# Tashan SciSpark Research Assistant

> Use this tool when you need to automate the discovery and analysis of scientific papers, generate novel research hypotheses, and create comprehensive paper drafts. It solves problems related to research idea generation, paper analysis, and entity extraction, accepting inputs such as research topics and keywords, and producing outputs like refined hypotheses and paper drafts. Ideal for researchers, scientists, and academics looking to streamline their research workflow and identify innovative ideas.

Canonical page: https://skillsregistry.net/skills/daiduo2-tashan-scispark  
JSON: https://api.skillsregistry.net/v1/skills/daiduo2-tashan-scispark

## Description

Tashan SciSpark automates scientific paper discovery, analysis, and idea generation through integration with arXiv, Google Scholar, and multiple LLM providers including OpenAI, DeepSeek, and Gemini. The system employs a Mixture of Agents approach for collaborative idea refinement, combining Bayesian reasoning, automated feature engineering, and transformer-based analysis to generate novel research hypotheses and comprehensive paper drafts. Built with FastAPI and Celery for scalable processing, it includes specialized prompt templates for entity extraction, hypothesis generation, and technical optimization.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/daiduo2-tashan-scispark)
- **Repository:** <https://github.com/daiduo2/tashan_scispark_mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "daiduo2-tashan-scispark"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/daiduo2-tashan-scispark` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/daiduo2-tashan-scispark/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt