stock-market-hotspot-discovery

Stock Market Hotspot Discovery

Throughnatural language questionsidentify current market hotspots and return a Markdown hotspot report. Applicable scenarios include:

• Overview of today's market hotspots (news/events/topics)
• Identification of hot stocks and active directions
• Quickly capture sentiment changes and focal points during the trading day

Functional Scope

Basic Hotspot Capabilities

• Input a natural language question and call the hotspot discovery interface to generate structured conclusions
• Covers market-level hotspot information such as hot news and hot stocks
• Returns a readable Markdown report (preferentially extract data.displayData）
• Supports saving the results as a local .md file for after-hours review

Trigger Rules (When to Use This Skill)

• The user's question ismarket-level hotspot discovery: such as "What are today's hotspots?" or "What are the hot stocks?"
• The user has not specified a single stock/fund for in-depth diagnosis, nor requested specific indicator calculations
• The user is focused on generalized topics such as "hot, trending, major events, active sectors, directions of interest"

Non-Trigger Rules (When Not to Use This Skill)

• The user explicitly asks for in-depth analysis of a single stock (should use stock-diagnosis)
• The user explicitly asks for in-depth analysis of a single fund (should use fund-diagnosis)
• The user requests specific indicator calculations or quantitative modeling (MACD, backtesting, portfolio optimization, etc.)

Trigger Examples

Trigger (hotspot discovery)	Do not trigger (diagnosis/indicators)
What are today's hotspots?	How is Hikvision doing?
What are the hottest stocks today?	Has Danhua Technology's MACD formed a golden cross?
Which investment sectors are popular recently?	Help me build a fund portfolio optimization model

Quick Start

1. Command-Line Invocation

python3 {baseDir}/scripts/get_data.py --query "今日热点"

Output Example

Saved: /path/to/workspace/stock_market_hotspot_discovery/stock_market_hotspot_discovery_90bf169c.md
（随后输出 Markdown 热点内容）

Parameter Description:

Parameter	Description	Required
--query	The user's original natural language question	✅（--query or stdin, choose one)
--no-save	Only output the result, do not write to a local file	No

2. Code Invocation

import asyncio
from pathlib import Path
from scripts.get_data import discover_hotspot

async def main():
    result = await discover_hotspot(
        question="今日热点",
        output_dir=Path("workspace/stock_market_hotspot_discovery"),
        save_to_file=True,
    )
    if "error" in result:
        print(result["error"])
    else:
        print(result["content"])
        if result.get("output_path"):
            print("已保存至:", result["output_path"])

asyncio.run(main())

Output Specification

After obtaining the stock diagnosis result through a script or tool,the visible reply to the user must be based primarily on the Markdown body returned by the interface, avoiding secondary paraphrasing by the model. Only when the interface/script explicitly returns error, or the body is empty, use a brief text explanation of the failure reason;forbiddento fabricate report content when it fails.

Frequently Asked Questions

Why is the md file sometimes not saved?
→ When the return is an unsupported scenario or a failure structure (such as code/status exception,data being empty), the script will only output the content without writing to disk.

How can I view only the output without writing it to disk?

python3 -m scripts.get_data --query "今日热点" --no-save

Compliance Statement

• Hotspot information is time-sensitive, and the results reflect the market state at the moment the API is called.
• Hotspot information is for reference only and does not constitute investment advice; a risk disclaimer should be included with the output.
• It is prohibited to hard-code account IDs, session IDs, or tokens in code or prompts.
• When the API fails, do not fabricate conclusions; return a clear error or a statement of uncertainty.