A Stock Daily Market Sense
A-share After-Market Research Report Auto-Generation Tool
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: A Stock Daily Market Sense. It is used for: A-share After-Market Research Report Auto-Generation Tool Full Skill content: https://321skill.com/skills/a-stock-daily-market-sense-x-6/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.
This Skill addresses the time-consuming and labor-intensive nature of daily A-share market review for investors, which often leads to missed key signals. Manually compiling data on indices, turnover, market styles, and leading sectors is highly time-consuming and prone to subjective bias. Based on Tushare Pro daily data and Baostock style indices, this Skill automatically generates structured after-market research reports covering core dimensions such as market trend, turnover concentration, profitability effect, rising leading sectors, and high-volume decline risks.
Usage is straightforward: simply specify a trading date (e.g., "today" or a specific date). The Skill first runs a script to generate a deterministic evidence package, then uses a model to perform module-based analysis and writing. It supports feature-group analysis (e.g., discount start, monthly line platform breakout, limit-up before 10:30 AM) as well as quantitative backtesting and relative return factor mining. The final output is a Markdown research report, with the option to generate an HTML visual report featuring K-line charts and lifecycle swimlanes with one click.
It is particularly suitable for quantitative traders, individual investors, securities analysts, and financial media editors who need to review the A-share market daily. This is especially true for teams or individuals already using Tushare data who wish to automate their after-market analysis process and reduce subjective bias. For users who need to quickly grasp market sentiment, sector rotation, and risk signals, this Skill can significantly improve efficiency.
It is recommended to run the Skill after the market closes each day to ensure data completeness. Please note: This Skill does not provide buy/sell recommendations and does not use an LLM to generate raw data. All strength/weakness judgments are based on turnover evidence. External materials are used only to explain catalysts and cannot be used to retroactively adjust or upgrade leading sector ratings. Before use, a Tushare Pro token must be applied for, and a Python 3.8+ environment with the required dependency libraries must be installed.
Key Features
Unlike auto-reporting platforms such as JoinQuant and RiceQuant, this Skill emphasizes evidence-driven analysis with a priority on turnover data. It does not apply pre-packaged industry/concept labels. Leading sector ratings are locked based on statistical results, and external materials cannot be used to retroactively adjust these ratings, ensuring objectivity. Additionally, it supports quantitative backtesting with feature grouping and relative return factor mining, whereas similar tools typically only perform same-day review.
Limitations
Relies on Tushare Pro and Baostock data sources. Requires a Python 3.8+ environment and users must apply for their own Tushare token. Does not support analysis of Hong Kong stocks, US stocks, futures, or crypto assets. Does not provide ultra-short-term trading decisions or automated order placement functionality.
FAQ
How do I install this Skill? What dependencies are required?
Install via the ClawHub platform (`clawhub install a-stock-daily-market-sense`), or manually clone the repository and run `pip install tushare baostock pandas numpy`. A Tushare Pro token must be applied for in advance and configured as an environment variable.
What is the data update frequency? Does it support historical backtesting?
Data is based on Tushare daily feeds. Running the Skill after the market closes each day provides the latest data. It supports reviewing specified historical trading dates and quantitative backtesting with feature grouping (e.g., discount start, monthly line breakout) via the `factor_backtest.py` script.
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-stock-daily-market-sense-x-6/raw/index.md to read the original Skill definition (Markdown format) for A Stock Daily Market Sense, and install it according to the instructions.
Raw Markdown URL for AI: /skills/a-stock-daily-market-sense-x-6/raw/index.md