中国A股分析工具 logo

中国A股分析工具

Organization
agentbay-ai
中国A股分析工具

A股价值投资分析工具,提供股票筛选、个股深度分析、行业对比和估值计算功能。基于价值投资理论,使用akshare获取公开财务数据,适合低频交易的普通投资者。

Overview

Publisheragentbay-ai
Repositoryagentbay-skills
Skill name中国A股分析工具
Stars
50
Forks
5
Bundled files
8
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 8 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by agentbay-ai on GitHub. Read the source before you install it.

Installation

Install the 中国A股分析工具 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/agentbay-ai/agentbay-skills/tree/main/china-stock-analysis
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/agentbay-ai/agentbay-skills.git /tmp/agentbay-skills
mkdir -p .claude/skills
cp -r /tmp/agentbay-skills/china-stock-analysis .claude/skills/agentbay-ai-a
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable 中国A股分析工具 in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads 中国A股分析工具 on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so 中国A股分析工具 is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

China Stock Analysis Skill

基于价值投资理论的中国A股分析工具,面向低频交易的普通投资者。

When to Use

当用户请求以下操作时调用此skill:

  • 分析某只A股股票
  • 筛选符合条件的股票
  • 对比多只股票或行业内股票
  • 计算股票估值或内在价值
  • 查看股票的财务健康状况
  • 检测财务异常风险

Prerequisites

Python环境要求

bash
pip install akshare pandas numpy

依赖检查

在执行任何分析前,先检查akshare是否已安装:

bash
python -c "import akshare; print(akshare.__version__)"

如果未安装,提示用户安装:

bash
pip install akshare

Core Modules

1. Stock Screener (股票筛选器)

筛选符合条件的股票

2. Financial Analyzer (财务分析器)

个股深度财务分析

3. Industry Comparator (行业对比)

同行业横向对比分析

4. Valuation Calculator (估值计算器)

内在价值测算与安全边际计算


Workflow 1: Stock Screening (股票筛选)

用户请求筛选股票时使用。

Step 1: Collect Screening Criteria

向用户询问筛选条件。提供以下选项供用户选择或自定义:

估值指标:

  • PE (市盈率): 例如 PE < 15
  • PB (市净率): 例如 PB < 2
  • PS (市销率): 例如 PS < 3

盈利能力:

  • ROE (净资产收益率): 例如 ROE > 15%
  • ROA (总资产收益率): 例如 ROA > 8%
  • 毛利率: 例如 > 30%
  • 净利率: 例如 > 10%

成长性:

  • 营收增长率: 例如 > 10%
  • 净利润增长率: 例如 > 15%
  • 连续增长年数: 例如 >= 3年

股息:

  • 股息率: 例如 > 3%
  • 连续分红年数: 例如 >= 5年

财务安全:

  • 资产负债率: 例如 < 60%
  • 流动比率: 例如 > 1.5
  • 速动比率: 例如 > 1

筛选范围:

  • 全A股
  • 沪深300成分股
  • 中证500成分股
  • 创业板/科创板
  • 用户自定义列表

Step 2: Execute Screening

bash
python scripts/stock_screener.py \
    --scope "hs300" \
    --pe-max 15 \
    --roe-min 15 \
    --debt-ratio-max 60 \
    --dividend-min 2 \
    --output screening_result.json

参数说明:

  • --scope: 筛选范围 (all/hs300/zz500/cyb/kcb/custom:600519,000858,...)
  • --pe-max/--pe-min: PE范围
  • --pb-max/--pb-min: PB范围
  • --roe-min: 最低ROE
  • --growth-min: 最低增长率
  • --debt-ratio-max: 最大资产负债率
  • --dividend-min: 最低股息率
  • --output: 输出文件路径

Step 3: Present Results

读取 screening_result.json 并以表格形式呈现给用户:

代码名称PEPBROE股息率评分
600519贵州茅台25.38.530.2%2.1%85

Workflow 2: Stock Analysis (个股分析)

用户请求分析某只股票时使用。

Step 1: Collect Stock Information

询问用户:

  1. 股票代码或名称
  2. 分析深度级别:
    • 摘要级:关键指标 + 投资结论(1页)
    • 标准级:财务分析 + 估值 + 行业对比 + 风险提示
    • 深度级:完整调研报告,包含历史数据追踪

Step 2: Fetch Stock Data

bash
python scripts/data_fetcher.py \
    --code "600519" \
    --data-type all \
    --years 5 \
    --output stock_data.json

参数说明:

  • --code: 股票代码
  • --data-type: 数据类型 (basic/financial/valuation/holder/all)
  • --years: 获取多少年的历史数据
  • --output: 输出文件

Step 3: Run Financial Analysis

bash
python scripts/financial_analyzer.py \
    --input stock_data.json \
    --level standard \
    --output analysis_result.json

参数说明:

  • --input: 输入的股票数据文件
  • --level: 分析深度 (summary/standard/deep)
  • --output: 输出文件

Step 4: Calculate Valuation

bash
python scripts/valuation_calculator.py \
    --input stock_data.json \
    --methods dcf,ddm,relative \
    --discount-rate 10 \
    --growth-rate 8 \
    --output valuation_result.json

参数说明:

  • --input: 股票数据文件
  • --methods: 估值方法 (dcf/ddm/relative/all)
  • --discount-rate: 折现率(%)
  • --growth-rate: 永续增长率(%)
  • --margin-of-safety: 安全边际(%)
  • --output: 输出文件

Step 5: Generate Report

读取分析结果,参考 templates/analysis_report.md 模板生成中文分析报告。

报告结构(标准级):

  1. 公司概况:基本信息、主营业务
  2. 财务健康:资产负债表分析
  3. 盈利能力:杜邦分析、利润率趋势
  4. 成长性分析:营收/利润增长趋势
  5. 估值分析:DCF/DDM/相对估值
  6. 风险提示:财务异常检测、股东减持
  7. 投资结论:综合评分、操作建议

Workflow 3: Industry Comparison (行业对比)

Step 1: Collect Comparison Targets

询问用户:

  1. 目标股票代码(可多个)
  2. 或者:行业分类 + 对比数量

Step 2: Fetch Industry Data

bash
python scripts/data_fetcher.py \
    --codes "600519,000858,002304" \
    --data-type comparison \
    --output industry_data.json

或按行业获取:

bash
python scripts/data_fetcher.py \
    --industry "白酒" \
    --top 10 \
    --output industry_data.json

Step 3: Generate Comparison

bash
python scripts/financial_analyzer.py \
    --input industry_data.json \
    --mode comparison \
    --output comparison_result.json

Step 4: Present Comparison Table

指标贵州茅台五粮液洋河股份行业均值
PE25.318.215.622.4
ROE30.2%22.5%20.1%18.5%
毛利率91.5%75.2%72.3%65.4%
评分857875-

Workflow 4: Valuation Calculator (估值计算)

Step 1: Collect Valuation Parameters

询问用户估值参数(或使用默认值):

DCF模型参数:

  • 折现率 (WACC): 默认10%
  • 预测期: 默认5年
  • 永续增长率: 默认3%

DDM模型参数:

  • 要求回报率: 默认10%
  • 股息增长率: 使用历史数据推算

相对估值参数:

  • 对比基准: 行业均值 / 历史均值

Step 2: Run Valuation

bash
python scripts/valuation_calculator.py \
    --code "600519" \
    --methods all \
    --discount-rate 10 \
    --terminal-growth 3 \
    --forecast-years 5 \
    --margin-of-safety 30 \
    --output valuation.json

Step 3: Present Valuation Results

估值方法内在价值当前价格安全边际价格结论
DCF¥2,150¥1,680¥1,505低估
DDM¥1,980¥1,680¥1,386低估
相对估值¥1,850¥1,680¥1,295合理

Financial Anomaly Detection (财务异常检测)

在分析过程中自动检测以下异常信号:

检测项目

  1. 应收账款异常

    • 应收账款增速 > 营收增速 × 1.5
    • 应收账款周转天数大幅增加
  2. 现金流背离

    • 净利润持续增长但经营现金流下降
    • 现金收入比 < 80%
  3. 存货异常

    • 存货增速 > 营收增速 × 2
    • 存货周转天数大幅增加
  4. 毛利率异常

    • 毛利率波动 > 行业均值波动 × 2
    • 毛利率与同行严重偏离
  5. 关联交易

    • 关联交易占比过高(> 30%)
  6. 股东减持

    • 大股东近期减持公告
    • 高管集中减持

风险等级

  • 🟢 低风险:无明显异常
  • 🟡 中风险:1-2项轻微异常
  • 🔴 高风险:多项异常或严重异常

A-Share Specific Analysis (A股特色分析)

政策敏感度

根据行业分类提供政策相关提示:

  • 房地产:房住不炒政策
  • 新能源:补贴政策变化
  • 医药:集采政策影响
  • 互联网:反垄断、数据安全

股东结构分析

  1. 控股股东类型(国企/民企/外资)
  2. 股权集中度
  3. 近期增减持情况
  4. 质押比例

Output Format

JSON输出格式

所有脚本输出JSON格式,便于后续处理:

json
{
  "code": "600519",
  "name": "贵州茅台",
  "analysis_date": "2025-01-25",
  "level": "standard",
  "summary": {
    "score": 85,
    "conclusion": "低估",
    "recommendation": "建议关注"
  },
  "financials": { ... },
  "valuation": { ... },
  "risks": [ ... ]
}

Markdown报告

生成结构化的中文Markdown报告,参考 templates/analysis_report.md。


Error Handling

网络错误

如果akshare数据获取失败,提示用户:

  1. 检查网络连接
  2. 稍后重试(可能是接口限流)
  3. 尝试更换数据源

股票代码无效

提示用户检查股票代码是否正确,提供可能的匹配建议。

数据不完整

对于新上市股票或财务数据不完整的情况,说明数据限制并基于可用数据进行分析。


Best Practices

  1. 数据时效性:财务数据以最新季报/年报为准,价格数据为当日收盘价
  2. 投资建议:所有分析仅供参考,不构成投资建议
  3. 风险提示:始终包含风险提示,特别是财务异常检测结果
  4. 对比分析:单只股票分析时,自动包含行业均值对比

Important Notes

  • 所有分析基于公开财务数据,不涉及任何内幕信息
  • 估值模型的参数假设对结果影响较大,需向用户说明
  • A股市场受政策影响较大,定量分析需结合定性判断

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the 中国A股分析工具 AI skill do?

A股价值投资分析工具,提供股票筛选、个股深度分析、行业对比和估值计算功能。基于价值投资理论,使用akshare获取公开财务数据,适合低频交易的普通投资者。

Why use 中国A股分析工具 on TypingMind?

Because you install it once and use it with any model. 中国A股分析工具 is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install 中国A股分析工具 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agentbay-ai/agentbay-skills/tree/main/china-stock-analysis. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use 中国A股分析工具?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with 中国A股分析工具?

As many as you like. As long as a model supports skills, you can use 中国A股分析工具 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the 中国A股分析工具 AI skill free?

It is published on GitHub by agentbay-ai. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇