‹ 首页

example-data-processor

@fkesheh · 收录于 1 周前

Process CSV data files by cleaning, transforming, and analyzing them. Use this when users need to work with CSV files, clean data, or perform basic data analysis tasks.

场景数据整理数据分析

适合你，如果经常需要处理CSV格式的数据文件

/ 下载安装
example-data-processor.skill双击,或拖进 Claude 桌面版 / Cowork,即完成安装↓ .skill↓ .zip
用别的 agent?下载 .zip 解压,把文件夹放进它的技能目录
Claude Code~/.claude/skills/(项目级 .claude/skills/)
Codex CLI~/.codex/skills/
Cursor自动读取上面两处目录
其他工具见其文档的「skills」目录;两个下载是同一份文件,只是名字不同
/ 通过 npx 安装 校验哈希
npx oh-my-skill add fkesheh/skill-mcp/example-data-processor
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- fkesheh/skill-mcp/example-data-processor
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify fkesheh/skill-mcp/example-data-processor
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
29GitHub stars
~413最小装载
~1.4K含声明引用
~1.4K文本包总量
镜像托管

怎么用

技能原文 SKILL.md作者撰写 · MIT · fe11e20

Example Data Processor

This skill demonstrates a complete skill structure with scripts, references, and proper documentation.

What This Skill Does

Processes CSV data files with these capabilities:

  • Clean and validate data
  • Transform columns
  • Generate summary statistics
  • Export results
Usage
Process a CSV file

To process a CSV file:

Process the data in myfile.csv

The skill will:

  1. Read the CSV file
  2. Clean the data (remove nulls, fix formats)
  3. Generate statistics
  4. Output a summary report
Custom Processing

For custom processing options:

Process sales.csv and group by region
Scripts

scripts/process_csv.py - Main data processing script

  • Reads CSV files
  • Applies transformations
  • Generates output

scripts/fetch_data.py - API data fetcher (demonstrates uv dependencies)

  • Fetches data from APIs using requests
  • Beautiful output formatting with rich
  • Auto-installs dependencies via uv inline metadata (PEP 723)
  • No manual pip install needed!

scripts/validate.py - Data validation script

  • Checks data quality
  • Reports issues
Configuration

The scripts use these environment variables:

  • OUTPUT_DIR - Where to save processed files (optional)
  • MAX_ROWS - Maximum rows to process (optional)

Set them using:

Set OUTPUT_DIR to /path/to/output
Reference Documentation

For detailed information:

  • [Data Formats](references/formats.md) - Supported data formats and schemas
  • [Examples](references/examples.md) - Common usage examples
Troubleshooting

"File not found" error:

  • Ensure the CSV file exists
  • Provide the full path to the file

"Invalid data" error:

  • Check the CSV format matches expected schema
  • See [Data Formats](references/formats.md) for requirements
按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。
…