / Web of Science / Scopus.

Overview

Publisher	ai4protein
Repository	`VenusFactory2`
Skill name	`openalex`
Stars	255
Forks	37
Bundled files	Instructions only
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 Openalex 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/openalex
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/openalex .claude/skills/openalex

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

Use it in TypingMind

Enable Openalex 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 Openalex 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 Openalex 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.

OpenAlex

Overview

OpenAlex is a free index of >250M scholarly works built atop the Microsoft Academic Graph's successor. No API key required for the polite pool. Optional OPENALEX_EMAIL / USER_EMAIL env var → priority routing; OPENALEX_API_KEY env var → premium pool with higher limits.

Project Tools (VenusFactory2)

Tool	Args	Returns	Description
download_openalex_entries_by_query	`entity_type` (required: `works` \| `authors` \| `sources` \| `institutions` \| `topics` \| `concepts` \| `publishers` \| `funders` \| ...), `out_dir`, `search` (free-text keyword), `filter_expr` (OpenAlex filter syntax, e.g. `authorships.author.id:A123,publication_year:>2020`), `sort` (e.g. `cited_by_count:desc`), `per_page` (default 25, max 200), `page` (default 1), `timeout`	rich JSON envelope; saved JSON page at `file_info.file_path`; `biological_metadata.total_count` + `result_count` + `next_page` hint	Search OpenAlex.
download_openalex_entry_by_id	`entity_type`, `openalex_id` (e.g. `W3177828909`, `A5089215617`, or full openalex.org URL), `out_dir`, `timeout`	rich JSON envelope; full entity JSON at `file_info.file_path`; `biological_metadata` extracts `display_name`, `cited_by_count`, `publication_year`, `doi`	Fetch a single entity by ID.

When to Use This Skill

"Find papers about X" / "what's the most cited paper on Y" → search works with sort=cited_by_count:desc
"Who is the most prolific author in topic X" → search authors with filter_expr=topics.id:T...
"Get me the full record for [DOI/work ID]" → download_openalex_entry_by_id on works
"What's institution X publishing about lately" → search works with filter_expr=authorships.institutions.id:I...,publication_year:2024

Filter Syntax Cheatsheet

Filters are comma-separated for AND, | inside a value for OR. Examples:

Filter	Effect
`publication_year:2023`	exact year
`publication_year:>2020`	year > 2020
`from_publication_date:2023-01-01`	inclusive lower bound
`cited_by_count:>100`	well-cited papers
`authorships.author.id:A5089215617`	papers by a given author
`authorships.institutions.id:I4210090411`	papers from a given institution (`I4210090411` = DeepMind)
`topics.id:T11444`	papers in a specific topic
`is_oa:true`	open access only
`type:journal-article`	filter by work type
`doi:10.1038/s41586-021-03819-2`	exact DOI lookup

ID Prefixes

W = Work (paper)
A = Author
S = Source (journal/conference/book/repo)
I = Institution
T = Topic
C = Concept
P = Publisher
F = Funder

Pagination

Set per_page ≤ 200 and walk page=1, 2, ... until biological_metadata.next_page is None.
For deep paging (>10k results), use OpenAlex's cursor pagination instead — out of scope for this tool; download the first page, inspect meta.next_cursor, then drive the cursor manually.

Common Mistakes

per_page=1000: max is 200. Set to 200 then paginate.
Wrong entity prefix: download_openalex_entry_by_id(entity_type='works', openalex_id='A123...') will 404 — the prefix A says author, not work.
Filtering without an entity context: filter_expr=author.id:A123 makes no sense for entity_type=authors (use id:A123 instead).
Free-text vs filter confusion: search="cited_by_count desc" won't sort — use the sort parameter.

References

OpenAlex docs
Entity-type filter ref (one page per entity type)
Get an OpenAlex API key (optional)

Frequently asked questions

What does the Openalex AI skill do?

Why use Openalex on TypingMind?

Because you install it once and use it with any model. Openalex 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 Openalex in TypingMind?

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

Which AI models can use Openalex?

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 Openalex?

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

Is the Openalex AI skill free?

It is published on GitHub by ai4protein. Check the repository for licensing terms. 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

Swarm Advanced

ruvnet

CommunityPopular

Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows

Dcf Valuation

Discounted cash flow valuation and intrinsic value analysis for public companies. Use when the brief asks for DCF, fair value, intrinsic value, price target, undervalued or overvalued analysis, or…

Magazine Web Ppt

For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment,…

Html Ppt Zhangzara Cartesian

nexu-io

OrganizationPopular

An economics senior thesis on the employment effects of local minimum-wage increases — identification strategy, evidence, and limitations. Built as a decision-grade coursework defense deck for thesis…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

OpenAlex

Overview

Project Tools (VenusFactory2)

When to Use This Skill

Filter Syntax Cheatsheet

ID Prefixes

Pagination

Common Mistakes

References

Frequently asked questions

Related AI Skills

Set up your own AI workspace now