daily-stock-analysis

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Daily Stock Analysis (股票智能分析系统)

每日股票分析（股票智能分析系统）

Skill by ara.so — Daily 2026 Skills collection.

LLM-powered stock analysis system for A-share, Hong Kong, and US markets. Automatically fetches quotes, news, and fundamentals, generates AI decision dashboards with buy/sell targets, and pushes results to WeChat/Feishu/Telegram/Discord/Email on a schedule via GitHub Actions — zero server cost.

由ara.so提供的Skill — 每日2026技能合集。

基于大语言模型（LLM）的A股、港股、美股分析系统，可自动获取行情、资讯及基本面数据，生成包含买卖目标价的AI决策仪表盘，并通过GitHub Actions定时推送结果至微信/飞书/Telegram/Discord/邮件等渠道 — 零服务器成本。

What It Does

功能特性

AI Decision Dashboard: One-line conclusion + precise buy/sell/stop-loss prices + checklist per stock
Multi-market: A-shares (CN), HK stocks, US stocks + indices (SPX, DJI, IXIC)
Data sources: AkShare, Tushare, YFinance for quotes; Tavily/SerpAPI/Brave for news
LLM backends: Gemini, OpenAI, Claude, DeepSeek, Qwen via LiteLLM (unified)
Push channels: WeChat Work, Feishu, Telegram, Discord, DingTalk, Email, PushPlus
Automation: GitHub Actions cron schedule, no server needed
Web UI: Portfolio management, history, backtesting, Agent Q&A
Agent: Multi-turn strategy Q&A with 11 built-in strategies (MA crossover, Elliott Wave, etc.)

AI决策仪表盘：一句话核心结论 + 精准买卖/止损价格 + 单只股票检查清单
多市场支持：A股（中国）、港股、美股 + 指数（SPX、DJI、IXIC）
数据来源：行情数据来自AkShare、Tushare、YFinance；资讯数据来自Tavily/SerpAPI/Brave
LLM后端：通过LiteLLM统一接入Gemini、OpenAI、Claude、DeepSeek、Qwen
推送渠道：企业微信、飞书、Telegram、Discord、钉钉、邮件、PushPlus
自动化运行：通过GitHub Actions定时任务执行，无需服务器
Web界面：投资组合管理、历史记录、回测、Agent问答
智能Agent：支持11种内置策略的多轮策略问答（如均线金叉、艾略特波浪等）

Installation

安装部署

Method 1: GitHub Actions (Recommended, Zero Cost)

方法1：GitHub Actions（推荐，零成本）

Step 1: Fork the repository

https://github.com/ZhuLinsen/daily_stock_analysis

Step 2: Configure Secrets (

Settings → Secrets and variables → Actions

)

Required — at least one LLM key:

GEMINI_API_KEY        # Google AI Studio (free tier available)
OPENAI_API_KEY        # OpenAI or compatible (DeepSeek, Qwen, etc.)
OPENAI_BASE_URL       # e.g. https://api.deepseek.com/v1
OPENAI_MODEL          # e.g. deepseek-chat, gpt-4o
AIHUBMIX_KEY          # AIHubMix (recommended, covers Gemini+GPT+Claude+DeepSeek)
ANTHROPIC_API_KEY     # Claude

Required — stock list:

STOCKS                # e.g. 600519,300750,AAPL,TSLA,00700.HK

Required — at least one notification channel:

TELEGRAM_BOT_TOKEN
TELEGRAM_CHAT_ID
FEISHU_WEBHOOK_URL
WECHAT_WEBHOOK_URL
EMAIL_SENDER / EMAIL_PASSWORD / EMAIL_RECEIVERS
DISCORD_WEBHOOK_URL

Step 3: Trigger manually or wait for cron

Go to

Actions → stock_analysis → Run workflow

步骤1：复刻仓库

https://github.com/ZhuLinsen/daily_stock_analysis

步骤2：配置密钥（

设置 → 密钥和变量 → Actions

）

必填项 — 至少一个LLM密钥：

GEMINI_API_KEY        # Google AI Studio（提供免费额度）
OPENAI_API_KEY        # OpenAI或兼容平台（如DeepSeek、Qwen等）
OPENAI_BASE_URL       # 示例：https://api.deepseek.com/v1
OPENAI_MODEL          # 示例：deepseek-chat, gpt-4o
AIHUBMIX_KEY          # AIHubMix（推荐，支持Gemini+GPT+Claude+DeepSeek）
ANTHROPIC_API_KEY     # Claude

必填项 — 股票列表：

STOCKS                # 示例：600519,300750,AAPL,TSLA,00700.HK

必填项 — 至少一个通知渠道：

TELEGRAM_BOT_TOKEN
TELEGRAM_CHAT_ID
FEISHU_WEBHOOK_URL
WECHAT_WEBHOOK_URL
EMAIL_SENDER / EMAIL_PASSWORD / EMAIL_RECEIVERS
DISCORD_WEBHOOK_URL

步骤3：手动触发或等待定时任务

进入

Actions → stock_analysis → 运行工作流

Method 2: Local / Docker

方法2：本地部署 / Docker

bash

git clone https://github.com/ZhuLinsen/daily_stock_analysis
cd daily_stock_analysis
cp .env.example .env

bash

git clone https://github.com/ZhuLinsen/daily_stock_analysis
cd daily_stock_analysis
cp .env.example .env

Edit .env with your keys

编辑.env文件，填入你的密钥

pip install -r requirements.txt python main.py


**Docker:**
```bash
docker build -t stock-analysis .
docker run --env-file .env stock-analysis

Docker Compose:

bash

docker-compose up -d

pip install -r requirements.txt python main.py


**Docker部署：**
```bash
docker build -t stock-analysis .
docker run --env-file .env stock-analysis

Docker Compose部署：

bash

docker-compose up -d

Configuration

配置说明

.env

File (Local)

.env文件（本地部署）

env

undefined

env

undefined

LLM - pick one or more

LLM - 选择一个或多个

GEMINI_API_KEY=your_gemini_key OPENAI_API_KEY=your_openai_key OPENAI_BASE_URL=https://api.deepseek.com/v1 OPENAI_MODEL=deepseek-chat AIHUBMIX_KEY=your_aihubmix_key

Stock list (comma-separated)

股票列表（逗号分隔）

STOCKS=600519,300750,AAPL,TSLA,00700.HK

Notification

通知设置

TELEGRAM_BOT_TOKEN=your_bot_token TELEGRAM_CHAT_ID=your_chat_id

Optional settings

可选设置

REPORT_TYPE=full # simple | full | brief ANALYSIS_DELAY=10 # seconds between stocks (avoid rate limiting) MAX_WORKERS=3 # concurrent analysis threads SINGLE_STOCK_NOTIFY=false # push each stock immediately when done NEWS_MAX_AGE_DAYS=3 # ignore news older than N days

undefined

REPORT_TYPE=full # simple | full | brief（简洁版 | 完整版 | 摘要版） ANALYSIS_DELAY=10 # 单只股票分析间隔（秒，避免请求限制） MAX_WORKERS=3 # 并发分析线程数 SINGLE_STOCK_NOTIFY=false # 单只股票分析完成后立即推送 NEWS_MAX_AGE_DAYS=3 # 忽略超过N天的旧资讯

undefined

Multi-Channel LLM (Advanced)

多渠道LLM配置（进阶）

env

LLM_CHANNELS=gemini,deepseek,claude
LLM_GEMINI_PROTOCOL=google
LLM_GEMINI_API_KEY=your_key
LLM_GEMINI_MODELS=gemini-2.0-flash,gemini-1.5-pro
LLM_GEMINI_ENABLED=true

LLM_DEEPSEEK_PROTOCOL=openai
LLM_DEEPSEEK_BASE_URL=https://api.deepseek.com/v1
LLM_DEEPSEEK_API_KEY=your_key
LLM_DEEPSEEK_MODELS=deepseek-chat
LLM_DEEPSEEK_ENABLED=true

env

LLM_CHANNELS=gemini,deepseek,claude
LLM_GEMINI_PROTOCOL=google
LLM_GEMINI_API_KEY=your_key
LLM_GEMINI_MODELS=gemini-2.0-flash,gemini-1.5-pro
LLM_GEMINI_ENABLED=true

LLM_DEEPSEEK_PROTOCOL=openai
LLM_DEEPSEEK_BASE_URL=https://api.deepseek.com/v1
LLM_DEEPSEEK_API_KEY=your_key
LLM_DEEPSEEK_MODELS=deepseek-chat
LLM_DEEPSEEK_ENABLED=true

Stock Grouping (Send Different Stocks to Different Emails)

股票分组推送（不同股票推送给不同邮箱）

env

STOCK_GROUP_1=600519,300750,000858
EMAIL_GROUP_1=investor1@example.com

STOCK_GROUP_2=AAPL,TSLA,NVDA
EMAIL_GROUP_2=investor2@example.com

env

STOCK_GROUP_1=600519,300750,000858
EMAIL_GROUP_1=investor1@example.com

STOCK_GROUP_2=AAPL,TSLA,NVDA
EMAIL_GROUP_2=investor2@example.com

Market Review Mode

市场复盘模式

env

MARKET_REVIEW=cn      # cn | us | both

env

MARKET_REVIEW=cn      # cn | us | both

cn = A-share three-phase review strategy

cn = A股三阶段复盘策略

us = US Regime Strategy (risk-on/neutral/risk-off)

us = 美股Regime策略（风险偏好/中性/规避）

both = both markets

both = 同时复盘两个市场

undefined

undefined

Key Commands (CLI)

核心命令（CLI）

bash

undefined

bash

undefined

Run full analysis immediately

立即运行完整分析

python main.py

Analyze specific stocks only

仅分析指定股票

STOCKS=600519,AAPL python main.py

Run web dashboard

启动Web仪表盘

python web_app.py

Access at http://localhost:5000

访问地址：http://localhost:5000

Run with Docker (env file)

使用Docker运行（加载.env文件）

docker run --env-file .env stock-analysis python main.py

Run schedule mode (waits for cron, then runs)

启动定时模式（等待定时任务触发后运行）

SCHEDULE_RUN_IMMEDIATELY=true python main.py

undefined

SCHEDULE_RUN_IMMEDIATELY=true python main.py

undefined

GitHub Actions Workflow

GitHub Actions工作流

The workflow file

.github/workflows/stock_analysis.yml

runs on schedule:

yaml

undefined

工作流文件

.github/workflows/stock_analysis.yml

按计划运行：

yaml

undefined

Default schedule - customize in the workflow file

默认定时规则 - 在工作流文件中自定义

on: schedule: - cron: '30 1 * * 1-5' # 9:30 AM CST (UTC+8) weekdays workflow_dispatch: # manual trigger


**To change schedule:** Edit `.github/workflows/stock_analysis.yml` cron expression.

**To add secrets via GitHub CLI:**
```bash
gh secret set GEMINI_API_KEY --body "$GEMINI_API_KEY"
gh secret set STOCKS --body "600519,300750,AAPL,TSLA"
gh secret set TELEGRAM_BOT_TOKEN --body "$TG_TOKEN"
gh secret set TELEGRAM_CHAT_ID --body "$TG_CHAT_ID"

on: schedule: - cron: '30 1 * * 1-5' # 工作日上午9:30（UTC+8） workflow_dispatch: # 手动触发


**修改定时规则：** 编辑`.github/workflows/stock_analysis.yml`中的cron表达式。

**通过GitHub CLI添加密钥：**
```bash
gh secret set GEMINI_API_KEY --body "$GEMINI_API_KEY"
gh secret set STOCKS --body "600519,300750,AAPL,TSLA"
gh secret set TELEGRAM_BOT_TOKEN --body "$TG_TOKEN"
gh secret set TELEGRAM_CHAT_ID --body "$TG_CHAT_ID"

Code Examples

代码示例

Programmatic Analysis (Python)

程序化分析（Python）

python

undefined

python

undefined

Run analysis for specific stocks programmatically

程序化分析指定股票

import asyncio from analyzer import StockAnalyzer

async def analyze(): analyzer = StockAnalyzer()

# Analyze a single A-share stock
result = await analyzer.analyze_stock("600519")  # Moutai
print(result['conclusion'])
print(result['buy_price'])
print(result['stop_loss'])
print(result['target_price'])

asyncio.run(analyze())

undefined

import asyncio from analyzer import StockAnalyzer

async def analyze(): analyzer = StockAnalyzer()

# 分析单只A股股票
result = await analyzer.analyze_stock("600519")  # 贵州茅台
print(result['conclusion'])
print(result['buy_price'])
print(result['stop_loss'])
print(result['target_price'])

asyncio.run(analyze())

undefined

Custom Notification Integration

自定义通知集成

python

from notifier import NotificationManager

notifier = NotificationManager()

python

from notifier import NotificationManager

notifier = NotificationManager()

Send to Telegram

发送至Telegram

await notifier.send_telegram( token=os.environ['TELEGRAM_BOT_TOKEN'], chat_id=os.environ['TELEGRAM_CHAT_ID'], message="📈 Analysis complete\n600519: BUY at 1680, SL: 1620, TP: 1800" )

await notifier.send_telegram( token=os.environ['TELEGRAM_BOT_TOKEN'], chat_id=os.environ['TELEGRAM_CHAT_ID'], message="📈 分析完成\n600519：建议在1680买入，止损1620，止盈1800" )

Send to Feishu webhook

发送至飞书Webhook

await notifier.send_feishu( webhook_url=os.environ['FEISHU_WEBHOOK_URL'], content=analysis_report )

undefined

await notifier.send_feishu( webhook_url=os.environ['FEISHU_WEBHOOK_URL'], content=analysis_report )

undefined

Using the Agent API

使用Agent API

python

import requests

python

import requests

Ask the stock agent a strategy question

向股票Agent提问策略问题

response = requests.post('http://localhost:5000/api/agent/chat', json={ "message": "600519现在适合买入吗？用均线金叉策略分析", "stock_code": "600519", "strategy": "ma_crossover" # ma_crossover, elliott_wave, chan_theory, etc. })

print(response.json()['reply'])

undefined

print(response.json()['reply'])

undefined

Backtest Analysis Accuracy

回测分析准确率

python

import requests

python

import requests

Trigger backtest for a stock

触发单只股票回测

response = requests.post('http://localhost:5000/api/backtest', json={ "stock_code": "600519", "days": 30 # evaluate last 30 days of AI predictions })

result = response.json() print(f"Direction accuracy: {result['direction_accuracy']}%") print(f"Take-profit hit rate: {result['tp_hit_rate']}%") print(f"Stop-loss hit rate: {result['sl_hit_rate']}%")

undefined

response = requests.post('http://localhost:5000/api/backtest', json={ "stock_code": "600519", "days": 30 # 评估过去30天的AI预测结果 })

result = response.json() print(f"方向准确率：{result['direction_accuracy']}%") print(f"止盈命中率：{result['tp_hit_rate']}%") print(f"止损命中率：{result['sl_hit_rate']}%")

undefined

Import Stocks from Image (Vision LLM)

从图片导入股票（视觉LLM）

python

import requests

python

import requests

Upload screenshot of stock list for AI extraction

上传股票列表截图，由AI提取股票信息

with open('watchlist_screenshot.png', 'rb') as f: response = requests.post( 'http://localhost:5000/api/stocks/import/image', files={'image': f} )

stocks = response.json()['extracted_stocks']

with open('watchlist_screenshot.png', 'rb') as f: response = requests.post( 'http://localhost:5000/api/stocks/import/image', files={'image': f} )

stocks = response.json()['extracted_stocks']

Returns: [{"code": "600519", "name": "贵州茅台", "confidence": 0.98}, ...]

返回结果：[{"code": "600519", "name": "贵州茅台", "confidence": 0.98}, ...]

undefined

undefined

Web Dashboard Features

Web仪表盘功能

Start the web app:

bash

python web_app.py

Route	Feature
`/`	Today's analysis dashboard
`/portfolio`	Holdings management, P&L tracking
`/history`	Past analysis reports (bulk delete supported)
`/backtest`	AI prediction accuracy backtest
`/agent`	Multi-turn strategy Q&A
`/settings`	LLM channels, notification config
`/import`	Import stocks from image/CSV/clipboard

启动Web应用：

bash

python web_app.py

路由	功能
`/`	今日分析仪表盘
`/portfolio`	持仓管理、盈亏追踪
`/history`	历史分析报告（支持批量删除）
`/backtest`	AI预测准确率回测
`/agent`	多轮策略问答
`/settings`	LLM渠道、通知配置
`/import`	从图片/CSV/剪贴板导入股票

Supported Stock Formats

支持的股票格式

undefined

undefined

A-shares (6-digit code)

A股（6位代码）

600519 # 贵州茅台 300750 # 宁德时代 000858 # 五粮液

HK stocks (5-digit + .HK)

港股（5位代码 + .HK）

00700.HK # 腾讯控股 09988.HK # 阿里巴巴

US stocks (ticker)

美股（交易代码）

AAPL TSLA NVDA

US indices

美股指数

SPX # S&P 500 DJI # Dow Jones IXIC # NASDAQ

undefined

SPX # 标普500 DJI # 道琼斯 IXIC # 纳斯达克

undefined

Built-in Trading Rules

内置交易规则

Rule	Config
No chasing highs	`DEVIATION_THRESHOLD=5` (%, auto-relaxed for strong trend)
Trend trading	MA5 > MA10 > MA20 bullish alignment required
Precise targets	Buy price, stop-loss, take-profit per stock
News freshness	`NEWS_MAX_AGE_DAYS=3` (skip stale news)
Checklist	Each condition marked: ✅ Satisfied / ⚠️ Caution / ❌ Not Met

规则	配置项
不追高	`DEVIATION_THRESHOLD=5` （%，强势趋势下自动放宽）
趋势交易	需满足MA5 > MA10 > MA20多头排列
精准目标	单只股票对应买入价、止损价、止盈价
资讯新鲜度	`NEWS_MAX_AGE_DAYS=3` （跳过旧资讯）
检查清单	每个条件标记：✅ 满足 / ⚠️ 注意 / ❌ 不满足

Troubleshooting

常见问题排查

Analysis runs but no push received:

bash

undefined

分析运行但未收到推送：

bash

undefined

Check notification config

检查通知配置

python -c "from notifier import test_all_channels; test_all_channels()"

Verify secrets are set (GitHub Actions)

验证GitHub Actions中的密钥是否设置

gh secret list


**LLM API errors / rate limiting:**
```env
ANALYSIS_DELAY=15        # increase delay between stocks
MAX_WORKERS=1            # reduce concurrency
LITELLM_FALLBACK_MODELS=gemini-1.5-flash,deepseek-chat  # add fallbacks

AkShare data fetch fails (A-shares):

bash

pip install akshare --upgrade

gh secret list


**LLM API错误 / 请求限制：**
```env
ANALYSIS_DELAY=15        # 增加单只股票分析间隔
MAX_WORKERS=1            # 减少并发数
LITELLM_FALLBACK_MODELS=gemini-1.5-flash,deepseek-chat  # 添加备用模型

AkShare行情数据获取失败（A股）：

bash

pip install akshare --upgrade

A-share data requires Chinese network or proxy

A股数据需要中国网络环境或代理


**YFinance US stock data issues:**
```bash
pip install yfinance --upgrade


**YFinance美股数据问题：**
```bash
pip install yfinance --upgrade

US stocks use YFinance exclusively for consistency

美股数据统一使用YFinance


**GitHub Actions not triggering:**
- Check Actions are enabled: `Settings → Actions → General → Allow all actions`
- Verify cron syntax at [crontab.guru](https://crontab.guru)
- Check workflow file exists: `.github/workflows/stock_analysis.yml`

**Web auth issues (admin password):**
```env


**GitHub Actions未触发：**
- 检查Actions是否启用：`设置 → Actions → 通用 → 允许所有Actions`
- 在[crontab.guru](https://crontab.guru)验证cron语法
- 确认工作流文件存在：`.github/workflows/stock_analysis.yml`

**Web界面权限问题（管理员密码）：**
```env

If auth was disabled and re-enabled, current password required

如果曾关闭权限后重新启用，需输入当前密码

Reset via environment variable

通过环境变量重置密码

WEB_ADMIN_PASSWORD=new_password


**Multi-worker deployment auth state:**
```bash

WEB_ADMIN_PASSWORD=new_password


**多Worker部署时权限状态不同步：**
```bash

Auth toggle only applies to current process

权限切换仅对当前进程生效

Must restart all workers to sync state

需重启所有Worker以同步状态

docker-compose restart

undefined

docker-compose restart

undefined

Report Types

报告类型

env

REPORT_TYPE=simple   # Concise: conclusion + key prices only
REPORT_TYPE=full     # Complete: all technical + fundamental + news analysis
REPORT_TYPE=brief    # 3-5 sentence summary

Full report includes:

一句话核心结论 (one-line core conclusion)
技术面分析 (technical: MA alignment, chip distribution)
基本面 (valuation, growth, earnings, institutional holdings)
舆情情报 (news sentiment, social media — US stocks)
精确买卖点位 (precise entry/exit levels)
操作检查清单 (action checklist)
板块涨跌榜 (sector performance boards)

env

REPORT_TYPE=simple   # 简洁版：仅包含结论 + 核心价格
REPORT_TYPE=full     # 完整版：包含技术面+基本面+资讯分析
REPORT_TYPE=brief    # 摘要版：3-5句话总结

完整版报告包含：

一句话核心结论
技术面分析（均线排列、筹码分布）
基本面（估值、成长性、盈利、机构持仓）
舆情情报（资讯情绪、社交媒体热度 — 美股）
精确买卖点位
操作检查清单
板块涨跌榜

LLM Priority Order

LLM优先级顺序

Gemini → Anthropic → OpenAI/AIHubMix/Compatible

AIHubMix is recommended for single-key access to all major models without VPN:

env

AIHUBMIX_KEY=$AIHUBMIX_KEY  # covers Gemini, GPT, Claude, DeepSeek

Gemini → Anthropic → OpenAI/AIHubMix/兼容平台

AIHubMix是推荐选项，无需VPN即可通过单个密钥访问所有主流模型：

env

AIHUBMIX_KEY=$AIHUBMIX_KEY  # 支持Gemini、GPT、Claude、DeepSeek

No OPENAI_BASE_URL needed — auto-configured

无需设置OPENAI_BASE_URL — 自动配置

undefined

undefined