菜单
Read web pages, articles, and document links by converting URLs into Markdown text. Use the `read_url` tool directly, without bash.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
券商研报分析助手，聚焦"研报获取→结构化提取→多机构观点对比→风险识别→决策辅助"。使用时机：汇总个股券商研报、追踪行业研报、对比多机构观点、识别卖方利益冲突、验证研报时效性。默认数据源为东方财富研报中心公开接口（无需 API Key）。
Asset allocation theory and optimizer usage — MPT / Black-Litterman / risk budgeting / all-weather strategy, including guides for 4 optimizers and rebalancing rules.
Correlation and cointegration analysis — co-movement discovery, deep return-correlation analysis, sector clustering, realized correlation, Engle-Granger / Johansen cointegration, half-life, Kalman dynamic hedge ratio, cross-market linkage analysis, and pair-trading signal generation
Data source selection decision tree. Load this skill BEFORE any backtest or data-fetching task to choose the best available data source.
Event-driven strategy based on sentiment-scored signals from news, announcements, and macro events. The LLM acts as the NLP engine, and event data follows a CSV schema.
Factor research framework with IC/IR analysis, quantile backtesting, and factor combination. Suitable for cross-sectional factor evaluation across multiple instruments.
| name | web-reader |
| description | Read web pages, articles, and document links by converting URLs into Markdown text. Use the `read_url` tool directly, without bash. |
| category | tool |
Converts any URL into clean Markdown text, removing ads, navigation, styling, and other distractions. Suitable for:
tushare, OKX, yfinance, and similar)Call the read_url tool directly (do not use bash + requests, call the tool directly):
read_url(url="https://tushare.pro/document/2?doc_id=27")
Returns JSON:
{
"status": "ok",
"title": "Page title",
"url": "Original URL",
"content": "Page content in Markdown format",
"length": 12345
}
read_url(url="https://tushare.pro/document/2?doc_id=27")
read_url(url="https://blog.example.com/quantitative-trading-guide")
read_url(url="https://github.com/PaddlePaddle/PaddleOCR")