csv-data-summarizer
交易日志 CSV 数据分析工具。自动分析交易记录 CSV 文件，计算胜率、盈亏比、最大回撤、Sharpe Ratio 等量化指标并生成可视化报告。当需要分析交易绩效、优化策略参数或生成交易报告时使用此 Skill。
Install with Tessl CLI
npx tessl i github:Lingjie-chen/MT5 --skill csv-data-summarizer74
Quality
61%
Does it follow best practices?
Impact
94%
1.20xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.trae/skills/csv-data-summarizer/SKILL.mdDiscovery
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 its purpose (trading log CSV analysis), lists specific quantitative metrics it calculates, and explicitly states when to use it. The description uses proper third-person voice, includes domain-specific trigger terms that traders would naturally use, and occupies a distinct niche that minimizes conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: '分析交易记录 CSV 文件' (analyze trading CSV files), '计算胜率、盈亏比、最大回撤、Sharpe Ratio' (calculate win rate, profit/loss ratio, max drawdown, Sharpe Ratio), and '生成可视化报告' (generate visualization reports). | 3 / 3 |
Completeness | Clearly answers both what (analyze trading CSV files, calculate quantitative metrics, generate reports) AND when ('当需要分析交易绩效、优化策略参数或生成交易报告时使用此 Skill' - use when analyzing trading performance, optimizing strategy parameters, or generating trading reports). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: '交易日志' (trading log), 'CSV', '交易记录' (trading records), '胜率' (win rate), '盈亏比' (profit/loss ratio), '最大回撤' (max drawdown), 'Sharpe Ratio', '交易绩效' (trading performance), '策略参数' (strategy parameters), '交易报告' (trading report). | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting trading/quantitative analysis with distinct triggers like '交易日志', 'Sharpe Ratio', '最大回撤', '盈亏比' that are unlikely to conflict with general data analysis or other CSV processing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive reference for trading metrics and report structure, but lacks actionable implementation. It reads more like a specification document than an executable skill - Claude knows what to produce but not how to produce it. The absence of any Python code for CSV parsing, metric calculation, or visualization generation significantly limits its utility.
Suggestions
Add executable Python code for CSV parsing and metric calculation (e.g., using pandas to read MT5 format and calculate win rate, max drawdown)
Include a clear step-by-step workflow: 1) Load and validate CSV, 2) Clean/normalize data, 3) Calculate metrics, 4) Generate report - with validation checkpoints
Add code for visualization generation (matplotlib/plotly) since the description mentions '可视化报告'
Remove redundant '说明' explanations for standard financial metrics that Claude already understands
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill provides useful reference tables and templates, but includes some redundant explanations (e.g., explaining what each metric means when Claude already knows). The formula tables are efficient, but the '说明' column often states the obvious. | 2 / 3 |
Actionability | The skill describes what to calculate and what output should look like, but provides no executable code for parsing CSVs, calculating metrics, or generating reports. It's entirely descriptive with no copy-paste ready implementation. | 1 / 3 |
Workflow Clarity | There is no clear workflow sequence. The skill lists analysis dimensions and output format but doesn't specify steps like: 1) parse CSV, 2) validate data, 3) calculate metrics, 4) generate report. No validation checkpoints for data quality or calculation verification. | 1 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections (指标计算, CSV格式, 分析维度, 输出模板), but everything is in one file. For a skill of this complexity, separating detailed formulas or example code into referenced files would improve navigation. | 2 / 3 |
Total | 6 / 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.
- 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.