// This skill should be used when the user asks to review trading performance, analyze wins/losses, or understand why their strategy is underperforming. Trigger phrases include "analyze my trades", "how is my strategy doing", "why am I losing", "review performance", "trading results", "what went wrong".
Guide user through factor research and mining. Trigger when user asks to "find effective factors", "mine factors", "research alpha factors", "help me design a factor", "factor analysis", or similar requests about discovering new trading factors.
This skill should be used when the user asks to check system health, verify their setup is working correctly, or wants an overall status report. Trigger phrases include "check my system", "is everything working", "system status", "health check", "diagnose my setup", "what's the status".
This skill should be used when the user explicitly asks to CREATE or BUILD a programmatic (Python code) trading strategy. Trigger phrases include "create a program strategy", "build a trading program", "set up programmatic trading", "write a trading bot", "create a Python strategy". Do NOT trigger for general questions about how programs work.
This skill should be used when the user explicitly asks to CREATE or BUILD an AI-decision (Prompt-based) trading strategy. Trigger phrases include "create a prompt strategy", "build an AI trading strategy", "set up AI decision trading", "help me create a prompt-based strategy". Do NOT trigger for general questions about how strategies work or what prompt strategies are.
This skill should be used when the user reports that their AI Trader is not triggering, not executing trades, or behaving unexpectedly. Trigger phrases include "why isn't my trader working", "strategy not executing", "no trades happening", "trader not triggering", "why no signals".
This skill should be used when the user wants to view, update, correct, or delete their stored memories. Trigger phrases include "show my memories", "update memory", "fix memory", "delete memory", "what do you remember about me", "correct this memory", "remove that memory".
| name | performance-review |
| shortcut | review |
| description | This skill should be used when the user asks to review trading performance, analyze wins/losses, or understand why their strategy is underperforming. Trigger phrases include "analyze my trades", "how is my strategy doing", "why am I losing", "review performance", "trading results", "what went wrong". |
| description_zh | 当用户要求回顾交易表现、分析盈亏或了解策略表现不佳的原因时使用此技能。 |
Analyze trading performance and provide actionable optimization suggestions. Combines Attribution AI analysis with memory-based historical context.
list_traders(trader_id) → get trader details and current statusget_wallet_status(wallet_address) → current balance and positionsDelegate deep analysis to Attribution AI:
call_attribution_ai(task="Analyze trading performance for trader X over the last N days. Identify patterns in winning and losing trades.")→ [CHECKPOINT] Present performance summary in plain language:
From the analysis, identify:
These insights will be automatically saved to user memory by the context compression system for future reference.
→ [CHECKPOINT] Present key insights and ask if user wants optimization suggestions.
Based on findings, suggest specific improvements:
Signal Pool Adjustments:
Strategy Logic Adjustments:
If user agrees to optimize:
→ [CHECKPOINT] Show proposed changes before applying. Wait for user confirmation.