RepoAI
Browse MCPs

Literature Search Biorxiv

88TrustedShips scripts

Access biology and medical preprint metadata directly from bioRxiv and medRxiv repositories.

What it does

Literature Search Biorxiv integrates specialized scripts into your environment to query preprint archives. It shifts your workflow from manual browser-based searching to programmatic retrieval, allowing you to incorporate academic findings into your workspace without leaving the terminal.

The tool handles the communication with the archives, managing pagination and rate-limiting protocols automatically. When you need specific paper details or bulk metadata for a particular timeframe, it captures the data into structured files for easier analysis.

When it earns its place

Reach for it when…

Apply this when you need precise metadata for a known paper via DOI or when exploring recent submissions in specific life science or medical disciplines within a tight timeframe of up to four weeks.

Look elsewhere when…

Avoid this for open-ended exploratory research that lacks a date constraint or category, as the lack of server-side topic indexing makes broad searches inefficient and prone to timeouts. Use a dedicated bibliographic database or academic search engine instead for generalized discovery.

What to say to use it

You never invoke a skill directly — the assistant picks it up when your request matches what it covers. These are the kinds of things that do that.

  • Pull the metadata for the preprint with this DOI
  • Find new neuroscience preprints from the first two weeks of January
  • Show me medical papers related to this condition published this month
  • Download details for recent bioRxiv submissions in genomics

Install it

Install for all your projects

Copy the skill directory into your personal skills folder. Claude picks it up on its own the next time your request matches what it does — there is nothing to enable.

bash
git clone --depth 1 --branch main https://github.com/google-deepmind/science-skills.git /tmp/science-skills
mkdir -p ~/.claude/skills
cp -r /tmp/science-skills/skills/literature_search_biorxiv ~/.claude/skills/literature-search-biorxiv

Install for one project only

Put it in the project's own skills folder instead, so it can be committed and shared with everyone working on that repository.

bash
cp -r /tmp/science-skills/skills/literature_search_biorxiv .claude/skills/literature-search-biorxiv

If a skill of the same name exists in both places, the personal one wins.

Installing on Claude.ai or through the API instead? The full guide covers every surface.

Pair it with an MCP server

Literature Search Biorxiv changes how the work is done. These servers change what Claude can reach while doing it.

How skills and MCP servers differ →