股海罗盘 - A股股票量化分析
Quantitative analysis of A-share individual stocks, featuring signal backtesting, pattern discovery, and report generation.
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 of A-share individual stocks, featuring signal backtesting, pattern discovery, and report generation. Full Skill content: https://321skill.com/skills/a-share-quant-analysis-16/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 points for A-share investors: ambiguous indicator signals, scattered data, and information asymmetry. Through a self-learning quantitative engine, it backtests over 600,000 historical signals for each stock, outputs the historical match rate for each signal (how many times it was correct out of the past 100 occurrences), and presents it visually with a progress bar, providing an evidence-based foundation for judgment.
Usage is extremely simple: input a stock code to instantly obtain 17 dimensions of comprehensive data (market quotes, capital flows, technical indicators, financials, holdings, lock-up expiries, research reports). It automatically uncovers five types of pattern charts (support/resistance levels, probability of pullback after a sharp rise, probability of rebound after a sharp decline, etc.) and generates a DOCX report with candlestick charts, which can be directly saved, shared, or sent to clients. Exclusive ETF Four-Quadrant Linkage Analysis + multi-source capital flow cross-validation helps identify sector resonance and independent market movements. Full-market brokerage research report coverage statistics + EPS consensus divergence verify whether research reports reflect true consensus.
Suitable for quantitative traders, individual investors, analysts, and finance students, it aids in investment decision-making, strategy validation, and research report analysis. It is recommended to treat historical match rates as a reference rather than an absolute basis, combining them with fundamental analysis and market sentiment for comprehensive judgment, especially noting that black swan events may invalidate historical patterns.
Key Features
Each signal includes a historical match rate + progress bar, making it clear at a glance how many times it was correct out of the past 100 occurrences. Exclusive ETF Four-Quadrant Linkage + brokerage research report cross-validation filters out noise from the perspectives of multi-source capital flows and report consensus. One-click DOCX report generation eliminates the need for manual screenshots.
Limitations
Not applicable to other markets such as Hong Kong stocks or US stocks. Relies on historical data and cannot predict black swan events or extreme market conditions.
FAQ
How is the signal match rate calculated?
Based on backtesting over 600,000 historical signals for the stock, it calculates the proportion of times the subsequent price movement aligned with the signal's expectation. This is displayed with a progress bar. For example, a 75% match rate indicates the signal was correct 75 times out of the past 100 similar occurrences.
Can the generated DOCX report be used directly for investment decisions?
The report provides quantitative analysis for reference, but investment decisions should integrate multiple dimensions such as fundamentals, market sentiment, and policy. Historical match rates do not guarantee future performance. It is recommended as an auxiliary tool and should not be relied upon solely.
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-analysis-16/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-analysis-16/raw/index.md