Fund Screener

This is a quantitative fund screener for China's public mutual fund market that pulls live data through AkShare and filters by risk-adjusted metrics like Sharpe, Sortino, and Calmar ratios. It's built for comparing thousands of funds at once or doing deep dives on individual holdings, with preset modes for bond funds, balanced funds, and alpha strategies. The interesting part is the optional BrowserMCP integration that cross-checks AkShare data against Baidu for actual fund sizes and holdings, since AkShare apparently conflates manager-level and fund-level assets. Outputs to CSV. If you're analyzing Chinese funds and need more than just returns, this handles the quantitative screening piece and saves you from manually verifying discrepancies across data sources.

skills.sh installs: 294
GitHub stars: 6
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add sososun/mutual-fund-skills --skill fund-screener --agent claude-code

Installs into .claude/skills of the current project.

Files

基金分析技能 (Fund Screener)

通过 AkShare 获取中国公募基金实时数据，基于量化指标筛选优质基金产品。

功能

单基金深度分析: 对单只基金进行全方位诊断，包括风险指标、阶段收益、年度收益、资产配置、基金经理、持仓信息
全市场批量筛选: 从全市场开放式基金中智能筛选，支持多种模式
结果导出: 自动保存 CSV 文件

使用方法

运行此技能需要 Python 3.8+ 和依赖: pip install akshare pandas numpy

# 单基金分析
python fund_screener.py <基金代码> [基金名称]

# 纯债基金筛选（低风险）
python fund_screener.py --bond

# 固收+基金筛选
python fund_screener.py --gushou-plus

# 股票类基金筛选
python fund_screener.py --stock

# Alpha策略筛选（卡玛比率）
python fund_screener.py --stock-alpha

# 自定义参数
python fund_screener.py --bond --min-sharpe 1.0 --max-dd 2 --min-return 2.5
python fund_screener.py --gushou-plus --min-sortino 1.5
python fund_screener.py --stock-alpha --min-calmar 0.8 --min-return 10

# 数量控制
python fund_screener.py --bond --max 50

筛选模式与指标

模式	参数	核心指标	默认筛选标准
纯债基金	`--bond`	夏普比率	夏普>=1.0, 回撤<2%, 收益>2.5%
固收+	`--gushou-plus`	索提诺比率	夏普>=0.8, 索提诺>=1.2, 回撤<5%, 收益>3.5%
股票Alpha	`--stock-alpha`	卡玛比率	卡玛>=1.2, 回撤<30%, 收益>10%
默认/股票	无/`--stock`	夏普比率	夏普>=0.5, 回撤<15%, 收益>3%