financial-data-analysis

Original：🇨🇳 Chinese

Translated

3 scripts

Financial time series analysis method toolkit. Covers stocks / commodity futures / cryptocurrencies / ETFs / foreign exchange / indices, full process from data acquisition to high-level analysis. Built-in 70+ analysis methods, covering 8 major method domains: time series testing, predictive modeling, cross-asset relationships, volatility risk, portfolio optimization, state recognition, commodity-specific analysis and network analysis. Tushare MCP tool (A shares/Hong Kong stocks/US stocks/futures/funds/macro) is preferred for data acquisition, and yfinance scripts are used to supplement assets not covered by tushare such as commodity futures (CL=F) and crypto (BTC-USD).

2installs

Sourcekirkluokun/awesome-a-stock-openclawskills

Added on2026-03-29

NPX Install

npx skill4agent add kirkluokun/awesome-a-stock-openclawskills financial-data-analysis

SKILL.md Content (Chinese)

View Translation Comparison →

📊 Financial Time Series Analysis Toolkit

A comprehensive data analysis method toolkit covering stocks / commodity futures / cryptocurrencies / ETFs / foreign exchange / indices.

Data Acquisition Strategy

Asset Type	Data Source	Method
A-share market/finance/index	Tushare MCP	`tushare_daily` , `tushare_income` and other MCP tools
A-share futures	Tushare MCP	`tushare_fut_daily` , `tushare_fut_holding` etc.
Hong Kong stocks/US stocks	Tushare MCP	`tushare_hk_daily` , `tushare_us_daily`
Macroeconomics	Tushare MCP	`tushare_cn_gdp` , `tushare_shibor` etc.
International commodity futures (WTI/gold etc.)	yfinance	`scripts/data_fetcher.py`
Cryptocurrency	yfinance	`scripts/data_fetcher.py`
Foreign exchange	Tushare MCP or yfinance	Depending on specific currency
Global indices	Tushare MCP or yfinance	`tushare_index_global` / yfinance

Rule: You must first load with
ToolSearch("+tushare <keyword>")
before calling the tushare MCP tool. The full index of tushare tools can be found in
reference/tool-index.md
of the
stock-tushare-pro-mcp
skill.

Analysis Method Routing

According to user intent, read the corresponding

references/methods/

documentation before performing analysis:

User Intent Keywords	Reference Document	Available Scripts
Stationarity, trend test, series decomposition, structural break, Hurst	`references/methods/01_time_series_fundamentals.md`	`scripts/analysis_toolkit.py`
Price forecast, ARIMA, Prophet, VAR	`references/methods/02_forecasting.md`	`scripts/analysis_toolkit.py`
Correlation, cointegration, causality, lead-lag	`references/methods/03_cross_asset_relationships.md`	`scripts/analysis_toolkit.py`
Volatility, GARCH, VaR, tail risk	`references/methods/04_volatility_and_risk.md`	`scripts/analysis_toolkit.py`
Portfolio optimization, factor analysis, risk parity, efficient frontier	`references/methods/05_portfolio_and_factor.md`	`scripts/analysis_toolkit.py`
Market state, regime, cycle, wavelet	`references/methods/06_regime_and_structure.md`	`scripts/analysis_toolkit.py`
Commodity seasonality, spread, term structure, contango	`references/methods/07_commodity_specific.md`	`scripts/analysis_toolkit.py`
Network analysis, information flow, clustering, MST	`references/methods/08_network_and_information.md`	`scripts/analysis_toolkit.py`
Technical indicators (MA/RSI/MACD/KDJ/Bollinger Bands)	`references/methods/01_time_series_fundamentals.md`	`scripts/indicators.py`
Chart drawing, visualization	`references/visualization_cookbook.md`	—
Report format	`references/output_templates.md`	—

Execution Process

1. Identify user intent → Check the routing table above
2. Read the corresponding references/methods/ document → Select appropriate method
3. Acquire data: tushare MCP tool (priority) or scripts/data_fetcher.py
4. Perform analysis: scripts/analysis_toolkit.py or scripts/indicators.py
5. Generate charts: Refer to references/visualization_cookbook.md
6. Output report: Follow references/output_templates.md format

Constraints

MUST

Mark data acquisition time and source (tushare / yfinance)
Attach a disclaimer to each report
Check series stationarity before analysis (when applicable)
Outlier marking and processing

MUST NOT

❌ Give deterministic return commitments
❌ Forge or fabricate data
❌ Ignore risk warnings
❌ Guess key indicators when data is missing

Output Storage Specification

Output Directory

The default root directory is

{output_dir}

(configured by input-variables, default

{workspace}/data/analysis/

).

{output_dir}/
├── reports/        # Analysis reports (.md)
├── charts/         # Chart files (.png)
├── datasets/       # Intermediate datasets (.csv)
└── temp/           # Temporary data (can be cleaned up)

File Naming

{type}_{underlying}_{date}.{format}

Examples:

```
report_CU_20260306.md
```
```
chart_AAPL_seasonal_20260306.png
```
```
dataset_corr_matrix_20260306.csv
```

Output Rules

Data Volume	Processing Method
< 20 rows	Display directly in the conversation, no file storage
>= 20 rows	Store in `datasets/` , return file path + summary
Charts	Store in `charts/` , display embedded in the conversation
Analysis reports	Store in `reports/` , return full report
Temporary/intermediate data	Store in `temp/` , remind users it can be cleaned up

Collaboration with tushare skill: Original market data storage follows the
output-storage.md
specification of the tushare skill (
{workspace}/data/tushare/
), The
{output_dir}
of this skill only stores analysis results, not original data, to avoid duplication.

Parameter Usage

All configurable parameters are declared through

input-variables

, and AI obtains values according to the following priority when executing:

Explicitly specified by the user in the conversation -> Highest priority
```
default
```
value in
```
input-variables
```
-> Fallback

# User says "save the analysis results to ~/Desktop/analysis"
-> output_dir = ~/Desktop/analysis

# User says "analyze copper prices"
-> output_dir = {workspace}/data/analysis (use default value)
-> default_period = 1y (use default value)