# Symposium

> Symposium — sam-siavoshian-symposium. Use this tool when you need to augment knowledge retrieval capabilities beyond traditional large language models (LLMs). Symposium solves complex research problems by spawning parallel agents to uncover new information, achieving a +23.1% improvement on Terminal Bench 2.0 SWE tasks. It takes in research queries and outputs expanded knowledge sets, ideal for use cases where existing LLMs are insufficient.

Canonical page: https://skillsregistry.net/skills/sam-siavoshian-symposium  
JSON: https://api.skillsregistry.net/v1/skills/sam-siavoshian-symposium

## Description

Multi-agent reasoning MCP server for Claude Code. Spawns parallel research agents to find knowledge LLMs don't have. +23.1% on Terminal Bench 2.0 SWE tasks.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/sam-siavoshian/Symposium)

## 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": "sam-siavoshian-symposium"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sam-siavoshian-symposium` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sam-siavoshian-symposium/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