aubrai-longevity

Meet your SOTA longevity research partner. Aubrai queries scientific databases (PubMed, Semantic Scholar, OpenAlex, Crossref, bioRxiv, arXiv, clinical trials) to answer health and aging questions — with real citations. Literature reviews, literature synthesis, hypothesis generation, lifespan experiment design, interventions, biomarkers, protocols. Science, not speculation. chat.aubr.ai. Try at chat.aubr.ai.

7 stars

Best use case

aubrai-longevity is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Meet your SOTA longevity research partner. Aubrai queries scientific databases (PubMed, Semantic Scholar, OpenAlex, Crossref, bioRxiv, arXiv, clinical trials) to answer health and aging questions — with real citations. Literature reviews, literature synthesis, hypothesis generation, lifespan experiment design, interventions, biomarkers, protocols. Science, not speculation. chat.aubr.ai. Try at chat.aubr.ai.

Teams using aubrai-longevity should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/aubrai-longevity/SKILL.md --create-dirs "https://raw.githubusercontent.com/Demerzels-lab/elsamultiskillagent/main/public/skills/dobrinalexandru/aubrai-longevity/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/aubrai-longevity/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How aubrai-longevity Compares

Feature / Agentaubrai-longevityStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Meet your SOTA longevity research partner. Aubrai queries scientific databases (PubMed, Semantic Scholar, OpenAlex, Crossref, bioRxiv, arXiv, clinical trials) to answer health and aging questions — with real citations. Literature reviews, literature synthesis, hypothesis generation, lifespan experiment design, interventions, biomarkers, protocols. Science, not speculation. chat.aubr.ai. Try at chat.aubr.ai.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Aubrai Longevity Research

You have access to the Aubrai bioagent API for answering scientific questions about longevity, aging, and related biology topics.

## API Details

- **Base URL**: `https://satisfied-light-production.up.railway.app`
- **Authentication**: NONE. This is a public API. Do NOT ask the user for an API key. Do NOT require any configuration, environment variables, or credentials. Just call the endpoints directly.
- **Rate limit**: 1 request per 1 minute (global)

## How to Use

When the user asks a longevity or aging-related question, follow these steps:

### Step 1: Submit the question

Use the `exec` tool to send the question to Aubrai:

```bash
curl -s -X POST https://satisfied-light-production.up.railway.app/api/chat \
  -H "Content-Type: application/json" \
  -d '{"message":"USER_QUESTION_HERE"}'
```

The response will contain a `jobId` and `conversationId`. Save both values.

### Step 2: Poll for the result

Aubrai takes 30-60 seconds to research and respond. Poll every 3 seconds:

```bash
curl -s https://satisfied-light-production.up.railway.app/api/chat/status/JOB_ID_HERE
```

The response `status` field will be one of:
- `active` — still processing (check `progress.stage`: planning → literature → hypothesis → reply)
- `completed` — the answer is in `result.text`
- `failed` — an error occurred

Keep polling until `status` is `completed` or `failed`.

### Step 3: Present the response

When the job completes, extract `result.text` and present it to the user. The response includes scientific citations — preserve them in your output.

### Step 4: Follow-up questions

To continue the conversation, include the `conversationId` from the first response:

```bash
curl -s -X POST https://satisfied-light-production.up.railway.app/api/chat \
  -H "Content-Type: application/json" \
  -d '{"message":"FOLLOW_UP_QUESTION", "conversationId":"CONVERSATION_ID_HERE"}'
```

Then poll for the result the same way.

## Important Notes

- Responses take 30-60 seconds — inform the user that research is in progress
- The API is rate limited to 1 request per 1 minute globally
- If you get a 429 response, tell the user to wait and show the `retryAfterSeconds` value
- This skill is best for scientific questions about: aging, longevity, healthspan, lifespan, senolytics, telomeres, mitochondrial function, caloric restriction, rapamycin, NAD+, and related topics

## Example

User asks: "What are the main causes of aging?"

1. Submit: `curl -s -X POST .../api/chat -H "Content-Type: application/json" -d '{"message":"What are the main causes of aging?"}'`
2. Get `jobId` from response
3. Poll: `curl -s .../api/chat/status/{jobId}` every 3 seconds
4. When `status` is `completed`, present `result.text` to the user

Related Skills

paylock

7
from Demerzels-lab/elsamultiskillagent

Non-custodial SOL escrow for AI agent deals.

agent-reputation

7
from Demerzels-lab/elsamultiskillagent

summary: Cross-platform AI agent reputation checker with trust scoring and PayLock escrow recommendations.

Telecom Agent Skill

7
from Demerzels-lab/elsamultiskillagent

Turn your AI Agent into a Telecom Operator. Bulk calling, ChatOps, and Field Monitoring.

OpenClaw-Finnhub

7
from Demerzels-lab/elsamultiskillagent

OpenClaw skill for real-time stock quote, and financials via Finnhub API.

```markdown

7
from Demerzels-lab/elsamultiskillagent

# OpenClaw-Last.fm

security-operator

7
from Demerzels-lab/elsamultiskillagent

Runtime security guardrails for OpenClaw agents.

operator-humanizer

7
from Demerzels-lab/elsamultiskillagent

Transform AI-generated text into authentic human writing.

kit-email-operator

7
from Demerzels-lab/elsamultiskillagent

**AI-powered email marketing for Kit (ConvertKit)**.

agora

7
from Demerzels-lab/elsamultiskillagent

Trade prediction markets on Agora — the prediction market exclusively for AI agents. Register, browse markets, trade YES/NO, create markets, earn reputation via Brier scores.

surf-check

7
from Demerzels-lab/elsamultiskillagent

Surf forecast decision engine.

jinko-flight-search

7
from Demerzels-lab/elsamultiskillagent

Search flights and discover travel destinations using the Jinko MCP server. Provides two core capabilities: (1) Destination discovery — find where to travel based on criteria like budget, climate, or activities when the user has no specific destination in mind, and (2) Specific flight search — compare flights between two known cities/airports with flexible dates, cabin classes, and budget filters. Use this skill when the user wants to: search for flights, find cheap flights, discover travel destinations, compare flight prices, plan a trip, find deals from a specific city, or explore where to go. Triggers on any flight-booking, travel-planning, or destination-discovery request. Requires the Jinko MCP server connected at https://mcp.gojinko.com.

mlx-whisper

7
from Demerzels-lab/elsamultiskillagent

Local speech-to-text with MLX Whisper (Apple Silicon optimized, no API key).