trading-agents

Name: trading-agents
Availability: InStock
Author: Arry8

Coordinate multi-agent LLMs to analyze tickers using fundamentals, sentiment, technicals, and news.

1|Updated Mar 30, 2026

Search Tags:#llm #multi-agent #risk-management #backtesting #trading #stock-analysis

Ready to run

npx skills add https://github.com/Arry8/openclaw-edge --skill trading-agents

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: trading-agents
Source: https://github.com/Arry8/openclaw-edge/tree/main/skills/trading-agents
Command: npx skills add https://github.com/Arry8/openclaw-edge --skill trading-agents

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

TradingAgents coordinates multi-agent LLMs to analyze financial tickers by combining fundamental, sentiment, technical, and news signals, delivering a comprehensive trading assessment and actionable insights.

Core Features & Use Cases

Multi-agent analyst team: fundamentals, sentiment, technicals, and news analysts work together to produce in-depth evaluations.
Researcher debate: bull vs bear researchers provide balanced perspectives and risk-aware conclusions.
CLI-first workflow: interactive command-line interface with optional Python package usage for scripting.
Backtesting & risk evaluation: test strategies over date ranges with configurable parameters and risk checks.
Data-vendor flexibility: supports multiple data sources, defaulting to yfinance for stock data.

Quick Start

Launch the interactive CLI with tradingagents and begin analyzing a ticker over a chosen date range.

Frequently Asked Questions about trading-agents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I use multi-agent LLMs to analyze stocks by combining fundamentals, sentiment, and technicals?▼

Multi-agent LLM stock analysis coordinates separate fundamentals, sentiment, technicals, and news analysts to produce a comprehensive trading assessment. Bull and bear researchers then debate to deliver balanced, risk-aware conclusions for your chosen ticker.

Can I backtest trading strategies over specific date ranges using LLM agents?▼

Backtesting trading strategies with LLM agents evaluates your strategy over configurable date ranges with risk checks. The multi-agent setup analyzes historical data to test parameters and generate risk-aware performance insights.

Do I need to install any CLI tools or configure LLM providers before analyzing tickers?▼

You need the tradingagents CLI installed via uv tool install and configuration set for your LLM providers. Once configured, launch the interactive command-line interface to begin analyzing tickers over your chosen date ranges.

Does this multi-agent trading analysis work with yfinance and other data vendors?▼

The multi-agent trading analysis supports multiple data vendors, defaulting to yfinance for stock data. This data-vendor flexibility allows the agent team to pull fundamental, technical, and news signals from your preferred financial data sources.

Can I script trading agent workflows in Python instead of using the interactive CLI?▼

Optional Python package usage allows you to script trading agent workflows directly. While the CLI provides an interactive first workflow, the Python integration lets you automate ticker analysis, backtesting, and strategy evaluation within your own scripts.

What is the best way to get balanced risk-aware trading insights for a ticker?▼

Balanced risk-aware trading insights are generated through a researcher debate mechanism. Bull and bear researchers evaluate the multi-agent findings to provide opposing perspectives, ensuring your final trading assessment weighs both upside potential and downside risks.