Skip to main content
skill CX Codex

biorxiv-search — Claude Code skill: semantic search of biology preprints

biorxiv-search is a Claude Code skill that searches bioRxiv preprints using natural-language queries. It returns full texts, figures, and relevance scores.

MIT 150 installs ★ 64 updated 2026-10-04

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add yorkeccak/scientific-skills --skill biorxiv-search -a claude-code
Open on GitHub

What biorxiv-search does

This skill wraps Valyu's semantic search API around the complete bioRxiv archive of biology preprints. Write a natural query—say, "DNA-binding proteins"—and get back relevant papers with relevance scores, full text, and links to figures. No parameter syntax, no faceted filters.

Internally, a Node.js script calls the Valyu API over built-in fetch with zero external dependencies. Results come as JSON: title, full content, images, bioRxiv URL. Pipe through jq to extract just links or text snippets. Requires a Valyu API key—$10 free credits covers dozens of searches. Set it up once with scripts/search setup <api-key>. Runs on Node.js 18+ with no other setup.

What it helps with

  • find preprints in your specialty beyond keyword matching
  • retrieve full article text plus figures in a single search
  • access research before it appears in peer-reviewed journals
  • gather material on molecular biology, genetics, or neuroscience
  • add bioRxiv search to an AI agent or workflow

Example prompts for the agent

  • Search bioRxiv for papers on CRISPR gene editing and off-target effects
  • Find preprints about embryonic stem cell differentiation pathways
  • Get the latest 20 papers on optogenetics in behavioral research

How to install biorxiv-search

1Skills CLI (Vercel)

npx skills add yorkeccak/scientific-skills --skill biorxiv-search -a claude-code

2Manually: put the files in place

~/.claude/skills/biorxiv-search/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/biorxiv-search/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about biorxiv-search

How do I install biorxiv-search in Claude Code?

Run npx skills add yorkeccak/scientific-skills --skill biorxiv-search -a claude-code, then open ~/.claude/skills/biorxiv-search/SKILL.md.

What do I need to use biorxiv-search?

Node.js 18+ and a Valyu API key (free, with $10 credits from https://platform.valyu.ai). The script has no external dependencies—it uses only built-in Node.js fetch.

How do I set up my Valyu API key?

Sign up at https://platform.valyu.ai and copy your key. On first search, the skill will ask for it; run scripts/search setup <your-key>, then retry the search.

Source text

SKILL.md · MIT
---
name: biorxiv-search
description: Search bioRxiv biology preprints with natural language queries. Semantic search powered by Valyu.
keywords:
  - biorxiv
  - biology-preprints
  - molecular-biology
  - genetics
  - life-sciences
  - semantic-search
license: MIT
---


# bioRxiv Search

Search the complete bioRxiv database of biological sciences preprints using natural language queries powered by Valyu's semantic search API.

## Why This Skill is Powerful

- **No API Parameter Parsing**: Just pass natural language queries directly - no need to construct complex search parameters
- **Semantic Search**: Understands the meaning of your query, not just keyword matching
- **Full-Text Access**: Returns complete article content, not just abstracts
- **Image Links**: Includes figures and images from papers
- **Comprehensive Coverage**: Access to all bioRxiv preprints in biological sciences

## Requirements

1. Node.js 18+ (uses built-in fetch)
2. Valyu API key from https://platform.valyu.ai ($10 free credits)

## CRITICAL: Script Path Resolution

The `scripts/search` commands in this documentation are relative to this skill's installation directory.

Before running any command, locate the script using:

```bash
BIORXIV_SCRIPT=$(find ~/.claude/plugins/cache -name "search" -path "*/biorxiv-search/*/scripts/*" -type f 2>/dev/null | head -1)
```

Then use the full path for all commands:
```bash
$BIORXIV_SCRIPT "CRISPR gene editing" 15
```

## API Key Setup Flow

When you run a search and receive `"setup_required": true`, follow this flow:

1. **Ask the user for their API key:**
   "To search bioRxiv, I need your Valyu API key. Get one free ($10 credits) at https://platform.valyu.ai"

2. **Once the user provides the key, run:**
   ```bash
   scripts/search setup <api-key>
   ```

3. **Retry the original search.**

### Example Flow:
```
User: Search bioRxiv for CRISPR advances
→ Response: {"success": false, "setup_required": true, ...}
→ Claude asks: "Please provide your Valyu API key from https://platform.valyu.ai"
→ User: "val_abc123..."
→ Claude runs: scripts/search setup val_abc123...
→ Response: {"success": true, "type": "setup", ...}
→ Claude retries: scripts/search "CRISPR advances" 10
→ Success!
```

## When to Use This Skill

- Finding biology research not yet published in journals
- Cross-disciplinary life sciences research
- Rapid access to unpublished experimental data
- Disease mechanism research
- Evolutionary and developmental biology studies
- Ecological research and conservation biology
## Output Format

```json
{
  "success": true,
  "type": "biorxiv_search",
  "query": "CRISPR gene editing",
  "result_count": 10,
  "results": [
    {
      "title": "Article Title",
      "url": "https://biorxiv.org/content/...",
      "content": "Full article text with figures...",
      "source": "biorxiv",
      "relevance_score": 0.95,
      "images": ["https://example.com/figure1.jpg"]
    }
  ],
  "cost": 0.025
}
```

## Processing Results

### With jq

```bash
# Get article titles
scripts/search "query" 10 | jq -r '.results[].title'

# Get URLs
scripts/search "query" 10 | jq -r '.results[].url'

# Extract full content
scripts/search "query" 10 | jq -r '.results[].content'
```

## Common Use Cases

### Molecular Biology

```bash
# Find recent molecular biology papers
scripts/search "protein-protein interaction networks" 50
```

### Neuroscience

```bash
# Search for neuroscience research
scripts/search "optogenetics in behavior studies" 20
```

### Genomics

```bash
# Find genomics papers
scripts/search "single cell RNA sequencing analysis" 15
```

### Developmental Biology

```bash
# Search for developmental biology papers
scripts/search "embryonic stem cell differentiation" 25
```


## Error Handling

All commands return JSON with `success` field:

```json
{
  "success": false,
  "error": "Error message"
}
```

Exit codes:
- `0` - Success
- `1` - Error (check JSON for details)

## API Endpoint

- Base URL: `https://api.valyu.ai/v1`
- Endpoint: `/search`
- Authentication: X-API-Key header

## Architecture

```
scripts/
├── search          # Bash wrapper
└── search.mjs      # Node.js CLI
```

Direct API calls using Node.js built-in `fetch()`, zero external dependencies.

## Adding to Your Project

If you're building an AI project and want to integrate bioRxiv Search directly into your application, use the Valyu SDK:

### Python Integration

```python
from valyu import Valyu

client = Valyu(api_key="your-api-key")

response = client.search(
    query="your search query here",
    included_sources=["valyu/valyu-biorxiv"],
    max_results=20
)

for result in response["results"]:
    print(f"Title: {result['title']}")
    print(f"URL: {result['url']}")
    print(f"Content: {result['content'][:500]}...")
```

### TypeScript Integration

```typescript
import { Valyu } from "valyu-js";

const client = new Valyu("your-api-key");

const response = await client.search({
  query: "your search query here",
  includedSources: ["valyu/valyu-biorxiv"],
  maxResults: 20
});

response.results.forEach((result) => {
  console.log(`Title: ${result.title}`);
  console.log(`URL: ${result.url}`);
  console.log(`Content: ${result.content.substring(0, 500)}...`);
});
```

See the [Valyu docs](https://docs.valyu.ai) for full integration examples and SDK reference.

© yorkeccak · MIT · yorkeccak/scientific-skills

Similar skills

All skills for Science and research →

From the same set13

The whole set →
literature-search literature-search — a Claude Code skill that queries PubMed, arXiv, bioRxiv and medRxiv together using plain-language phrases. One command returns full texts, figures and relevance scores from all four databases. CX Codex +1 605installs medrxiv-search medrxiv-search is a Claude Code skill that searches medRxiv medical preprints with plain-language queries and retrieves full article text. It supports searches for clinical and epidemiological research. CX Codex +1 196installs clinical-trials-search clinical-trials-search searches ClinicalTrials.gov using natural language queries via Valyu semantic search API. CX Codex +1 174installs drug-discovery-search drug-discovery-search is a Claude Code skill for natural-language searches of compounds, targets, and drug information. It supports target research, compound optimization, and safety assessment. CX Codex +1 169installs drug-labels-search drug-labels-search is a skill for Claude Code that searches official FDA drug labels via the Valyu API, returning relevant sections for natural-language queries. CX Codex +1 137installs drugbank-search drugbank-search is a Claude Code skill that searches DrugBank for medicines, interactions, mechanisms of action, and targets. It answers plain-language questions about these topics. CX Codex +1 136installs open-targets-search open-targets-search — a skill that asks Open Targets about drug-disease associations in plain language, with Valyu handling the semantic search. Handy when you want target evidence without assembling API parameters. CX Codex +1 130installs chembl-search chembl-search is a skill that searches ChEMBL for bioactive compounds and assay data from natural-language queries, supporting target-based searches and research into biological activity. CX Codex +1 128installs

Project sponsors

Companies that keep this analytics open