菜单
Performs exploratory data analysis (EDA) on datasets from CKAN portals and CSV files. Use when analyzing datasets, checking data quality, exploring CSV files, or when the user asks to examine, analyze, or validate data.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/ondata/ckan-mcp-server --skill data-exploration命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | data-exploration |
| description | Performs exploratory data analysis (EDA) on datasets from CKAN portals and CSV files. Use when analyzing datasets, checking data quality, exploring CSV files, or when the user asks to examine, analyze, or validate data. |
| allowed-tools | ["Read","Bash","Grep","Glob","ckan_package_show","ckan_organization_show","ckan_package_search","ckan_datastore_search","ckan_find_relevant_datasets"] |
This skill provides comprehensive capabilities for Exploratory Data Analysis (EDA) on datasets from CKAN portals and direct CSV files. It focuses on understanding data structure, assessing quality, identifying patterns, and generating insights.
For advanced CSV analysis using SQL:
# Schema analysis
duckdb -jsonlines -c "DESCRIBE SELECT * FROM read_csv('url')"
# Statistical summarization
duckdb -jsonlines -c "SUMMARIZE SELECT * FROM read_csv('url')"
# Data sampling
duckdb -jsonlines -c "SELECT * FROM read_csv('url') USING SAMPLE N"
# Custom queries
duckdb -jsonlines -c "SELECT column_name, COUNT(*), AVG(value) FROM read_csv('url') GROUP BY column_name"
ckan_package_show - Detailed dataset metadatackan_organization_show - Publisher informationckan_package_search - Dataset discoveryckan_datastore_search - DataStore query capabilitiesckan_find_relevant_datasets - Semantic search1. Metadata Validation
- Check title, description, license
- Verify publisher information
- Assess tag relevance
2. Structural Analysis
- Examine schema and data types
- Check column naming conventions
- Validate data formats
3. Content Analysis
- Assess completeness (null values)
- Verify consistency (internal logic)
- Check accuracy (calculated fields)
4. Statistical Profiling
- Generate descriptive statistics
- Analyze distributions
- Identify outliers
5. Insight Generation
- Detect patterns and trends
- Generate quality score
- Provide recommendations
User: "Analyze this dataset from dati.gov.it"
1. Retrieve dataset metadata using ckan_package_show
2. Download and examine CSV structure
3. Generate statistical summary
4. Check data quality metrics
5. Identify key insights and patterns
6. Produce comprehensive report
User: "Check the quality of this CSV file"
1. Examine file structure and schema
2. Check for missing values
3. Validate data types and formats
4. Verify internal consistency
5. Generate quality score (0-10)
6. Provide improvement recommendations
User: "Compare these two datasets"
1. Retrieve both datasets
2. Analyze schemas and structures
3. Compare statistical profiles
4. Identify similarities and differences
5. Highlight quality differences
6. Generate comparison report
# Dataset Analysis Report
## Metadata Overview
- Title, Publisher, License
- Creation date, modification date
- Resource count and formats
## Structural Analysis
- Schema table (columns, types)
- Data format assessment
- Naming convention evaluation
## Quality Assessment
- Completeness score (0-10)
- Consistency evaluation
- Accuracy verification
- Overall quality score
## Statistical Profile
- Key statistics table
- Distribution analysis
- Outlier detection
- Trend analysis
## Key Insights
- Important patterns discovered
- Notable anomalies found
- Quality improvement recommendations
## Technical Details
- Analysis methods used
- Tools and queries executed
- Limitations and assumptions
| Criterion | Weight | Description |
|--------------------|--------|--------------------------------------|
| Completeness | 30% | Percentage of non-null values |
| Consistency | 25% | Internal logical coherence |
| Accuracy | 20% | Correctness of calculations |
| Metadata Quality | 15% | Completeness of documentation |
| Format Standards | 10% | Compliance with best practices |
USING SAMPLE N) for initial explorationThis skill can work alongside:
code-analysis: For examining data processing scriptsdocumentation: For improving dataset documentationvisualization: For creating data visualizationsreporting: For generating comprehensive reports.claude/commands/openspec/ - OpenSpec command templatesAGENTS.md - Agent guidelines and rulesdocs/skills/skills.md - General skills documentationdocs/europe/openapi.yaml - API specifications