### Install Awesome Finance Skills using npx

Source: https://context7.com/rkiding/awesome-finance-skills/llms.txt

Use npx for a one-step installation of the Awesome Finance Skills. Alternatively, find skills interactively or install manually by cloning the repository.

```bash
npx skills add RKiding/Awesome-finance-skills@alphaear-news
```

```bash
npx skills find "alphaear"
```

```bash
git clone https://github.com/RKiding/Awesome-finance-skills.git
cp -r Awesome-finance-skills/skills/* ~/.config/opencode/skills/
```

--------------------------------

### Clone the Repository

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/README.md

Clone the Awesome Finance Skills repository to manually install the skills. This method is useful for offline installations or custom setups.

```bash
git clone https://github.com/RKiding/Awesome-finance-skills.git
```

--------------------------------

### Skill Structure Example

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/skill-creator/SKILL.md

Illustrates the directory structure for a typical skill, including the required SKILL.md file and optional bundled resources.

```tree
skill-name/
├── SKILL.md (required)
│   ├── YAML frontmatter metadata (required)
│   │   ├── name: (required)
│   │   └── description: (required)
│   └── Markdown instructions (required)
└── Bundled Resources (optional)
    ├── scripts/          - Executable code (Python/Bash/etc.)
    ├── references/       - Documentation intended to be loaded into context as needed
    └── assets/           - Files used in output (templates, icons, fonts, etc.)
```

--------------------------------

### Clone the Repository (Chinese)

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/README.md

Clone the Awesome Finance Skills repository to manually install the skills. This method is useful for offline installations or custom setups, with Chinese comments.

```bash
# 克隆仓库
git clone https://github.com/RKiding/Awesome-finance-skills.git
```

--------------------------------

### Install a Specific Skill with npx (Chinese)

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/README.md

Use `npx skills add` to install individual skills from the Awesome Finance Skills collection. This is the recommended one-step installation method, shown with Chinese comments.

```bash
# 安装指定技能（如：alphaear-news）
npx skills add RKiding/Awesome-finance-skills@alphaear-news
```

--------------------------------

### Install a Specific Skill with npx

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/README.md

Use `npx skills add` to install individual skills from the Awesome Finance Skills collection. This is the recommended one-step installation method.

```bash
npx skills add RKiding/Awesome-finance-skills@alphaear-news
```

--------------------------------

### SKILL.md Frontmatter Example

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/skill-creator/SKILL.md

Shows the required YAML frontmatter for a SKILL.md file, including name and description fields.

```yaml
name: (required)
description: (required)
```

--------------------------------

### Initialize a New Skill

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/skill-creator/SKILL.md

Use the init_skill.py script to generate a new skill template. Specify the skill name, output path, and optionally include resource directories or example files.

```bash
scripts/init_skill.py <skill-name> --path <output-directory> [--resources scripts,references,assets] [--examples]
```

```bash
scripts/init_skill.py my-skill --path skills/public
```

```bash
scripts/init_skill.py my-skill --path skills/public --resources scripts,references
```

```bash
scripts/init_skill.py my-skill --path skills/public --resources scripts --examples
```

--------------------------------

### Install Skills to Agent Frameworks

Source: https://context7.com/rkiding/awesome-finance-skills/llms.txt

Copies skill folders to the appropriate directories for various agent frameworks. The destination path determines the scope (personal, project, global, workspace).

```bash
# Claude Code / Codex - Personal scope
cp -r alphaear-news ~/.claude/skills/
cp -r alphaear-news ~/.codex/skills/
```

```bash
# Claude Code / Codex - Project scope
cp -r alphaear-news .claude/skills/
```

```bash
# OpenCode - Global scope
cp -r alphaear-news ~/.config/opencode/skills/
```

```bash
# OpenCode - Project scope
cp -r alphaear-news .opencode/skills/
# or
cp -r alphaear-news .claude/skills/
```

```bash
# Antigravity - Workspace scope
cp -r alphaear-news .agent/skills/
```

```bash
# Antigravity - Global scope
cp -r alphaear-news ~/.gemini/antigravity/global_skills/
```

```bash
# OpenClaw - Workspace scope (highest priority)
cp -r alphaear-news ./skills/
```

```bash
# OpenClaw - Managed scope
cp -r alphaear-news ~/.openclaw/skills/
```

--------------------------------

### Python Example for Market Forecasting

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-predictor/SKILL.md

Demonstrates how to use KronosPredictorUtility to forecast market trends for a given stock symbol. Ensure DatabaseManager and KronosPredictorUtility are correctly imported and initialized.

```python
from scripts.utils.kronos_predictor import KronosPredictorUtility
from scripts.utils.database_manager import DatabaseManager

db = DatabaseManager()
predictor = KronosPredictorUtility()

# Forecast
forecast = predictor.predict("600519", horizon="7d")
print(forecast)
```

--------------------------------

### Markdown for PDF Processing Quick Start

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/skill-creator/SKILL.md

This markdown snippet shows how to extract text using pdfplumber. It's part of a high-level guide with references pattern.

```markdown
# PDF Processing

## Quick start

Extract text with pdfplumber:
[code example]

## Advanced features

- **Form filling**: See [FORMS.md](FORMS.md) for complete guide
- **API reference**: See [REFERENCE.md](REFERENCE.md) for all methods
- **Examples**: See [EXAMPLES.md](EXAMPLES.md) for common patterns
```

--------------------------------

### Search for Skills with npx (Chinese)

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/README.md

Use `npx skills find` to search for available skills within the Awesome Finance Skills collection. This helps in discovering and selecting specific skills, with Chinese search query example.

```bash
# 或者搜索更多金融技能
npx skills find "get the finance news (alphaear-news)"
```

--------------------------------

### Write Financial Analysis Section (Writer)

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-reporter/references/PROMPTS.md

This prompt guides an AI agent to write a deep analysis section for a specific financial theme. It requires weaving input signals into a coherent narrative, citing ISQ scores and using a specific citation format, and including detailed predictions for affected tickers. The prompt also specifies formatting for titles, subtitles, and the inclusion of chart blocks.

```markdown
You are a senior financial analyst. Write a deep analysis section for the core theme **"{theme_title}"**.

### Input Signals (Cluster)
{signal_cluster_text}

### Requirements
1. **Narrative**: Weave signals into a coherent story. Start with Macro/Industry background, then transmission mechanism, finally stock impact.
2. **Quantification**: Cite ISQ scores (Confidence, Intensity) to support views.
3. **Citations**: Use `[@CITE_KEY]` format. Keys are provided in input.
4. **Predictions**: detailed predictions for affected tickers (T+3/T+5 direction).

### Formatting
- Main Title: `## {theme_title}`
- Subtitles: `###`
- **Charts**: Insert at least 1-2 `json-chart` blocks.

**Chart Example:**
```json-chart
{"type": "forecast", "ticker": "002371.SZ", "title": "Forecast", "pred_len": 5}
```
```

--------------------------------

### Analyst Forecast Adjustment Prompt

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-predictor/references/PROMPTS.md

Use this prompt to guide a quantitative strategy analyst in adjusting a base forecast using latest intelligence. Ensure the output adheres to the specified JSON structure.

```markdown
You are a senior quantitative strategy analyst.
Your task is to subjectively/logically adjust the given [Kronos Model Forecast] based on the [Latest Intelligence/News Context].

Ticker: {ticker}

【Kronos Base Forecast (OHLC)】:
{forecast_str}

【Latest Intelligence Context】:
{news_context}

**Adjustment Principles:**
1. Base forecast is technical-only.
2. Context may contain a "Quantitative Correction" from a news-aware model. **Highly respect** this unless logic is flawed.
3. Use qualitative analysis (news logic) to verify or fine-tune.
4. If no quantitative correction exists, verify trend manually against news sentiment.

**Output (Strict JSON):**
```json
{
  "adjusted_forecast": [
    {
      "date": "YYYY-MM-DD",
      "open": <float>,
      "high": <float>,
      "low": <float>,
      "close": <float>,
      "volume": <float>
    },
    ...
  ],
  "rationale": "Detailed logic..."
}
```
Ensure same number of data points as base forecast.
```

--------------------------------

### Generate Unified Trends Report

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-news/SKILL.md

Aggregates top news from multiple specified sources into a unified trends report. This is useful for getting a consolidated view of market sentiment.

```python
news_tools.get_unified_trends(sources)
```

--------------------------------

### Fetch Hot News with NewsNowTools

Source: https://context7.com/rkiding/awesome-finance-skills/llms.txt

Initialize NewsNowTools with a database manager to fetch trending financial news from various sources. Content extraction and database persistence are supported. Specify sources like 'cls', 'wallstreetcn', 'weibo', etc.

```python
from scripts.news_tools import NewsNowTools
from scripts.database_manager import DatabaseManager

db = DatabaseManager("data/signal_flux.db")
news_tools = NewsNowTools(db)

# Fetch top 15 news from Cailian (财联社)
news = news_tools.fetch_hot_news(source_id="cls", count=15, fetch_content=False)
for item in news[:3]:
    print(f"[{item['rank']}] {item['title']}")
    print(f"    URL: {item['url']}")
    print(f"    Published: {item['publish_time']}")

# Fetch with full content extraction
news_with_content = news_tools.fetch_hot_news("wallstreetcn", count=5, fetch_content=True)
print(news_with_content[0]['content'][:200])  # Markdown content from Jina

# Fetch specific URL content
content = news_tools.fetch_news_content("https://www.cls.cn/detail/1234567")
print(content)  # Returns Markdown formatted article
```

--------------------------------

### Run DeepEar Lite Test Script

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-deepear-lite/SKILL.md

Execute this command to verify the connection and data fetching capabilities of the DeepEar Lite skill.

```bash
python scripts/deepear_lite.py
```

--------------------------------

### Generate Chart Configurations with visualizer.py

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-reporter/SKILL.md

Use the `visualizer.py` script to manually generate chart configurations. This script is typically invoked by the Writer Prompt for creating visual aids within reports.

```python
scripts/visualizer.py
```

--------------------------------

### Package a Skill

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/skill-creator/SKILL.md

Use this script to package a completed skill into a distributable .skill file. It automatically validates the skill before packaging.

```bash
scripts/package_skill.py <path/to/skill-folder>
```

```bash
scripts/package_skill.py <path/to/skill-folder> ./dist
```

--------------------------------

### Copy Skills to OpenCode Agent (Chinese)

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/README.md

Manually copy the skills from the cloned repository to the designated skills directory for the OpenCode agent. Ensure the path is correct for your agent's configuration, with Chinese comments.

```bash
# 复制技能到你的 Agent（以 OpenCode 为例）
cp -r Awesome-finance-skills/skills/* ~/.config/opencode/skills/
```

--------------------------------

### Assemble Final Financial Report (Editor)

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-reporter/references/PROMPTS.md

Use this prompt to instruct an AI agent to assemble drafted financial report sections into a final, professional document. It requires ensuring correct structural hierarchy, generating reference and risk factor sections, and creating an executive summary with a quick scan table. The output must be strictly in Markdown format.

```markdown
You are a professional editor. Assemble the drafted sections into a final report.

### Draft Sections
{draft_sections}

### Requirements
1. **Structure**: Ensure H2/H3 hierarchy is correct.
2. **References**: Generate `## References` section from source list.
3. **Risk**: Generate `## Risk Factors`.
4. **Summary**: Generate `## Executive Summary` with a "Quick Scan" table.

Output strictly Markdown.
```

--------------------------------

### Generate Draw.io XML from Logic Description

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-logic-visualizer/references/PROMPTS.md

Use this prompt to instruct an AI to create Draw.io (MxGraph) XML diagrams. It specifies rules for XML format, node styling (including colors for positive, negative, and neutral impacts), auto-layout strategies, and edge connections. Requires a JSON input for nodes and logic.

```markdown
You are an expert at creating Draw.io (MxGraph) diagrams in XML format.
Your task is to generate a valid MXGraphModel XML based on the logic description.

### Rules:
1. Output ONLY the XML code. Start with `<mxGraphModel>` and end with `</mxGraphModel>`.
2. Do not use compressed XML. Use plain XML.
3. Use standard shapes: `rounded=1;whiteSpace=wrap;html=1;` for boxes.
4. **Auto-layout Strategy**:
   - Identify "layers" or "stages" in the logic.
   - Assign X coordinates based on layers (e.g., 0, 200, 400).
   - Assign Y coordinates to distribute nodes vertically (e.g., 0, 100, 200).
   - Ensure nodes do not overlap.
5. **Edges**: Connect nodes logically using `<mxCell edge="1" ...>`.

### Template:
<mxGraphModel dx="1000" dy="1000" grid="1" gridSize="10" guides="1" tooltips="1" connect="1" arrows="1" fold="1" page="1" pageScale="1" pageWidth="827" pageHeight="1169" math="0" shadow="0">
  <root>
    <mxCell id="0"/>
    <mxCell id="1" parent="0"/>
    
    <!-- Node Example -->
    <mxCell id="n1" value="Node Label" style="rounded=1;whiteSpace=wrap;html=1;fillColor=#dae8fc;strokeColor=#6c8ebf;" vertex="1" parent="1">
      <mxGeometry x="100" y="100" width="120" height="60" as="geometry"/>
    </mxCell>
    
    <!-- Edge Example -->
    <mxCell id="e1" value="Connection" style="edgeStyle=orthogonalEdgeStyle;rounded=0;orthogonalLoop=1;jettySize=auto;html=1;" edge="1" parent="1" source="n1" target="n2">
      <mxGeometry relative="1" as="geometry"/>
    </mxCell>
  </root>
</mxGraphModel>

Please generate a Draw.io XML diagram for the following logic flow:

**Title**: {title}

**Nodes and Logic**:
{nodes_json}

Ensure the layout flows logically from Left to Right (or Top to Bottom for hierarchies).
Use different colors for 'Positive' (Green/fillColor=#d5e8d4), 'Negative' (Red/fillColor=#f8cecc), and 'Neutral' (Grey/fillColor=#f5f5f5) impacts.
```

--------------------------------

### Fetch Prediction Market Data with PolymarketTools

Source: https://context7.com/rkiding/awesome-finance-skills/llms.txt

Initialize PolymarketTools with a database manager to retrieve active prediction market data from Polymarket. This includes questions, possible outcomes, prices, and trading volume. A formatted summary report can also be generated.

```python
from scripts.news_tools import PolymarketTools
from scripts.database_manager import DatabaseManager

db = DatabaseManager()
poly_tools = PolymarketTools(db)

# Get active prediction markets
markets = poly_tools.get_active_markets(limit=10)
for m in markets[:3]:
    print(f"Question: {m['question']}")
    print(f"  Outcomes: {m['outcomes']}")
    print(f"  Prices: {m['outcomePrices']}")
    print(f"  Volume: ${float(m['volume']):,.0f}")

# Get formatted summary report
summary = poly_tools.get_market_summary(limit=5)
print(summary)
```

--------------------------------

### Set HTTP Proxy Environment Variable

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-stock/SKILL.md

Configure HTTP proxy settings for network requests, particularly for accessing US stock data via yfinance when direct connection is not possible.

```bash
export HTTP_PROXY="http://<proxy_ip>:<port>"
export HTTPS_PROXY="http://<proxy_ip>:<port>"
```

--------------------------------

### Cluster Financial Signals into Themes (Planner)

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-reporter/references/PROMPTS.md

Use this prompt to instruct an AI agent to group scattered financial signals into 3-5 core logical themes for a structured report. It requires the agent to aggregate correlated signals, generate theme titles with signal IDs, and adhere to a specified JSON output format.

```markdown
You are a senior financial report editor. Your task is to cluster the following scattered financial signals into 3-5 core logical themes for a structured report.

### Input Signals
{signals_text}

### Requirements
1. **Theme Aggregation**: Group highly correlated signals (e.g., all related to "supply chain restructuring" or "policy tightening").
2. **Narrative Logic**: Generate only theme titles and list of signal IDs.
3. **Quantity Control**: 3-5 major themes.

### Output Format (JSON)
{
    "clusters": [
        {
            "theme_title": "Theme Name (e.g. Supply Chain Shock)",
            "signal_ids": [1, 3, 5],
            "rationale": "These signals all point to..."
        },
        ...
    ]
}
```

--------------------------------

### Copy Skills to OpenCode Agent

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/README.md

Manually copy the skills from the cloned repository to the designated skills directory for the OpenCode agent. Ensure the path is correct for your agent's configuration.

```bash
cp -r Awesome-finance-skills/skills/* ~/.config/opencode/skills/
```

--------------------------------

### Fetch Company Fundamentals with StockTools

Source: https://context7.com/rkiding/awesome-finance-skills/llms.txt

Retrieve basic company information such as sector, market cap, and PE ratio using `get_stock_fundamentals`. This method supports both A-Share and US stocks, utilizing different data sources.

```python
from scripts.stock_tools import StockTools, get_stock_analysis
from scripts.database_manager import DatabaseManager

db = DatabaseManager()
stock_tools = StockTools(db)

# A-Share fundamentals (via akshare/EastMoney)
fundamentals = stock_tools.get_stock_fundamentals("600519")
print(fundamentals)

# Output:
# {
#     'name': '贵州茅台',
#     'code': '600519',
#     'sector': '酿酒行业',
#     'market_cap': '22500亿',
#     'listing_date': '2001-08-27',
#     'pe_ratio': '35.2'
# }

# US stock fundamentals (via yfinance)
fundamentals_us = stock_tools.get_stock_fundamentals("AAPL")
print(fundamentals_us)

# Output:
# {
#     'name': 'Apple Inc.',
#     'sector': 'Technology',
#     'industry': 'Consumer Electronics',
#     'market_cap': 2950000000000,
#     'pe_ratio': 28.5,
#     'summary': 'Apple Inc. designs, manufactures, and markets smartphones...',
#     'currency': 'USD'
# }

# Generate complete stock analysis report
report = get_stock_analysis("600519", db)
print(report)

# Output:
# ## 📊 600519 分析报告
# - **查询时段**: 2023-10-15 -> 2024-01-15
# - **当前价**: ¥1788.30
# - **时段涨跌**: +5.23%
# - **最高/最低**: ¥1850.00 / ¥1680.00
# 
# ### 最近交易概览
# ```
#       date    close  change_pct     volume
# 2024-01-11  1755.20       -0.75  2123456.0
# 2024-01-12  1780.00        1.41  2567890.0
# ...
# ```
```

--------------------------------

### Search for Skills with npx

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/README.md

Use `npx skills find` to search for available skills within the Awesome Finance Skills collection. This helps in discovering and selecting specific skills.

```bash
npx skills find "alphaear"
```

--------------------------------

### NewsNowTools - Real-time Hot News Fetching

Source: https://context7.com/rkiding/awesome-finance-skills/llms.txt

Fetches trending financial news from multiple sources with optional content extraction and database persistence.

```APIDOC
## NewsNowTools - Real-time Hot News Fetching

### Description
Fetches trending financial news from multiple sources with 5-minute caching, content extraction via Jina Reader, and automatic database persistence.

### Method
```python
news_tools.fetch_hot_news(source_id: str, count: int = 10, fetch_content: bool = False)
```

### Parameters
#### Query Parameters
- **source_id** (str) - Required - The ID of the news source (e.g., "cls", "wallstreetcn", "weibo").
- **count** (int) - Optional - The number of news items to fetch. Defaults to 10.
- **fetch_content** (bool) - Optional - Whether to fetch the full content of the news articles. Defaults to False.

### Method
```python
news_tools.fetch_news_content(url: str)
```

### Parameters
#### Query Parameters
- **url** (str) - Required - The URL of the news article to fetch content from.

### Request Example
```python
from scripts.news_tools import NewsNowTools
from scripts.database_manager import DatabaseManager

db = DatabaseManager("data/signal_flux.db")
news_tools = NewsNowTools(db)

# Fetch top 15 news from Cailian (财联社)
news = news_tools.fetch_hot_news(source_id="cls", count=15, fetch_content=False)
for item in news[:3]:
    print(f"[{item['rank']}] {item['title']}")
    print(f"    URL: {item['url']}")
    print(f"    Published: {item['publish_time']}")

# Fetch with full content extraction
news_with_content = news_tools.fetch_hot_news("wallstreetcn", count=5, fetch_content=True)
print(news_with_content[0]['content'][:200])  # Markdown content from Jina

# Fetch specific URL content
content = news_tools.fetch_news_content("https://www.cls.cn/detail/1234567")
print(content)  # Returns Markdown formatted article
```

### Response
#### Success Response (200)
- **news** (list) - A list of news items, each containing 'rank', 'title', 'url', and 'publish_time'. If fetch_content is True, each item also includes 'content'.
- **content** (str) - Markdown formatted content of the article if fetch_news_content is used.

#### Response Example
```json
[
  {
    "rank": 1,
    "title": "央行宣布降准50个基点",
    "url": "https://www.cls.cn/detail/1234567",
    "publish_time": "2024-01-15 09:30:00",
    "content": "# 央行宣布降准..."
  }
]
```
```

--------------------------------

### Proxy Configuration for US Stocks

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-stock/SKILL.md

Instructions on how to configure proxy settings for accessing US stock data via yfinance if direct network access is restricted.

```APIDOC
## Proxy Configuration

For accessing US stock data through `yfinance`, you might need to configure proxy settings if your network environment restricts direct access to Yahoo Finance.

### Environment Variables
Set the following environment variables in your terminal:

```bash
export HTTP_PROXY="http://<proxy_ip>:<port>"
export HTTPS_PROXY="http://<proxy_ip>:<port>"
```

Replace `<proxy_ip>` and `<port>` with your actual proxy server IP address and port number.
```

--------------------------------

### Supported News Sources

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-news/references/sources.md

A list of supported news sources with their IDs, names, categories, and descriptions.

```APIDOC
## Supported News Sources

This section lists the news sources available for fetching financial and general news.

### News Sources Table

| Source ID | Name | Category | Description |
|:----------|:-----|:---------|:------------|
| `cls` | 财联社 | Finance | Real-time financial news, focus on A-shares and macro. |
| `wallstreetcn` | 华尔街见闻 | Finance | Global markets, macroeconomics, and detailed analysis. |
| `xueqiu` | 雪球热榜 | Finance | Community-driven stock discussions and hot topics. |
| `weibo` | 微博热搜 | General | Trending social topics, good for public sentiment. |
| `zhihu` | 知乎热榜 | General | In-depth discussions and Q&A on trending topics. |
| `baidu` | 百度热搜 | General | General public search trends. |
| `toutiao` | 今日头条 | General | Algorithmic news recommendations. |
| `douyin` | 抖音热榜 | General | Short video trends (titles only). |
| `thepaper` | 澎湃新闻 | General | Serious journalism and current affairs. |
| `36kr` | 36氪 | Tech | Startup, venture capital, and tech industry news. |
| `ithome` | IT之家 | Tech | Consumer electronics and tech gadgets. |
| `v2ex` | V2EX | Tech | Developer community trends. |
| `juejin` | 掘金 | Tech | Developer blogs and tutorials. |
| `hackernews` | Hacker News | Tech | Global tech and startup news (English). |
```

--------------------------------

### Generate Unified Trends Report with NewsNowTools

Source: https://context7.com/rkiding/awesome-finance-skills/llms.txt

Use the `get_unified_trends` method from NewsNowTools to aggregate top news from multiple specified sources into a single Markdown-formatted report. Requires initialization with a DatabaseManager.

```python
from scripts.news_tools import NewsNowTools
from scripts.database_manager import DatabaseManager

db = DatabaseManager()
news_tools = NewsNowTools(db)

# Generate unified report from multiple sources
report = news_tools.get_unified_trends(sources=["weibo", "zhihu", "wallstreetcn"])
print(report)
```

--------------------------------

### Fetch Hot News with NewsNowTools

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-news/SKILL.md

Use this function to fetch a specified number of hot news articles from a given source. Ensure you consult sources.md for valid source IDs.

```python
news_tools.fetch_hot_news(source_id, count)
```

--------------------------------

### Retrieve Historical Stock Price Data with StockTools

Source: https://context7.com/rkiding/awesome-finance-skills/llms.txt

Fetch historical OHLCV data for stocks using `get_stock_price`. This method includes intelligent caching and falls back to multiple data sources. It supports specifying date ranges and forcing a network refresh.

```python
from scripts.stock_tools import StockTools
from scripts.database_manager import DatabaseManager

db = DatabaseManager()
stock_tools = StockTools(db)

# Get 90 days of price data (default)
df = stock_tools.get_stock_price("600519")
print(df.tail())

# Output:
#          date     open    close     high      low      volume  change_pct
# 85 2024-01-10  1750.00  1768.50  1775.00  1745.00   2345678.0        1.05
# 86 2024-01-11  1770.00  1755.20  1772.00  1750.00   2123456.0       -0.75
# 87 2024-01-12  1756.00  1780.00  1785.00  1752.00   2567890.0        1.41
# 88 2024-01-14  1782.00  1795.50  1800.00  1778.00   2890123.0        0.87
# 89 2024-01-15  1796.00  1788.30  1802.00  1785.00   2345678.0       -0.40

# Get specific date range
df = stock_tools.get_stock_price(
    ticker="600519",
    start_date="2023-06-01",
    end_date="2023-12-31"
)
print(f"Retrieved {len(df)} trading days")

# Force refresh from network (bypass cache)
df = stock_tools.get_stock_price("600519", force_sync=True)

# Hong Kong stocks (5-digit codes)
df_hk = stock_tools.get_stock_price("00700")  # Tencent
print(df_hk.tail(3))

# US stocks (alphabetic tickers via yfinance)
df_us = stock_tools.get_stock_price("AAPL")
print(df_us.tail(3))
```

--------------------------------

### Generate Transmission Graph with Pyecharts

Source: https://context7.com/rkiding/awesome-finance-skills/llms.txt

Generates a transmission graph from node data and saves it as an HTML file. Requires VisualizerTools to be available.

```python
nodes = [
    {"node_name": "央行降准", "impact_type": "利好", "logic": "释放流动性"},
    {"node_name": "银行成本下降", "impact_type": "利好", "logic": "负债端成本降低"},
    {"node_name": "信贷扩张", "impact_type": "利好", "logic": "放贷意愿增强"},
    {"node_name": "股市流动性", "impact_type": "利好", "logic": "资金入市"}
]
graph = VisualizerTools.generate_transmission_graph(nodes, title="货币政策传导链")
VisualizerTools.render_chart_to_file(graph, "output/transmission_chain.html")
```

--------------------------------

### DatabaseManager - Core Data Persistence

Source: https://context7.com/rkiding/awesome-finance-skills/llms.txt

Manages SQLite database operations for news, stock prices, and analysis results. Initializes the database schema automatically. Ensure to close the connection when done.

```python
from scripts.database_manager import DatabaseManager

# Initialize (creates database if not exists)
db = DatabaseManager("data/signal_flux.db")

# Save news items
news_list = [
    {
        "id": "cls_1_2024-01-15",
        "source": "cls",
        "rank": 1,
        "title": "央行降准50个基点",
        "url": "https://www.cls.cn/detail/123",
        "content": "Full article content...",
        "publish_time": "2024-01-15 09:00:00",
        "sentiment_score": 0.72,
        "meta_data": {"category": "policy"}
    }
]
count = db.save_daily_news(news_list)
print(f"Saved {count} news items")

# Retrieve recent news
recent_news = db.get_daily_news(source="cls", limit=10, days=1)
for news in recent_news:
    print(f"[{news['source']}] {news['title']} (Sentiment: {news['sentiment_score']})")

# Update news content/analysis
db.update_news_content(
    news_id="cls_1_2024-01-15",
    content="Updated full content...",
    analysis="Bullish signal for banking sector"
)

# Delete news
db.delete_news("cls_1_2024-01-15")

# Clean up
db.close()
```

--------------------------------

### Prediction Markets Summary

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-news/SKILL.md

Fetches a summary of active prediction markets.

```APIDOC
## Prediction Markets Summary

### Description
Retrieves a formatted report of active prediction markets from Polymarket.

### Method
GET

### Endpoint
/get_market_summary

### Parameters
#### Query Parameters
- **limit** (integer) - Optional - The maximum number of markets to return. If not specified, a default limit is applied.

### Request Example
```json
{
  "limit": 5
}
```

### Response
#### Success Response (200)
- **market_summary** (array) - A list of active prediction markets, each with details like title, current odds, and end date.

#### Response Example
```json
{
  "market_summary": [
    {
      "title": "Will BTC reach $50k next month?",
      "odds": "65%",
      "end_date": "2023-12-31"
    }
  ]
}
```
```

--------------------------------

### NewsNowTools - Unified Trends Report

Source: https://context7.com/rkiding/awesome-finance-skills/llms.txt

Aggregates top news from multiple sources into a formatted Markdown report.

```APIDOC
## NewsNowTools - Unified Trends Report

### Description
Aggregates top news from multiple sources into a formatted Markdown report.

### Method
```python
news_tools.get_unified_trends(sources: list[str])
```

### Parameters
#### Query Parameters
- **sources** (list[str]) - Required - A list of news source IDs to include in the report (e.g., ["weibo", "zhihu", "wallstreetcn"]).

### Request Example
```python
from scripts.news_tools import NewsNowTools
from scripts.database_manager import DatabaseManager

db = DatabaseManager()
news_tools = NewsNowTools(db)

# Generate unified report from multiple sources
report = news_tools.get_unified_trends(sources=["weibo", "zhihu", "wallstreetcn"])
print(report)
```

### Response
#### Success Response (200)
- **report** (str) - A Markdown formatted string containing the aggregated news trends.

#### Response Example
```markdown
# 实时全网热点汇总 (2024-01-15 14:30)

### 🔥 微博热搜
- 央行降准释放流动性 ([链接](https://weibo.com/...))
- 新能源汽车销量破纪录 ([链接](https://weibo.com/...))
...

### 🔥 知乎热榜
- 如何看待最新经济数据 ([链接](https://zhihu.com/...))
...

### 🔥 华尔街见闻
- 美联储会议纪要解读 ([链接](https://wallstreetcn.com/...))
...
```
```

--------------------------------

### Stock Search and Ticker Lookup with StockTools

Source: https://context7.com/rkiding/awesome-finance-skills/llms.txt

Use StockTools to perform fuzzy searches for A-Share, Hong Kong, and US stock tickers. It supports Chinese and English names, common aliases, and automatically cleans ticker suffixes.

```python
from scripts.stock_tools import StockTools
from scripts.database_manager import DatabaseManager

db = DatabaseManager()
stock_tools = StockTools(db, auto_update=True)  # auto_update fetches stock list on first run

# Search by name (supports Chinese and English)
results = stock_tools.search_ticker("茅台", limit=5)
print(results)
# Output: [{'code': '600519', 'name': '贵州茅台'}]

# Search by ticker code
results = stock_tools.search_ticker("000001", limit=5)
print(results)
# Output: [{'code': '000001', 'name': '平安银行'}]

# Search using common aliases (CATL, BYD, Moutai, etc.)
results = stock_tools.search_ticker("CATL", limit=5)
print(results)
# Output: [{'code': '300750', 'name': '宁德时代'}]

# US stock tickers pass through directly
results = stock_tools.search_ticker("AAPL", limit=5)
print(results)
# Output: [{'code': 'AAPL', 'name': 'AAPL'}]

# Search with suffix (automatically cleaned)
results = stock_tools.search_ticker("600519.SH", limit=5)
print(results)
# Output: [{'code': '600519', 'name': '贵州茅台'}]
```

--------------------------------

### Analyze Sentiment (FinBERT / Local)

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-sentiment/SKILL.md

Performs high-speed, local sentiment analysis using the FinBERT model via the `sentiment_tools.py` script.

```APIDOC
## POST /analyze/sentiment/finbert

### Description
Analyzes the sentiment of a given financial text using a local FinBERT model.

### Method
POST

### Endpoint
/analyze/sentiment/finbert

### Parameters
#### Request Body
- **text** (string) - Required - The financial text to analyze.

### Request Example
{
  "text": "The stock market experienced a significant surge today."
}

### Response
#### Success Response (200)
- **score** (float) - The sentiment score ranging from -1.0 (Negative) to 1.0 (Positive).
- **label** (string) - The sentiment label (e.g., 'positive', 'negative', 'neutral').
- **reason** (string) - A brief explanation for the determined sentiment.

#### Response Example
{
  "score": 0.85,
  "label": "positive",
  "reason": "Positive market trends and investor confidence."
}
```

```APIDOC
## POST /batch/update/news/sentiment

### Description
Batch processes unanalyzed news in the database for sentiment analysis using the FinBERT model.

### Method
POST

### Endpoint
/batch/update/news/sentiment

### Parameters
#### Request Body
- **source** (string) - Required - The source of the news to process.
- **limit** (integer) - Optional - The maximum number of news items to process.

### Request Example
{
  "source": "financial_times",
  "limit": 100
}

### Response
#### Success Response (200)
- **message** (string) - Confirmation message indicating the batch update status.

#### Response Example
{
  "message": "Batch sentiment update completed for 100 news items."
}
```

--------------------------------

### Sentiment Analysis Prompt for LLM

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-sentiment/SKILL.md

Use this prompt when performing sentiment analysis via an LLM, especially when higher accuracy or reasoning is required. Ensure the LLM returns a JSON object with 'score', 'label', and 'reason'.

```markdown
请分析以下金融/新闻文本的情绪极性。
返回严格的 JSON 格式:
{"score": <float: -1.0到1.0>, "label": "<positive/negative/neutral>", "reason": "<简短理由>"}

文本: {text}
```

--------------------------------

### Analyze Sentiment with FinBERT

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-sentiment/SKILL.md

Use this method for high-speed, local sentiment analysis of financial text using a FinBERT model. It returns a sentiment score, label, and a brief reason.

```python
analyze_sentiment(text)
```

--------------------------------

### PolymarketTools - Prediction Market Data

Source: https://context7.com/rkiding/awesome-finance-skills/llms.txt

Retrieves active prediction market data from Polymarket.

```APIDOC
## PolymarketTools - Prediction Market Data

### Description
Retrieves active prediction market data from Polymarket, reflecting public sentiment and probability forecasts for major events.

### Method
```python
poly_tools.get_active_markets(limit: int = 10)
```

### Parameters
#### Query Parameters
- **limit** (int) - Optional - The maximum number of active markets to retrieve. Defaults to 10.

### Method
```python
poly_tools.get_market_summary(limit: int = 5)
```

### Parameters
#### Query Parameters
- **limit** (int) - Optional - The maximum number of market summaries to generate. Defaults to 5.

### Request Example
```python
from scripts.news_tools import PolymarketTools
from scripts.database_manager import DatabaseManager

db = DatabaseManager()
poly_tools = PolymarketTools(db)

# Get active prediction markets
markets = poly_tools.get_active_markets(limit=10)
for m in markets[:3]:
    print(f"Question: {m['question']}")
    print(f"  Outcomes: {m['outcomes']}")
    print(f"  Prices: {m['outcomePrices']}")
    print(f"  Volume: ${float(m['volume']):,.0f}")

# Get formatted summary report
summary = poly_tools.get_market_summary(limit=5)
print(summary)
```

### Response
#### Success Response (200)
- **markets** (list) - A list of active prediction markets, each containing 'question', 'outcomes', 'outcomePrices', and 'volume'.
- **summary** (str) - A Markdown formatted string summarizing the top prediction markets.

#### Response Example
```json
[
  {
    "question": "Will the Fed cut rates in March 2024?",
    "outcomes": ["Yes", "No"],
    "outcomePrices": ["0.35", "0.65"],
    "volume": "2500000"
  }
]
```

```markdown
# 🔮 Polymarket 热门预测 (2024-01-15 14:30)

**1. Will the Fed cut rates in March 2024?**
   概率: ['0.35', '0.65']
   交易量: $2,500,000
...
```
```

--------------------------------

### Fetch Prediction Market Summary

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-news/SKILL.md

Retrieves a formatted report of currently active prediction markets. This function is part of the PolymarketTools utility.

```python
polymarket_tools.get_market_summary(limit)
```

--------------------------------

### Markdown for DOCX Processing

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/skill-creator/SKILL.md

This markdown snippet illustrates conditional details for DOCX processing, linking to advanced topics like redlining and OOXML.

```markdown
# DOCX Processing

## Creating documents

Use docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md).

## Editing documents

For simple edits, modify the XML directly.

**For tracked changes**: See [REDLINING.md](REDLINING.md)
**For OOXML details**: See [OOXML.md](OOXML.md)
```

--------------------------------

### Polymarket API

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-news/references/sources.md

Information about the Polymarket API for accessing prediction markets.

```APIDOC
## Polymarket API

### Base URL
`https://gamma-api.polymarket.com`

### Data
Provides access to prediction markets, such as "Will Fed cut rates?".

### Endpoint: Get Active Markets

#### Description
Retrieves the top active prediction markets by trading volume.

### Method
GET

### Endpoint
`/markets/active`

### Query Parameters
None specified.

### Request Example
(No request body for GET request)

### Response
#### Success Response (200)
- **markets** (array) - A list of active markets.
  - **market_id** (string) - Unique identifier for the market.
  - **question** (string) - The question posed by the prediction market.
  - **volume** (number) - The current trading volume for the market.

#### Response Example
```json
{
  "markets": [
    {
      "market_id": "fed-rate-cut-q3-2024",
      "question": "Will the Federal Reserve cut interest rates in Q3 2024?",
      "volume": 1500000.50
    },
    {
      "market_id": "election-winner-2024",
      "question": "Who will win the 2024 US Presidential Election?",
      "volume": 1200000.75
    }
  ]
}
```
```

--------------------------------

### Web Search API

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-search/SKILL.md

Perform finance web searches using various engines like Jina, DDG, and Baidu. Includes options for smart caching and aggregating results.

```APIDOC
## Web Search

### Description
Performs finance web searches using specified engines.

### Method
`search(query, engine, max_results)`

### Parameters
#### Query Parameters
- **query** (string) - Required - The search query.
- **engine** (string) - Required - The search engine to use (e.g., `jina`, `ddg`, `baidu`, `local`).
- **max_results** (integer) - Optional - The maximum number of results to return.

### Response
#### Success Response (200)
- **summary** (string) - A summary of the search results.
- **results** (List[Dict]) - A list of detailed search results.

### Method
`aggregate_search(query)`

### Description
Combines search results from multiple web engines.

### Parameters
#### Query Parameters
- **query** (string) - Required - The search query.

### Response
#### Success Response (200)
- **combined_results** (List[Dict]) - Aggregated search results from multiple engines.
```

--------------------------------

### Local RAG Search API

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-search/SKILL.md

Searches a local 'daily_news' database using Retrieval Augmented Generation (RAG).

```APIDOC
## Local RAG Search

### Description
Searches the local 'daily_news' database for relevant financial information.

### Method
`search(query, engine='local')`

### Parameters
#### Query Parameters
- **query** (string) - Required - The search query.
- **engine** (string) - Required - Must be set to `local` for RAG search.

### Response
#### Success Response (200)
- **results** (List[Dict]) - A list of relevant documents from the local database.
```

--------------------------------

### Unified Trends Report

Source: https://github.com/rkiding/awesome-finance-skills/blob/main/skills/alphaear-news/SKILL.md

Aggregates and unifies top news trends from multiple sources.

```APIDOC
## Unified Trends Report

### Description
Aggregates top news from multiple specified sources to provide a unified trend report.

### Method
POST

### Endpoint
/get_unified_trends

### Parameters
#### Request Body
- **sources** (array of strings) - Required - A list of source IDs to aggregate trends from (e.g., ['weibo', 'zhihu', 'wallstreetcn']).

### Request Example
```json
{
  "sources": ["weibo", "zhihu"]
}
```

### Response
#### Success Response (200)
- **trends** (array) - A list of unified trend reports, each containing aggregated news items.

#### Response Example
```json
{
  "trends": [
    {
      "source": "Unified",
      "title": "Top Trend Example",
      "summary": "Summary of the aggregated trend."
    }
  ]
}
```
```

--------------------------------

### Financial Text Sentiment Analysis with SentimentTools

Source: https://context7.com/rkiding/awesome-finance-skills/llms.txt

Perform sentiment analysis on financial texts using FinBERT for local inference. The `analyze_sentiment` method returns a score from -1.0 (negative) to 1.0 (positive) and a sentiment label.

```python
from scripts.sentiment_tools import SentimentTools
from scripts.database_manager import DatabaseManager

db = DatabaseManager()

# Initialize with BERT mode (default)
sentiment_tools = SentimentTools(db, mode="bert")

# Analyze single text
result = sentiment_tools.analyze_sentiment("央行宣布降准，释放长期资金约1万亿元")
print(result)

# Output:
# {
#     'score': 0.72,
#     'label': 'positive',
#     'reason': 'BERT automated analysis'
# }

# Negative sentiment example
result = sentiment_tools.analyze_sentiment("公司业绩大幅下滑，股价暴跌10%")
print(result)

# Output:
# {
#     'score': -0.85,
#     'label': 'negative',
#     'reason': 'BERT automated analysis'
# }
```