Xpersona
agentCLAWHUBUnverified

量化策略研发实验室

量化策略研发实验室 — 让 Claude 按顶级机构角色分工（高盛策略架构师、文艺复兴回测引擎、Two Sigma 风控、Citadel Alpha 研究、Jane Street 做市、AQR 因子模型...共 15 个角色）系统性地设计、验证、风控、执行量化交易策略。当用户要求设计量化策略、做回测、构建因子、风... Skill: 量化策略研发实验室 Owner: yili1992 Summary: 量化策略研发实验室 — 让 Claude 按顶级机构角色分工（高盛策略架构师、文艺复兴回测引擎、Two Sigma 风控、Citadel Alpha 研究、Jane Street 做市、AQR 因子模型...共 15 个角色）系统性地设计、验证、风控、执行量化交易策略。当用户要求设计量化策略、做回测、构建因子、风... Tags: latest:1.0.1 Version history: v1.0.1 | 2026-05-05T13:48:25.601Z | user quant-research-lab 1.0.1 - Added .gitignore file to define files and directories to be ignored by Git. - Added LICENSE file to specify the p

OpenClaw
View on ClawHubHomepage

Rank

62

Safety

84

Downloads

1.3k

Updated

Oct 10, 2026

Version

1.0.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor
Clawhubvendor · observed Oct 10, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 10, 2026
Adoption signal
1.3K downloadsadoption · observed Oct 10, 2026
Latest release
1.0.1release · observed May 5, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17612wey0k7hn9mryf4xn4kbs862ktp:quant-research-lab
  1. Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-yili1992-quant-research-lab/snapshot"

Documentation

CLAWHUB

143,420 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: quant-research-lab
description: "量化策略研发实验室 — 让 Claude 按顶级机构角色分工（高盛策略架构师、文艺复兴回测引擎、Two Sigma 风控、Citadel Alpha 研究、Jane Street 做市、AQR 因子模型...共 15 个角色）系统性地设计、验证、风控、执行量化交易策略。当用户要求设计量化策略、做回测、构建因子、风控建模、策略优化、执行算法设计时触发。用户可能提到：量化策略、回测、因子、alpha 信号、风控、仓位管理、做市、统计套利、配对交易、宏观交易、TWAP、VWAP、投资组合优化、交易系统架构。"
---

# quant-research-lab — 量化策略研发实验室

## 角色注册表

| ID | 角色 | 机构 | 文件 | depends_on | complexity | Phase |
|:---|:---|:---|:---|:---|:---|:---|
| 01 | 策略架构师 | Goldman Sachs | roles/01-gs-strategy-architect.md | - | high | 1 |
| 02 | 回测引擎 | Renaissance Technologies | roles/02-rentec-backtest-engine.md | 01 | normal | 1 |
| 03 | 风控经理 | Two Sigma | roles/03-twosigma-risk-manager.md | 01 | normal | 1 |
| 04 | Alpha 研究员 | Citadel | roles/04-citadel-alpha-researcher.md | - | high | 1 |
| 05 | 做市引擎 | Jane Street | roles/05-js-market-maker.md | 01 | normal | 3 |
| 06 | 因子模型 | AQR | roles/06-aqr-factor-builder.md | 02 | normal | 2 |
| 07 | 统计套利 | D.E. Shaw | roles/07-deshaw-stat-arb.md | 01 | normal | 2 |
| 08 | 宏观策略 | Bridgewater | roles/08-bridgewater-macro.md | 01 | normal | 3 |
| 09 | 数据管道 | Bloomberg | roles/09-bbg-data-pipeline.md | - | normal | 2 |
| 10 | 执行算法 | Virtu | roles/10-virtu-execution.md | 01 | normal | 1 |
| 11 | ML 研究员 | Point72 | roles/11-point72-ml-researcher.md | 01 | high | 3 |
| 12 | 组合优化 | Man Group | roles/12-man-portfolio-optimizer.md | 01,02,03,06 | normal | 2 |
| 13 | 交易系统 | Millennium | roles/13-millennium-trading-system.md | 10,12 | normal | 2 |
| 14 | 因子回测 | Dimensional | roles/14-dimensional-factor-backtest.md | 01 | normal | 3 |
| 15 | 合规框架 | Goldman Sachs | roles/15-gs-compliance.md | 13 | normal | 3 |

## 使用方式

### 触发 Skill

**自然语言**（推荐）：直接描述量化需求，Skill 自动激活。例如：
- "帮我设计一个费率套利策略"
- "做一下这个策略的回测"
- "优化入场信号"
- "启动量化流水线"

**显式加载**：`/quant-research-lab`

### 操作指令（Skill 加载后使用自然语言）

| 你说 | 行为 |
|:---|:---|
| "启动流水线" / "pipeline" / "跑全流程" | 展示轨道选择菜单，用户选择后启动对应 Pipeline |
| "因子流水线" / "因子挖掘" / "执行流水线" / "宏观流水线" / "套利流水线" / "ML流水线" / "做市流水线" | 直接启动指定轨道 Pipeline |
| "全量流水线" / "完整流水线" | 启动全部 15 角色完整流程 |
| "从角色 03 恢复" / "继续流水线" | 从角色 NN 断点恢复（需 state 文件存在） |
| "从角色 02 重新执行" / "重跑风控" | 丢弃 NN 及之后输出，从 NN 重新开始 |
| "用高盛角色" / "做回测" / "风控分析" / "alpha 研究" / "执行算法" | 单独触发某个角色（Toolbox 模式） |
| "结合上次结果做回测" | 单独触发 + 注入最近完成角色的上下文 |
| "流水线进度" / "status" | 查看进度 |
| "重置流水线" / "reset" | 清空状态重新开始 |

## 编排逻辑

### Step 0: 收集上下文

当 Skill 被激活时（通过自然语言触发或 `/quant-research-lab` 显式加载）：

1. **读取角色注册表**获取可用角色列表（从本文档 `## 角色注册表` 表格中解析 ID、角色名、文件名、depends_on、complexity、Phase）
2. **检查 `state/research-context.md` 是否存在**：
   - **不存在** → 新建，写入初始模板（含 YAML frontmatter 和空角色输出区）
   - **存在且 `status: in-progress`** → 提示用户可从断点恢复：`检测到未完成的 Pipeline（{pipeline_id}），已完成角色：{completed_roles}。说"从角色 {next_recovery} 恢复"即可继续。`
3. **如果是新 Pipeline，向用户确认 3 个必填项**：
   - 交易市场/标的（`{user_market}`）
   - 可用资金规模（`{user_capital}`）
   - 当前最想解决的问题（`{user_focus}`）
   将答案填入 state 文件的 `## 项目上下文` 区

### Toolbox 模式：触发单个角色

触发方式：用户说"用高盛角色"、"做回测"、"风控分析"、"alpha 研究"、"执行算法"等，或按角色名/关键词匹配

1. **匹配角色**：在注册表中按角色名称（如"回测"）或文件名（如"

README.md

<p align="center">
  <a href="README.md">English</a> |
  <a href="README_CN.md">中文</a> |
  <a href="README_JA.md">日本語</a> |
  <a href="README_FR.md">Français</a> |
  <a href="README_RU.md">Русский</a>
</p>

<p align="center">
  <h1 align="center">Quant Research Lab</h1>
  <p align="center">
    <strong>Multi-Agent Quantitative Strategy R&D Framework</strong>
  </p>
  <p align="center">
    15 Specialized LLM Agents Modeled After Top Quant Firms
  </p>
</p>

<p align="center">
  <a href="https://github.com/anthropics/claude-code" target="_blank"><img alt="Claude Code" src="https://img.shields.io/badge/Claude_Code-Compatible-D97706?logo=anthropic&logoColor=white"/></a>
  <a href="https://hermes.nousresearch.com" target="_blank"><img alt="Hermes Agent" src="https://img.shields.io/badge/Hermes_Agent-Skill-7C3AED?logo=data:image/svg+xml;base64,..." /></a>
  <img alt="Roles" src="https://img.shields.io/badge/Roles-15-blue" />
  <img alt="Pipeline Tracks" src="https://img.shields.io/badge/Pipeline_Tracks-8-green" />
  <a href="LICENSE"><img alt="License: MIT" src="https://img.shields.io/badge/License-MIT-yellow.svg" /></a>
</p>

---

> **Quant Research Lab** is an AI-agent skill that brings institutional-grade quantitative strategy research workflow to LLM-powered coding agents. It deploys 15 specialized agents — each modeled after the expertise of a top quant firm (Goldman Sachs, Renaissance Technologies, Two Sigma, Citadel, Jane Street, and more) — to collaboratively design, backtest, risk-manage, and validate quantitative trading strategies.

> ⚠️ **Disclaimer**: This framework is designed for **research and educational purposes** only. It does not constitute financial, investment, or trading advice. Trading performance depends on many factors including model choice, data quality, and market conditions. Always perform your own due diligence.

---

## Table of Contents

- [Framework Overview](#framework-overview)
- [The 15 Roles](#the-15-roles)
- [Pipeline Architecture](#pipeline-architecture)
- [Installation](#installation)
- [Usage](#usage)
- [Quality Gates](#quality-gates)
- [State Management](#state-management)
- [Project Structure](#project-structure)
- [Contributing](#contributing)
- [License](#license)

---

## Framework Overview

Quant Research Lab mirrors how real-world quantitative trading firms operate: complex strategy research is decomposed into specialized roles, each bringing domain expertise from a different institutional perspective. The framework orchestrates these roles through two modes:

- **Toolbox Mode** — Invoke any individual role on demand for targeted analysis
- **Pipeline Mode** — Run pre-configured tracks (sequences of roles) for end-to-end strategy research

```
┌─────────────────────────────────────────────────────────────┐
│                    Quant Research Lab                        │
│                                                             │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌──────────┐   │
│  │ Stra

_meta.json

{
  "ownerId": "kn7dm72g6k962wq83k12vqb9yn80126f",
  "slug": "quant-research-lab",
  "version": "1.0.1",
  "publishedAt": 1777988905601
}

README_CN.md

<p align="center">
  <a href="README.md">English</a> |
  <a href="README_CN.md">中文</a> |
  <a href="README_JA.md">日本語</a> |
  <a href="README_FR.md">Français</a> |
  <a href="README_RU.md">Русский</a>
</p>

<p align="center">
  <h1 align="center">量化策略研发实验室</h1>
  <p align="center">
    <strong>多智能体量化策略研发框架</strong>
  </p>
  <p align="center">
    15 个专业化 LLM 智能体，对标顶级量化机构
  </p>
</p>

<p align="center">
  <a href="https://github.com/anthropics/claude-code" target="_blank"><img alt="Claude Code" src="https://img.shields.io/badge/Claude_Code-Compatible-D97706?logo=anthropic&logoColor=white"/></a>
  <a href="https://hermes.nousresearch.com" target="_blank"><img alt="Hermes Agent" src="https://img.shields.io/badge/Hermes_Agent-Skill-7C3AED?logo=data:image/svg+xml;base64,..." /></a>
  <img alt="Roles" src="https://img.shields.io/badge/Roles-15-blue" />
  <img alt="Pipeline Tracks" src="https://img.shields.io/badge/Pipeline_Tracks-8-green" />
  <a href="LICENSE"><img alt="License: MIT" src="https://img.shields.io/badge/License-MIT-yellow.svg" /></a>
</p>

---

> **量化策略研发实验室** 是一项 AI 智能体技能，将机构级量化策略研究工作流带给由 LLM 驱动的编程智能体。它部署了 15 个专业化智能体——每个都对标顶级量化机构（Goldman Sachs、Renaissance Technologies、Two Sigma、Citadel、Jane Street 等）的专业能力——协同完成量化交易策略的设计、回测、风控管理与验证。

> ⚠️ **免责声明**：本框架仅用于**研究和教育目的**，不构成金融、投资或交易建议。交易表现取决于多种因素，包括模型选择、数据质量和市场条件。请务必自行进行尽职调查。

---

## 目录

- [框架概述](#框架概述)
- [15 个角色](#15-个角色)
- [流水线架构](#流水线架构)
- [安装](#安装)
- [使用方法](#使用方法)
- [质量门控](#质量门控)
- [状态管理](#状态管理)
- [项目结构](#项目结构)
- [贡献指南](#贡献指南)
- [许可证](#许可证)

---

## 框架概述

量化策略研发实验室镜像了现实世界量化交易公司的运作方式：复杂的策略研究被分解为专业化角色，每个角色从不同机构视角带来领域专长。本框架通过两种模式编排这些角色：

- **工具箱模式** — 按需调用任意单个角色进行针对性分析
- **流水线模式** — 运行预配置的轨迹（角色序列）进行端到端策略研究

```
┌─────────────────────────────────────────────────────────────┐
│                    Quant Research Lab                        │
│                                                             │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌──────────┐   │
│  │ Strategy  │→ │ Backtest │→ │   Risk   │→ │  Alpha   │   │
│  │ Architect │  │  Engine  │  │ Manager  │  │Researcher│   │
│  │ (GS)      │  │ (RenTech)│  │ (Two σ)  │  │ (Citadel)│   │
│  └──────────┘  └──────────┘  └──────────┘  └──────────┘   │
│       │              │             │              │         │
│       ▼              ▼             ▼              ▼         │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌──────────┐   │
│  │Execution │  │  Factor  │  │ Stat Arb │  │  Macro   │   │
│  │ Algo     │  │  Model   │  │(D.E.Shaw)│  │(Bridge-  │   │
│  │ (Virtu)  │  │  (AQR)   │  │          │  │ water)   │   │
│  └──────────┘  └──────────┘  └──────────┘  └──────────┘   │
│       │              │             │              │         │
│       ▼              ▼             ▼              ▼         │
│  ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌──────────┐   │
│  │Data Pipe │  │    ML    │  │Portfolio │  │ Trading  │   │
│  │ (Bloomberg)│ │Researcher│  │Optimizer │  │ System   │   │
│  │          │  │(Point72) │  │(Man Grp) │  │

README_FR.md

<p align="center">
  <a href="README.md">English</a> |
  <a href="README_CN.md">中文</a> |
  <a href="README_JA.md">日本語</a> |
  <a href="README_FR.md">Français</a> |
  <a href="README_RU.md">Русский</a>
</p>

<p align="center">
  <h1 align="center">Quant Research Lab</h1>
  <p align="center">
    <strong>Laboratoire de Recherche Quantitative</strong>
  </p>
  <p align="center">
    Cadre R&D de Stratégies Quantitatives Multi-Agents
  </p>
  <p align="center">
    15 Agents LLM Spécialisés, Modélisés d'après les Plus Grandes Firms Quant
  </p>
</p>

<p align="center">
  <a href="https://github.com/anthropics/claude-code" target="_blank"><img alt="Claude Code" src="https://img.shields.io/badge/Claude_Code-Compatible-D97706?logo=anthropic&logoColor=white"/></a>
  <a href="https://hermes.nousresearch.com" target="_blank"><img alt="Hermes Agent" src="https://img.shields.io/badge/Hermes_Agent-Skill-7C3AED?logo=data:image/svg+xml;base64,..." /></a>
  <img alt="Roles" src="https://img.shields.io/badge/Roles-15-blue" />
  <img alt="Pipeline Tracks" src="https://img.shields.io/badge/Pipeline_Tracks-8-green" />
  <a href="LICENSE"><img alt="License: MIT" src="https://img.shields.io/badge/License-MIT-yellow.svg" /></a>
</p>

---

> **Quant Research Lab** est une compétence d'agents IA qui apporte un flux de travail de recherche en stratégies quantitatives de niveau institutionnel aux agents de programmation alimentés par LLM. Il déploie 15 agents spécialisés — chacun modélisé selon l'expertise d'une grande firme quantitative (Goldman Sachs, Renaissance Technologies, Two Sigma, Citadel, Jane Street, et d'autres) — pour concevoir, backtester, gérer les risques et valider de manière collaborative des stratégies de trading quantitatives.

> ⚠️ **Avertissement** : Ce cadre est conçu uniquement à des fins de **recherche et d'éducation**. Il ne constitue pas un conseil financier, d'investissement ou de trading. Les performances de trading dépendent de nombreux facteurs, notamment le choix du modèle, la qualité des données et les conditions de marché. Effectuez toujours votre propre diligence raisonnable.

---

## Table des matières

- [Vue d'ensemble du cadre](#vue-densemble-du-cadre)
- [Les 15 rôles](#les-15-rôles)
- [Architecture du pipeline](#architecture-du-pipeline)
- [Installation](#installation)
- [Utilisation](#utilisation)
- [Portes de qualité](#portes-de-qualité)
- [Gestion de l'état](#gestion-de-letat)
- [Structure du projet](#structure-du-projet)
- [Contribuer](#contribuer)
- [Licence](#licence)

---

## Vue d'ensemble du cadre

Quant Research Lab reproduit le fonctionnement des véritables firmes de trading quantitatif : la recherche de stratégies complexes est décomposée en rôles spécialisés, chacun apportant une expertise métier depuis une perspective institutionnelle différente. Le cadre orchestre ces rôles à travers deux modes :

- **Mode Boîte à outils** — Invoquez n'importe quel rôle individuellement pour une analyse ciblée
- **Mode Pipeline** — Exé

Related agents

Same protocol, similar job.

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/yili1992/skills/quant-research-lab",
      "sourceUrl": "https://clawhub.ai/yili1992/skills/quant-research-lab",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-10T20:30:05.838Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-yili1992-quant-research-lab/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-yili1992-quant-research-lab/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-10T20:30:05.838Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "1.3K downloads",
      "href": "https://clawhub.ai/yili1992/quant-research-lab",
      "sourceUrl": "https://clawhub.ai/yili1992/quant-research-lab",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-10T20:30:05.838Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "1.0.1",
      "href": "https://clawhub.ai/yili1992/quant-research-lab",
      "sourceUrl": "https://clawhub.ai/yili1992/quant-research-lab",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-05-05T13:48:25.601Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-yili1992-quant-research-lab/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-yili1992-quant-research-lab/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 1.0.1",
      "description": "quant-research-lab 1.0.1 - Added .gitignore file to define files and directories to be ignored by Git. - Added LICENSE file to specify the project's licensing terms. - No other changes to source code or features in this version.",
      "href": "https://clawhub.ai/yili1992/quant-research-lab",
      "sourceUrl": "https://clawhub.ai/yili1992/quant-research-lab",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-05-05T13:48:25.601Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 10, 2026.

Sponsored

Ads related to 量化策略研发实验室 and adjacent AI workflows.