claude-skill

vibe-investing: AI‑driven quant tools for NASDAQ, S&P 500 & crypto trading

Name: vibe-investing: AI‑driven quant tools for NASDAQ, S&P 500 & crypto trading
Author: gameworkerkim

Empowers founders to run LLM‑backed quantitative strategies, multi‑agent backtesting, and data‑rich market insights across stocks and crypto.

From the repo · “AI-powered Vibe Investing for NASDAQ, S&P500 & crypto: LLM quant trading tools, multi-agent backtesting, and data-driven market columns (mNAV arbitrage, BTC-Nasdaq coupling, Alpha Arena). 미국 주식·가상화폐 AI 투자 큐레이션·칼럼·트레이딩 봇.”

intermediate⏱ 1-2 hours💵 Free + LLM API costs

350 stars+4★ this week102 forksHTMLGuide quality 8/10 · reviewed Oct 15Updated 10/22/2026100% free · open source

What it is

Use AI-powered trading tools to automate investment decisions.

Real use case example

"A founder of a crypto trading firm wants to automate testing their portfolio allocation models. They use Vibe Investing to set up a backtesting environment for their strategies, analyze historical market data, and refine their approach. This results in a more data-driven investment strategy."

Best insideClaude DesktopClaude API

When to use it

•When you need to analyze and predict stock prices for NASDAQ and S&P500
•When you want to explore arbitrage opportunities between crypto and traditional markets
•When you need to backtest and optimize your trading strategies using multi-agent systems

Ready-to-paste prompt

Run `python trading/mNAV_arbitrage.py --market nasdaq --crypto btc` to analyze arbitrage opportunities between NASDAQ and Bitcoin

Heads up: Make sure you have the required Python libraries installed, including `pandas`, `numpy`, and `matplotlib`, and that you have a valid API key for the market data providers used by the tool

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/vibe-investing && curl -fsSL https://workflowstacks.com/api/skills/vibe-investing/claude-skill -o ~/.claude/skills/vibe-investing/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

What's inside — free to inspect

No purchase needed

Read the entire source before you build — unlike paid marketplaces that hide it behind a buy button.

top-level files

folders

200.1M

source size

—

license

Key files

AGENTS.md

Awesome AI Quant Prompt github repos evaluation kr.MD

Harness quant v2 readme .MD

Readme en.MD

README.md

requirements.txt

File tree

.claude/

.github/

01.Trading Strategy/

02.Investment Idea Column/

03. Media-Column/

AfterMarketClose/

AIInvestor/

CASSANDRA AI/

Claude_Fable5_Prompt/

Harness quantv2/

kiwoom_sdk/

LAON_VaultGuard/

Leaf_OpenEBook/

mNAV(Market-to-Net-Asset-Value) arbitrage/

monarchjuno/

MyETF Project/

Paper 논문/

QQQUpDownSignal/

TechDoc/

TokenForge/

Toss/

toss-dashboard/

TradingLog/

VibeQuant/

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/vibe-investing && curl -fsSL https://workflowstacks.com/api/skills/vibe-investing/claude-skill -o ~/.claude/skills/vibe-investing/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

gameworkerkim

Language

HTML