hedging

Name: hedging
Availability: InStock
Author: xueqingpeng

Automates daily hedging decisions for a fixed stock pair using offline MCP data.

11|Updated Mar 14, 2026

Search Tags:#risk-management #hedging #algorithmic-trading #pair-trading #offline-mcp

Ready to run

npx skills add https://github.com/xueqingpeng/trading-analysis --skill hedging

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: hedging
Source: https://github.com/xueqingpeng/trading-analysis/tree/main/.claude/skills/hedging
Command: npx skills add https://github.com/xueqingpeng/trading-analysis --skill hedging

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires duckdb, numpy, pandas, fastmcp, pydantic, and includes scripts (resource) components.

What problem does it solve?

Automates daily hedging decisions for a fixed stock pair using offline MCP data.

Core Features & Use Cases

Deterministic single-day hedging: on the run's first day, selects a fixed pair and writes the initial decision; on subsequent days, upserts a single day’s recommendation for the same pair.
Data-driven, offline workflow: uses hedging_mcp tools to fetch prices, news highlights, and filings context without directly reading DuckDB or Parquet files.
Lifecycle-backed output: writes to results/hedging with a structured JSON containing status, pair, start/end dates, and a day-by-day recommendations log.

Quick Start

Run the hedging task for a chosen TARGET_DATE to generate the first daily recommendation.

Frequently Asked Questions about hedging

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate daily pair trading hedging decisions for a fixed stock pair?▼

You automate daily pair trading hedging decisions by running a task that derives a TARGET_DATE and outputs a single daily recommendation for a fixed stock pair, writing structured JSON to results/hedging.

What is deterministic single-day hedging and how does the lifecycle output work?▼

Deterministic single-day hedging selects a fixed pair and writes an initial decision on the first day, then upserts a single day's recommendation on subsequent days into a structured JSON log with status, dates, and recommendations.

How do I fetch prices and news highlights for algorithmic trading without directly reading Parquet files?▼

You fetch prices, news highlights, and filings context for hedging decisions by using offline MCP tools, which provide constrained data access without directly reading DuckDB or Parquet files.

Does the hedging workflow support ongoing pair trading tasks or only new single-day runs?▼

The hedging workflow supports both new and ongoing tasks by applying deterministic action semantics across single-day decision runs, upserting daily recommendations for the same fixed stock pair throughout the hedging lifecycle.

Do I need DuckDB and Pandas installed to run offline MCP hedging tasks?▼

Yes, you need DuckDB, Pandas, NumPy, FastMCP, and Pydantic installed, as these dependencies support the offline MCP data access, deterministic decision logic, and structured JSON output lifecycle.