龙虾A股研究员

Convert natural-language A-share research queries into structured data retrieval and conclusions.

2|Updated Apr 6, 2026
One-click install
npx skills add https://github.com/augustscl/awesome-xiawang-skills --skill a-augustscl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: 龙虾A股研究员
Source: https://github.com/augustscl/awesome-xiawang-skills/tree/main/lobster-a-share-researcher
Command: npx skills add https://github.com/augustscl/awesome-xiawang-skills --skill a-augustscl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires akshare, pandas, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Converts casual or ambiguous A股 research questions into structured data queries and readable research outputs so users get concise conclusions, key metrics, and risk reminders instead of raw API dumps.

Core Features & Use Cases

  • Individual stock quick check: one-sentence conclusion plus latest price, change, and volume for a ticker or name.
  • Historical K-line analysis: summarize recent trends, key highs/lows, and percentage change over a chosen period.
  • Financial comparison: compare 3–5 core financial indicators between two stocks with clear data sources and caveats.
  • Sector and concept observation: identify strongest/weakest sectors and representative names.
  • Fund flow and screening: present net inflow/outflow, differentiate large orders if available, and return small screening results with selection logic and limits.

Quick Start

Ask the skill to "Check the 30-day trend and key financial metrics for 600519 and provide a concise conclusion, key data, and a risk notice."

Frequently Asked Questions about 龙虾A股研究员

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

FAQPage Schema
How do I get A-share stock research conclusions from natural language queries instead of raw data dumps?

The Skill converts natural language A-share queries into structured data retrieval, returning concise conclusions, key metrics, and explicit risk warnings instead of raw API dumps.

Can I compare financial indicators between two A-share stocks using AkShare data?

Yes, financial comparison compares three to five core financial indicators between two A-share stocks, returning structured results with clear data sources and caveats.

What's the best way to analyze historical K-line trends for A-share market data?

Historical K-line analysis summarizes recent trends, key highs and lows, and percentage changes over a selected period, returning readable interpretive conclusions instead of raw price arrays.

Does AkShare support tracking A-share fund flow and differentiating large orders?

Yes, fund flow tracking presents net inflow or outflow for A-share stocks and differentiates large orders if available, returning the data with summarized conclusions.

How do I screen A-share stocks and identify the strongest industry or concept boards?

Sector and concept observation identifies the strongest and weakest industry boards with representative names, while stock screening returns small result sets with explicit selection logic and limits.

What are the limitations of using pandas and AkShare for A-share stock research?

Limitations include dependence on AkShare data availability for fund flow and large order differentiation, and the tool is designed for basic screening and observation rather than high-frequency trading execution.