event-driven

Name: event-driven
Availability: InStock
Author: hxhyyy

Generate sentiment-based trading signals from financial news and macro events.

Updated Jul 8, 2026

Search Tags:#llm #finance #signals #backtesting #trading #sentiment

Ready to run

npx skills add https://github.com/hxhyyy/Vibe-Trading --skill event-driven-hxhyyy

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: event-driven
Source: https://github.com/hxhyyy/Vibe-Trading/tree/main/agent/src/skills/event-driven
Command: npx skills add https://github.com/hxhyyy/Vibe-Trading --skill event-driven-hxhyyy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy.

What problem does it solve?

This Skill addresses the challenge of quantifying qualitative market information, such as news and macro events, into actionable trading signals while avoiding look-ahead bias.

Core Features & Use Cases

Sentiment Scoring: Uses an LLM to convert news and announcements into standardized sentiment scores ranging from -1.0 to 1.0.
Signal Aggregation: Combines event-driven signals with technical indicators using time-decay logic to ensure market relevance.
Use Case: A trader can process a stream of earnings reports and central bank announcements to adjust their portfolio exposure based on the calculated impact magnitude of these events.

Quick Start

Use the event-driven skill to analyze the sentiment of the latest market news and generate a trading signal based on the provided event CSV.

Frequently Asked Questions about event-driven

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

FAQPage Schema

How do I generate trading signals from financial news using sentiment analysis?▼

To generate trading signals from financial news, this Skill uses an LLM to convert news and announcements into standardized sentiment scores ranging from -1.0 to 1.0. It then aggregates these event-driven signals with time-decay logic to ensure market relevance.

How does event-driven backtesting avoid look-ahead bias when processing macro events?▼

Event-driven backtesting avoids look-ahead bias by processing event data into standardized CSV formats and applying time-series alignment. This ensures that sentiment-based trading signals are calculated strictly using chronologically accurate information.

Can I use pandas and numpy to align time-series data for live trading workflows?▼

Yes, you can use pandas and numpy to align time-series data for live trading workflows. This Skill requires these dependencies to calculate time-decay aggregation and align event-driven signals accurately for both live and backtesting environments.

What is the best way to quantify qualitative market information for trading?▼

The best way to quantify qualitative market information is using LLM-driven scoring to convert news and announcements into numerical sentiment scores. This approach transforms textual macro events into actionable, time-decayed trading signals.

Do I need a specific CSV format to process earnings reports for sentiment scoring?▼

Yes, you need to provide a standardized event CSV format to process earnings reports and central bank announcements. The Skill processes this structured event data to generate LLM-driven sentiment scores for your portfolio exposure adjustments.

Why does signal aggregation use time-decay logic for event-driven trading?▼

Signal aggregation uses time-decay logic to ensure ongoing market relevance when combining event-driven signals with technical indicators. This prevents older financial news from disproportionately influencing current trading decisions and portfolio exposure.