Use Case
Trading Coach is a powerful AI agent skill that extends your assistant with new capabilities. π AI Trading Review Coach β Turn your brokerage CSV into actionable insights for improvement! Automatic FIFO matching positions, 8-dimensional quality score (entry/exit/trend/risk...), 10-dimensional AI insight. Supports mainstream brokerages such as Futu (Chinese/English), Tiger, CITIC, and Huatai. Trigger conditions: Users provide transaction CSV, request analysis of transaction performance, evaluate transaction quality, generate review report, Calculate profit and loss statistics, identify trading pattern problems, "Help me review the transaction", "Analyze my transaction". This guide walks you through installing Trading Coach, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Trading Coach: npx clawhub@latest --dir ~/.claude/skills install trading-coach
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to finance & investment to trigger Trading Coach
Review the output and refine your prompt for better results
Combine Trading Coach with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Trading Coach
Help me get started with Trading Coach
What can Trading Coach do for my finance & investment workflow?
Show me an example of using Trading Coach
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install trading-coachOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install trading-coachβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/trading-coach/π‘Extract and place the folder at the path above, then restart your agent.