股海罗盘 - A股股票量化分析
Quantitative analysis for A-shares, with historical match rate for each signal.
Install & Use
Copy this prompt and send it to your AI assistant (Claude / Cursor / TRAE / Codex / WorkBuddy etc.) to auto-install:
Help me install this AI Skill: 股海罗盘 - A股股票量化分析. It is used for: Quantitative analysis for A-shares, with historical match rate for each signal. Full Skill content: https://321skill.com/skills/a-share-quant-signals/raw/index.md Read that page and install it.
The prompt includes a link to the full Skill content. You can also view the full content.
Stock Compass addresses the core pain point for A-share investors: How reliable are indicator signals? Traditional stock trading tools only provide a signal without revealing its historical success rate. Stock Compass employs a self-learning quantitative engine to backtest over 600,000 historical signals for each stock, outputting the historical match rate and a progress bar for each signal. This lets you see at a glance how many times out of the past 100 occurrences the signal was correct. It also provides 17 dimensions of comprehensive data (market quotes, capital flows, technicals, fundamentals, holdings, share unlock events, research reports, etc.), eliminating the need to switch between pages.
Usage is straightforward: Simply input a stock code or name. The AI will automatically fetch the stock's full dataset, analyze the current signal, generate the historical match rate and five types of pattern charts (support/resistance, probability of pullback after a sharp rise, probability of rebound after a sharp decline, etc.), and supports one-click export to a DOCX report (including candlestick charts). The exclusive ETF Four-Quadrant Linkage Analysis helps identify sector resonance versus independent market moves, while cross-verification of brokerage research report opinions reveals whether there is a true market consensus.
Target Users: Retail A-share investors, quantitative trading enthusiasts, traders needing to quickly verify signal reliability, and finance professionals who need to regularly produce analysis reports for clients or teams. Also suitable for university students for financial data analysis and thesis research.
Usage Recommendations: For stocks listed for less than one year (recent IPOs), the historical backtest sample is smaller, limiting the reference value of the match rate. It is recommended to prioritize use for stocks with a longer trading history (e.g., listed for over 3 years). Also, historical match rates do not guarantee future repetition; they should be combined with the latest market environment for comprehensive judgment.
Key Features
Every signal comes with its historical match rate and a progress bar, making it immediately clear how many times it was correct out of the past 100 occurrences—instead of just providing an indicator without an answer. Additionally, the exclusive ETF Four-Quadrant Linkage Analysis and multi-source capital flow cross-verification can identify sector resonance versus independent market moves.
Limitations
Not suitable for stocks listed for less than one year (recent IPOs), stocks under prolonged suspension, or extreme market conditions like continuous limit-up/lock-limit boards. The match rate has limited reference value when the historical backtest sample is insufficient.
FAQ
Is this skill paid?
Currently, this skill is an open-source and free project. Specific usage may be limited by the dependent market data sources (e.g., you may need to apply for your own API key).
Which stocks are supported?
Supports all listed A-shares (including Main Board, ChiNext, and STAR Market). However, for recent IPOs, historical data is limited, reducing the reference value of the match rate.
Installation guide for AI assistants
If your AI coding assistant (Claude Code, Cursor, TRAE etc.) can see this page, send it this message to auto-install:
Visit https://321skill.com/skills/a-share-quant-signals/raw/index.md to read the original Skill definition (Markdown format) for 股海罗盘 - A股股票量化分析, and install it according to the instructions.
Raw Markdown URL for AI: /skills/a-share-quant-signals/raw/index.md