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。
90
92%
Does it follow best practices?
Impact
77%
1.11xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines a specific domain (quantitative trading system anomaly root cause analysis), lists concrete problem types it addresses, and explicitly states when to use it. The description uses proper third-person voice and includes domain-specific terminology that users in this field would naturally use.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: '策略切换失败、风控拦截、订单执行异常、仓位计算错误' (strategy switching failures, risk control interception, order execution anomalies, position calculation errors) and '系统性根因分析' (systematic root cause analysis). | 3 / 3 |
Completeness | Clearly answers both what ('量化交易系统异常根因追踪' - quantitative trading system anomaly root cause tracking) and when ('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' - when trading system encounters these specific deep issues). | 3 / 3 |
Trigger Term Quality | Includes natural domain-specific keywords users would say: '量化交易系统' (quantitative trading system), '异常' (anomaly), '策略切换' (strategy switching), '风控' (risk control), '订单执行' (order execution), '仓位' (position), '根因' (root cause). | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific niche targeting quantitative trading system anomalies with distinct triggers like '策略切换失败', '风控拦截', '订单执行异常', '仓位计算错误' - unlikely to conflict with general debugging or other trading skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured root cause analysis skill for quantitative trading systems. It excels in organization and workflow clarity with a systematic 4-step methodology. The main weakness is that some diagnostic steps describe what to check rather than providing executable commands or code snippets.
Suggestions
Replace vague diagnostic descriptions like '检查 MT5 连接状态和心跳' with actual executable commands or code snippets
Add concrete code examples for common fixes in the '快速修复' column (e.g., how to set manual_exchange_rate)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables and structured lists to convey information without unnecessary explanation. It assumes Claude understands trading systems and jumps directly to actionable diagnostic steps. | 3 / 3 |
Actionability | Provides concrete diagnostic tables and grep commands, but lacks executable code examples for the actual fixes. The 'diagnostic commands' column often describes what to check rather than providing copy-paste commands. | 2 / 3 |
Workflow Clarity | Clear 4-step methodology with explicit validation checkpoints (Step 4 includes test environment verification, regression tests, and 24h monitoring). The workflow handles error recovery through hypothesis generation and verification cycles. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections (methodology, log analysis, quick reference tables). References external docs appropriately (strategy_rules.md Chapter 9) without deep nesting. Content is appropriately scoped for a single skill file. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- Lingjie-chen/MT5
- Commit
3069d33
- Reviewed
Table of Contents
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.