root-cause-tracing

量化交易系统异常根因追踪。当交易系统出现策略切换失败、风控拦截、订单执行异常、仓位计算错误等深层问题时，使用此 Skill 进行系统性根因分析。

1.11x

Quality

92%

Does it follow best practices?

Impact

77%

1.11x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Evaluation results

66%

-7%

Trading Bot Strategy Lock-In Investigation

Strategy switch diagnosis

Criteria

Without context

With context

Symptom collection

100%

Scope scoping

100%

strategy_logs query

Grep for strategy switches

Cooldown period identified

100%

windows_bot.log referenced

100%

50%

src/trading_bot/ logs

Data layer check

100%

Risk control consideration

100%

Test environment first

100%

70%

Regression tests

100%

24h monitoring

100%

82%

23%

Unexpected Zero-Position Condition Investigation

Risk control layer diagnosis

Criteria

Without context

With context

Symptom collection

100%

Scope scoping

100%

max_allowed_drawdown_percent checked

100%

current_drawdown_percent source verified

83%

100%

Risk control grep pattern

20%

70%

windows_bot.log referenced

25%

100%

Config vs effective values

40%

60%

Data layer first

75%

100%

Execution layer check

12%

87%

Test environment first

24h monitoring

100%

85%

Abnormal Position Sizing After Maintenance Window

Data layer and exchange rate diagnosis

Criteria

Without context

With context

Symptom collection

100%

Scope scoping

100%

ExchangeRateService cache TTL

100%

91%

manual_exchange_rate recommended

100%

Error grep pattern used

Data layer first

87%

100%

Sync logs checked

100%

Decimal precision check

50%

MT5 return codes

50%

100%

Test environment first

100%

Regression tests

100%

Repository: Lingjie-chen/MT5
Commit: 3069d33

Evaluated: 26 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Trading Bot Strategy Lock-In Investigation Unexpected Zero-Position Condition Investigation Abnormal Position Sizing After Maintenance Window

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.