China Stock Analysis Skill

A Chinese A-share analysis tool based on value investment theory, targeting ordinary investors with low-frequency trading.

When to Use

Call this skill when the user requests the following operations:

Analyze a specific A-share stock
Screen stocks that meet criteria
Compare multiple stocks or stocks within an industry
Calculate stock valuation or intrinsic value
Check the financial health of a stock
Detect financial anomaly risks

Prerequisites

Python Environment Requirements (venv is mandatory)

All script commands should be run in the project virtual environment.

bash

python3 -m venv .venv
source .venv/bin/activate

Install Dependencies:

bash

pip install tushare pandas numpy

Environment Bootstrap (Must be completed automatically before execution)

Before running any scripts, execute the following in the current project directory:

bash

cd <skill project directory>
if [ ! -d ".venv" ]; then
  python3 -m venv .venv
fi
source .venv/bin/activate
python3 -m pip install -U pip
python3 -m pip install tushare pandas numpy

Notes:

```
.venv
```
must be located in the root directory of the skill project (not a global directory)
If
```
import tushare
```
fails, the above bootstrap must be executed first before proceeding with subsequent analysis processes

TUSHARE_TOKEN

BRAVE_API_KEY

are recommended to be stored in

~/.aj-skills/.env

, and loaded into the current shell before execution:

bash

set -a
source ~/.aj-skills/.env
set +a

Notes:

The script will not automatically read
```
~/.aj-skills/.env
```

Must be explicitly passed via CLI parameters:

--token "${TUSHARE_TOKEN}"

--brave-api-key "${BRAVE_API_KEY}"

Pre-execution Parameter Check (using

test

command):

bash

test -n "${TUSHARE_TOKEN}" || { echo "Missing TUSHARE_TOKEN"; exit 1; }
# Check only when using Brave news source
test -n "${BRAVE_API_KEY}" || { echo "Missing BRAVE_API_KEY (required when news-provider=brave)"; exit 1; }

Dependency Check

Before performing any analysis, check if tushare is installed:

bash

python3 -c "import tushare; print(tushare.__version__)"

Core Modules

1. Stock Screener

Screen stocks that meet criteria

2. Financial Analyzer

In-depth financial analysis of individual stocks

3. Industry Comparator

Horizontal comparison analysis within the same industry

4. Valuation Calculator

Intrinsic value measurement and margin of safety calculation

5. News & Sentiment

Capture recent public news and generate sentiment risk assessment

Workflow 1: Stock Screening

Used when the user requests stock screening.

Step 1: Collect Screening Criteria

Ask the user for screening criteria. Provide the following options for selection or customization:

Valuation Metrics:

PE (Price-to-Earnings Ratio): e.g., PE < 15
PB (Price-to-Book Ratio): e.g., PB < 2
PS (Price-to-Sales Ratio): e.g., PS < 3

Profitability:

ROE (Return on Equity): e.g., ROE > 15%
ROA (Return on Assets): e.g., ROA > 8%
Gross Profit Margin: e.g., > 30%
Net Profit Margin: e.g., > 10%

Growth:

Revenue Growth Rate: e.g., > 10%
Net Profit Growth Rate: e.g., > 15%
Consecutive Growth Years: e.g., >= 3 years

Dividends:

Dividend Yield: e.g., > 3%
Consecutive Dividend Years: e.g., >= 5 years

Financial Safety:

Asset-Liability Ratio: e.g., < 60%
Current Ratio: e.g., > 1.5
Quick Ratio: e.g., > 1

Screening Scope:

All A-shares
CSI 300 Constituents
CSI 500 Constituents
ChiNext/STAR Market
User-defined list

Step 2: Execute Screening

bash

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

Parameter Explanation:

```
--scope
```
: Screening scope (all/hs300/zz500/cyb/kcb/custom:600519,000858,...)
```
--pe-max/--pe-min
```
: PE range
```
--pb-max/--pb-min
```
: PB range
```
--roe-min
```
: Minimum ROE
```
--growth-min
```
: Minimum growth rate
```
--debt-ratio-max
```
: Maximum asset-liability ratio
```
--dividend-min
```
: Minimum dividend yield
```
--token
```
: tushare token (required)
```
--format
```
: Output format (json/table)
```
--quiet
```
: Silent mode
```
--output
```
: Output file path

Step 3: Present Results

Read

screening_result.json

and present to the user in table format:

Code	Name	PE	PB	ROE	Dividend Yield	Score
600519	Kweichow Moutai	25.3	8.5	30.2%	2.1%	85

Workflow 2: Stock Analysis

Used when the user requests analysis of a specific stock.

Step 1: Collect Stock Information

Ask the user:

Stock code or name
Analysis depth level:
- Summary Level: Key indicators + investment conclusion (1 page)
- Standard Level: Financial analysis + valuation + industry comparison + risk warning
- In-depth Level: Complete research report including historical data tracking

Step 1.5: Prepare Output Directory

When analyzing a single stock, the skill needs to automatically create an output directory with the naming rule:

```
${stock_name}_${stock_code}
```

Example:

bash

stock_dir="Kweichow Moutai_600519"
mkdir -p "${stock_dir}"

Step 2: Fetch Stock Data

Recommended to use "module-wise fetch + aggregation" process (CLI decoupling):

bash

mkdir -p "${stock_dir}/data"

# 1) Basic Information
python scripts/fetch_basic.py \\
  --code "600519" \\
  --token "${TUSHARE_TOKEN}" \\
  --output "${stock_dir}/data/basic.json"

# 2) Financial Data
python scripts/fetch_financial.py \\
  --code "600519" \\
  --token "${TUSHARE_TOKEN}" \\
  --years 5 \\
  --output "${stock_dir}/data/financial.json"

# 3) Valuation & Market Data
python scripts/fetch_valuation.py \\
  --code "600519" \\
  --token "${TUSHARE_TOKEN}" \\
  --output "${stock_dir}/data/valuation.json"
python scripts/fetch_price.py \\
  --code "600519" \\
  --token "${TUSHARE_TOKEN}" \\
  --days 180 \\
  --output "${stock_dir}/data/price.json"

# 4) News & Sentiment
python scripts/fetch_news_data.py \\
  --code "600519" \\
  --name "Kweichow Moutai" \\
  --days 7 \\
  --limit 20 \\
  --provider brave \\
  --brave-api-key "${BRAVE_API_KEY}" \\
  --output "${stock_dir}/data/news.json"

# 5) Real-time & Event Window
python scripts/fetch_realtime.py \\
  --code "600519" \\
  --token "${TUSHARE_TOKEN}" \\
  --benchmark hs300 \\
  --window 60 \\
  --output "${stock_dir}/data/realtime.json"
python scripts/fetch_event_window.py \\
  --code "600519" \\
  --token "${TUSHARE_TOKEN}" \\
  --name "Kweichow Moutai" \\
  --benchmark hs300 \\
  --pre-days 1 \\
  --post-days 1,3,5 \\
  --provider brave \\
  --brave-api-key "${BRAVE_API_KEY}" \\
  --output "${stock_dir}/data/event_window.json"

# 6) Aggregate into Analysis Input
python scripts/assemble_data.py \\
  --input-dir "${stock_dir}/data" \\
  --output "${stock_dir}/stock_data.json"

Compatibility mode (single command fetch) is retained as follows:

bash

python scripts/data_fetcher.py \\
    --code "600519" \\
    --token "${TUSHARE_TOKEN}" \\
    --data-type all \\
    --with-news \\
    --news-provider brave \\
    --brave-api-key "${BRAVE_API_KEY}" \\
    --with-realtime \\
    --with-event-window \\
    --benchmark hs300 \\
    --realtime-window 60 \\
    --event-window-pre 1 \\
    --event-window-post 1,3,5 \\
    --news-days 7 \\
    --news-limit 20 \\
    --years 5 \\
    --output "${stock_dir}/stock_data.json"

Parameter Explanation:

```
--code
```
: Stock code
```
--data-type
```
: Data type (basic/financial/valuation/holder/news/all)
```
--years
```
: Number of years of historical data to fetch
```
--token
```
: tushare token (required)
```
--with-news
```
: Attach news and sentiment data
```
--news-days
```
: News window days
```
--news-limit
```
: Maximum number of news items
```
--news-sources
```
: News source filter (comma-separated)
```
--news-provider
```
: News source (auto/brave/tushare/rss)
```
--brave-api-key
```
: Brave Search API Key (required when
```
news-provider=brave
```
)
```
--with-realtime
```
: Attach real-time indicators (trend/confirmation/risk/筹码)
```
--with-event-window
```
: Attach event window analysis (1/3/5-day reaction after events)
```
--benchmark
```
: Relative strength benchmark index (hs300/zz500/zz1000/cyb/kcb)
```
--realtime-window
```
: Real-time indicator calculation window (days)
```
--event-window-pre
```
: Event window pre-days
```
--event-window-post
```
: Event window post-days (comma-separated)
```
--cache-ttl-min
```
: Cache validity period (minutes)
```
--format
```
: Output format (json/table)
```
--quiet
```
: Silent mode
```
--output
```
: Output file

Optional: Execute News & Sentiment Process Separately

bash

python scripts/news_fetcher.py --code 600519 --name Kweichow Moutai --token "${TUSHARE_TOKEN}" --days 7 --limit 20 --provider brave --brave-api-key "${BRAVE_API_KEY}" --output "${stock_dir}/news.json"
python scripts/sentiment_analyzer.py --input "${stock_dir}/news.json" --output "${stock_dir}/sentiment.json"

Step 3: Run Financial Analysis

bash

python scripts/financial_analyzer.py \\
    --input "${stock_dir}/stock_data.json" \\
    --level standard \\
    --output "${stock_dir}/analysis_result.json"

Or directly read module-wise directory (auto-aggregation):

bash

python scripts/financial_analyzer.py \\
    --input-dir "${stock_dir}/data" \\
    --level standard \\
    --output "${stock_dir}/analysis_result.json"

Parameter Explanation:

```
--input
```
: Input stock data file
```
--input-dir
```
: Module-wise directory (auto-read and aggregate into analysis input)
```
--level
```
: Analysis depth (summary/standard/deep)
```
--output
```
: Output file

Step 4: Calculate Valuation

bash

python scripts/valuation_calculator.py \\
    --input "${stock_dir}/stock_data.json" \\
    --methods dcf,ddm,relative \\
    --discount-rate 10 \\
    --growth-rate 8 \\
    --output "${stock_dir}/valuation_result.json"

Parameter Explanation:

```
--input
```
: Stock data file
```
--methods
```
: Valuation methods (dcf/ddm/relative/all)
```
--discount-rate
```
: Discount rate (%)
```
--terminal-growth
```
: Perpetual growth rate (%)
```
--growth-rate
```
: Compatible alias for perpetual growth rate (%)
```
--margin-of-safety
```
: Margin of safety (%)
```
--format
```
: Output format (json/table)
```
--quiet
```
: Silent mode
```
--output
```
: Output file

Step 5: Generate Report

Read analysis results and generate a Chinese analysis report referring to the

templates/analysis_report.md

template.

Mandatory Inspection Items for Report Generation (All must be satisfied): 0. The final report must be saved as a Markdown file (

.md

)

Must include the "News & Sentiment" chapter

Must use

news_sentiment/news_items

from

stock_data.json

to fill corresponding fields

If news fetching fails, clearly state the failure reason in the report (from
```
news_sentiment.error
```
)
Must not omit the
```
summary_title
```
and "Performance & Audit Signals" chapters in the template
If
```
stock_data.json
```
contains
```
realtime_metrics
```
, the report must include the "Real-time Indicator Dashboard" chapter (trend/confirmation/risk/筹码)
If
```
stock_data.json
```
contains
```
event_window
```
, the report must include "Event Window Reaction" content (number of events, 1/3/5-day returns after events, 1/3/5-day excess returns after events)
If
```
realtime_metrics
```
exists, the comprehensive score must adopt 40% Financial + 60% Real-time (real-time priority)

Report Structure (Standard Level):

Company Overview: Basic information, main business
Financial Health: Balance sheet analysis
Profitability: DuPont analysis, profit margin trends
Growth Analysis: Revenue/profit growth trends
Real-time Indicator Dashboard: Trend/confirmation/risk/筹码
Event Window Analysis: Post-event returns and excess returns
Valuation Analysis: DCF/DDM/Relative Valuation
Risk Warning: Financial anomaly detection, shareholder reduction
Investment Conclusion: Comprehensive score, operation suggestions (real-time priority)

Report Title Specification:

summary_title

uses the format:

Stock Name(Stock Code): Summary Conclusion

Example:

Kweichow Moutai(600519): Financially Stable, Valuation and Risk Matching is Good

Output File:

${stock_dir}/final_report.md

Step 6: Humanize Output

Read

${stock_dir}/final_report.md

and call the

humanizer-zh

skill for polishing and optimization.

Output File:

${stock_dir}/final_report_humanized.md

Workflow 3: Industry Comparison

CLI Method (Sector Analysis, Recommended)

bash

# 1) Fetch Sector Data
python scripts/sector_fetcher.py \\
  --sector-name "Computing Power Sector" \\
  --token "${TUSHARE_TOKEN}" \\
  --sector-file config/sector_computing_default.json \\
  --output "${stock_dir}/sector_data.json"

# 2) Generate Sector Analysis Results + Markdown Report
python scripts/sector_analyze.py \\
  --input "${stock_dir}/sector_data.json" \\
  --output "${stock_dir}/sector_analysis.json"

Step 1: Collect Comparison Targets

Ask the user:

Target stock codes (multiple allowed)
Or: Industry classification + number of comparisons

Step 2: Fetch Industry Data

bash

python scripts/data_fetcher.py \\
    --codes "600519,000858,002304" \\
    --token "${TUSHARE_TOKEN}" \\
    --data-type comparison \\
    --output industry_data.json

Or fetch by industry:

bash

python scripts/data_fetcher.py \\
    --industry "Liquor" \\
    --token "${TUSHARE_TOKEN}" \\
    --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

Indicator	Kweichow Moutai	Wuliangye	Yanghe Co., Ltd.	Industry Average
PE	25.3	18.2	15.6	22.4
ROE	30.2%	22.5%	20.1%	18.5%
Gross Profit Margin	91.5%	75.2%	72.3%	65.4%
Score	85	78	75	-

Workflow 4: Valuation Calculator

Step 1: Collect Valuation Parameters

Ask the user for valuation parameters (or use default values):

DCF Model Parameters:

Discount Rate (WACC): Default 10%
Forecast Period: Default 5 years
Perpetual Growth Rate: Default 3%

DDM Model Parameters:

Required Rate of Return: Default 10%
Dividend Growth Rate: Derived from historical data

Relative Valuation Parameters:

Comparison Benchmark: Industry average / Historical average

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

Valuation Method	Intrinsic Value	Current Price	Margin of Safety Price	Conclusion
DCF	¥2,150	¥1,680	¥1,505	Undervalued
DDM	¥1,980	¥1,680	¥1,386	Undervalued
Relative Valuation	¥1,850	¥1,680	¥1,295	Reasonable

Financial Anomaly Detection

Automatically detect the following anomaly signals during analysis:

Detection Items

Abnormal Accounts Receivable
- Accounts receivable growth rate > Revenue growth rate × 1.5
- Significant increase in accounts receivable turnover days
Cash Flow Divergence
- Sustained net profit growth but declining operating cash flow
- Cash-to-income ratio < 80%
Abnormal Inventory
- Inventory growth rate > Revenue growth rate × 2
- Significant increase in inventory turnover days
Abnormal Gross Profit Margin
- Gross profit margin volatility > Industry average volatility × 2
- Severe deviation from peers' gross profit margin
Related Party Transactions
- High proportion of related party transactions (> 30%)
Shareholder Reduction
- Recent reduction announcements by major shareholders
- Concentrated reduction by executives

Risk Levels

🟢 Low Risk: No obvious anomalies
🟡 Medium Risk: 1-2 minor anomalies
🔴 High Risk: Multiple anomalies or severe anomalies

A-Share Specific Analysis

Policy Sensitivity

Provide policy-related prompts based on industry classification:

Real Estate: "Houses are for living, not for speculation" policy
New Energy: Changes in subsidy policies
Pharmaceuticals: Impact of volume-based procurement policies
Internet: Anti-monopoly, data security

Shareholder Structure Analysis

Controlling shareholder type (SOE/Private Enterprise/Foreign Capital)
Ownership concentration
Recent increase/reduction situations
Pledge ratio

Output Format

JSON/Table Output Format

Default
```
json
```
Optional
```
--format table
```
for quick terminal viewing
Use
```
--quiet
```
to disable process logs

All scripts output JSON format for easy subsequent processing:

json

{
  "code": "600519",
  "name": "Kweichow Moutai",
  "analysis_date": "2025-01-25",
  "level": "standard",
  "summary": {
    "score": 85,
    "conclusion": "Undervalued",
    "recommendation": "Recommended to pay attention"
  },
  "financials": { ... },
  "valuation": { ... },
  "risks": [ ... ]
}

Markdown Report

Generate structured Chinese Markdown report, referring to

templates/analysis_report.md

Data Contract

Core data structures are constrained by

scripts/data_contract.py

. Analysis scripts will verify before running:

Required top-level fields:
```
code/fetch_time/data_type/basic_info
```

Common optional fields:

financial_data/financial_indicators/valuation/price/holder/dividend

News-related fields:
```
news_items/news_sentiment
```

Performance audit fields:

performance_data

(including

forecast/express/audit/main_business

)

Report field requirements:

```
financial_data.balance_sheet
```
must be an array
```
financial_data.income_statement
```
must be an array
```
financial_data.cash_flow
```
must be an array

Field Mapping (Akshare -> Tushare)

Compatible Semantics	Current Field (Recommended)	Compatible Aliases/Source
PE(TTM)	`valuation.latest.pe_ttm`	`valuation.latest.pe`
PB	`valuation.latest.pb`	-
Net Profit	`financial_data.income_statement[].净利润`	`n_income`
Net Operating Cash Flow	`financial_data.cash_flow[].经营活动产生的现金流量净额`	`n_cashflow_act`
Capital Expenditure Cash	`financial_data.cash_flow[].购建固定资产、无形资产和其他长期资产支付的现金`	`c_pay_acq_const_fiolta`
ROE	`financial_indicators[].净资产收益率`	`roe`
Asset-Liability Ratio	`financial_indicators[].资产负债率`	`debt_to_assets`

Error Handling

Network Errors

If tushare data fetching fails, prompt the user:

Check network connection
Retry later (may be interface rate limiting)
Try switching data sources

Invalid Stock Code

Prompt the user to check if the stock code is correct, and provide possible matching suggestions.

Incomplete Data

For newly listed stocks or those with incomplete financial data, explain the data limitations and perform analysis based on available data.

Best Practices

Data Timeliness: Financial data is based on the latest quarterly/annual report, price data is the closing price of the day; when
```
--with-realtime
```
/
```
--with-event-window
```
is enabled, supplement dynamic indicators of trends and event impacts
Investment Advice: All analysis is for reference only and does not constitute investment advice
Risk Warning: Always include risk warnings, especially the results of financial anomaly detection
Comparison Analysis: When analyzing a single stock, automatically include industry average comparison
Scoring Weight: Use
```
40% Financial + 60% Real-time
```
when real-time data exists; fallback to financial score when real-time data is missing

Important Notes

All analysis is based on public financial data and does not involve any insider information
Parameter assumptions of valuation models have a significant impact on results, which should be explained to users
The A-share market is greatly affected by policies, so quantitative analysis should be combined with qualitative judgments ",

aj-stock-analysis

NPX Install

Tags

SKILL.md Content (Chinese)

China Stock Analysis Skill

When to Use

Prerequisites

Python Environment Requirements (venv is mandatory)

Environment Bootstrap (Must be completed automatically before execution)

Dependency Check

Core Modules

1. Stock Screener

2. Financial Analyzer

3. Industry Comparator

4. Valuation Calculator

5. News & Sentiment

Workflow 1: Stock Screening

Step 1: Collect Screening Criteria

Step 2: Execute Screening

Step 3: Present Results

Workflow 2: Stock Analysis

Step 1: Collect Stock Information

Step 1.5: Prepare Output Directory

Step 2: Fetch Stock Data

Optional: Execute News & Sentiment Process Separately

Step 3: Run Financial Analysis

Step 4: Calculate Valuation

Step 5: Generate Report

Step 6: Humanize Output

Workflow 3: Industry Comparison

CLI Method (Sector Analysis, Recommended)

Step 1: Collect Comparison Targets

Step 2: Fetch Industry Data

Step 3: Generate Comparison

Step 4: Present Comparison Table

Workflow 4: Valuation Calculator

Step 1: Collect Valuation Parameters

Step 2: Run Valuation

Step 3: Present Valuation Results

Financial Anomaly Detection

Detection Items

Risk Levels

A-Share Specific Analysis

Policy Sensitivity

Shareholder Structure Analysis

Output Format

JSON/Table Output Format

Markdown Report

Data Contract

Field Mapping (Akshare -> Tushare)

Error Handling

Network Errors

Invalid Stock Code

Incomplete Data

Best Practices

Important Notes