deep-research
量化交易市场深度研究工具。支持宏观经济分析、技术面研究、资产相关性分析和市场微观结构研究。当需要进行深度市场调研、分析经济数据影响或研究新交易品种时使用此 Skill。
71
Quality
58%
Does it follow best practices?
Impact
89%
1.48xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.trae/skills/deep-research/SKILL.mdDiscovery
67%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 description adequately covers both what the skill does and when to use it, with an explicit 'Use when' clause in Chinese. However, the capabilities listed are high-level categories rather than concrete actions, and the trigger terms could be expanded to include more natural user phrases and variations.
Suggestions
Replace category labels with specific concrete actions (e.g., '分析GDP数据对市场影响', '计算资产间相关系数', '研究订单簿深度')
Add more natural trigger terms users might say, such as '量化策略', '回测', '因子分析', '市场数据', specific asset types like '股票', '期货', '加密货币'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (quantitative trading market research) and lists several action areas (macro analysis, technical research, correlation analysis, market microstructure), but these are category labels rather than concrete specific actions like 'extract', 'fill', 'merge'. | 2 / 3 |
Completeness | Clearly answers both what (quantitative trading research with macro, technical, correlation, and microstructure analysis) AND when ('当需要进行深度市场调研、分析经济数据影响或研究新交易品种时' - when deep market research, economic data analysis, or researching new trading instruments is needed). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like '宏观经济分析' (macro analysis), '技术面研究' (technical research), '市场调研' (market research), but missing common user variations and natural phrases users might say when needing this skill. | 2 / 3 |
Distinctiveness Conflict Risk | Reasonably specific to quantitative trading research domain, but terms like '市场分析' and '经济数据' could overlap with general financial analysis or economics skills. The combination of quantitative trading focus helps but isn't fully distinctive. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
50%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 research framework for quantitative trading market analysis with good structural organization using tables and clear categorization. However, it lacks executable code examples for the analytical tasks described, relies too heavily on descriptive frameworks rather than actionable implementations, and could benefit from validation checkpoints given the high-stakes nature of trading decisions.
Suggestions
Add executable Python code for key operations like calculating correlation matrices, fetching economic calendar data, or parsing COT reports
Include validation checkpoints in research workflows, such as 'verify data freshness before analysis' or 'cross-reference findings with multiple sources before trading implications'
Split detailed reference content (data sources, common correlations) into separate files and keep SKILL.md as a concise overview with clear navigation links
Remove explanatory content about well-known correlations (XAUUSD vs DXY) that Claude already understands, or condense into a quick-reference format
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is reasonably efficient with good use of tables, but includes some unnecessary framing (适用场景 section lists obvious use cases) and the research framework sections could be more condensed. The tables are well-structured but some content like '常见相关性' explains relationships Claude likely already knows. | 2 / 3 |
Actionability | Provides structured frameworks and templates but lacks executable code. The '研究步骤' are descriptive rather than showing actual Python/code implementations for calculating correlations or fetching data. The JSON output format is helpful but there's no code showing how to generate it. | 2 / 3 |
Workflow Clarity | Research steps are listed in logical sequence (e.g., correlation analysis steps 1-5), but there are no validation checkpoints or feedback loops. For a research workflow that could lead to trading decisions, there should be explicit verification steps before acting on findings. | 2 / 3 |
Progressive Disclosure | Content is organized into clear sections with tables, but everything is in one monolithic file. The data sources and research frameworks could be split into separate reference files. The GitHub reference at the end suggests external content exists but isn't properly integrated. | 2 / 3 |
Total | 8 / 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.