vibe-trading

Convert trade journals into if-then shadow rules and backtest them across markets.

Updated May 5, 2026
One-click install
npx skills add https://github.com/wudye/traderAssistHK --skill vibe-trading-wudye
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: vibe-trading
Source: https://github.com/wudye/traderAssistHK/tree/main/backend
Command: npx skills add https://github.com/wudye/traderAssistHK --skill vibe-trading-wudye

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires vibe-trading-ai, weasyprint.

What problem does it solve?

Vibe-Trading converts your trading journal into a structured “shadow strategy” and then objectively backtests it across multiple markets, so you can find which parts of your behavior actually produce edge instead of relying on memory or anecdotes.

Core Features & Use Cases

  • Shadow Account loop: extract 3–5 human-readable if-then rules from profitable roundtrips, backtest them, and compute delta-PnL with attribution (what you did right vs what you missed).
  • Multi-market backtesting & benchmarking: run strategy research across A-shares, HK/US equities, crypto, futures, forex, and options using multiple backtest engines and a benchmark comparison panel.
  • Multi-agent swarm research teams: coordinate pre-built research desks for deeper analysis when an LLM key is available.
  • Finance skill knowledge base: access a large set of specialized finance skills (technical patterns, factor analysis, risk methods, options pricing, and more) for research workflows.

Quick Start

Ask the agent to run the Shadow Account loop on your uploaded broker CSV (analyze_trade_journal → extract_shadow_strategy → run_shadow_backtest → render_shadow_report) to generate your HTML/PDF report.

Frequently Asked Questions about vibe-trading

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

FAQPage Schema
How do I backtest my trading journal entries across multiple markets?

Extracting shadow rules from a trading journal converts your trade history into 3-5 human-readable if-then conditions derived from profitable roundtrips. This mechanism transforms subjective trading instincts into testable rules for objective delta-PnL attribution.

What is the best way to convert trade journal instincts into a structured shadow strategy?

Converting trade journal instincts into a shadow strategy involves analyzing roundtrips to extract human-readable if-then rules, then running multi-market backtests to compute delta-PnL. This approach replaces anecdotal memory with objective behavior profiling.

Does multi-market backtesting support A-shares, crypto, and options pricing?

Yes, multi-market backtesting supports A-shares, HK/US equities, crypto, futures, forex, and options pricing. It uses multiple backtest engines alongside a benchmark comparison panel to evaluate extracted shadow strategies across these asset classes.

Do I need an LLM key to run multi-agent swarm research for factor analysis?

You need an LLM key to coordinate multi-agent swarm research teams for deeper factor analysis and options pricing. Without an LLM configuration, you can still run the standard shadow-account pipeline for backtesting and report generation.

How to generate an HTML or PDF report for trading strategy refinement?

Generating a report for trading strategy refinement uses the render_shadow_report component after backtesting. It outputs a formatted HTML or PDF document detailing delta-PnL attribution and behavior profiling to guide strategy adjustments.