菜单
Parse brokerage CSV exports that exist in multiple formats with overlapping data across files
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/vamseeachanta/workspace-hub --skill multi-format-csv-parser-with-deduplication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 | multi-format-csv-parser-with-deduplication |
| description | Parse brokerage CSV exports that exist in multiple formats with overlapping data across files |
| version | 1.0.0 |
| source | auto-extracted |
| extracted | "2026-04-14T00:00:00.000Z" |
| metadata | {"tags":["data-ingestion","csv-parsing","deduplication","brokerage-data"]} |
When ingesting brokerage data across multiple files or format versions, first map all edge cases (header variations, footer disclaimers, BOM markers). Auto-detect format from header row. Strip footers and BOM before parsing. Build a deduplication key (e.g., date + ticker + quantity + price) to merge overlapping transaction rows across files. Validate final dataset against user-stated holdings to catch parsing errors early.
