postgres-trading
交易数据库 PostgreSQL 只读查询工具。用于查询交易记录、持仓数据、盈亏统计、策略执行日志。当需要分析历史交易数据、检查数据库状态或生成统计报告时使用此 Skill。
95
93%
Does it follow best practices?
Impact
95%
1.50xAverage 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 a well-crafted skill description that clearly defines its scope (read-only PostgreSQL queries for trading data), lists specific queryable data types, and provides explicit usage triggers. The description is concise yet comprehensive, using appropriate third-person voice and domain-specific terminology that users would naturally use.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: '查询交易记录、持仓数据、盈亏统计、策略执行日志' (query transaction records, position data, profit/loss statistics, strategy execution logs). Uses third person voice appropriately. | 3 / 3 |
Completeness | Clearly answers both what ('只读查询工具' for querying various trading data types) AND when ('当需要分析历史交易数据、检查数据库状态或生成统计报告时使用此 Skill'). Has explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: '交易数据库', 'PostgreSQL', '交易记录', '持仓数据', '盈亏统计', '历史交易数据', '统计报告'. Good coverage of domain-specific terms in Chinese. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche: trading database with PostgreSQL, read-only queries, specific data types (transactions, positions, P&L, strategy logs). Unlikely to conflict with general database or document skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%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-crafted skill with excellent actionability through concrete SQL templates and clear safety boundaries. The content is concise and domain-specific without explaining concepts Claude already knows. The main weakness is the lack of explicit workflow guidance for query execution, error handling, and result validation.
Suggestions
Add a brief workflow section showing the query execution process: 1) Load config, 2) Connect with readonly=True, 3) Execute query, 4) Validate results, 5) Handle errors
Include example error handling for common failure cases (connection timeout, invalid SQL, empty results)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient - no unnecessary explanations of what PostgreSQL is or how databases work. Every section serves a clear purpose with minimal padding. | 3 / 3 |
Actionability | Provides fully executable SQL queries for common trading scenarios, copy-paste ready connection configuration, and concrete pip install command. All examples are complete and specific to the trading domain. | 3 / 3 |
Workflow Clarity | While the skill clearly documents safety rules and query templates, it lacks explicit workflow steps for the query process itself. No validation checkpoints or error handling guidance for when queries fail or return unexpected results. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections (scenarios, prerequisites, config, templates, safety rules). Content is appropriately sized for a single file with logical groupings. The intent matching table provides excellent navigation for common use cases. | 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.