Delegate independent tasks to specialized agents working concurrently with isolated context.
ERP 貿易模組文檔查詢
erp-trade-doc
查詢 DataWin ERP 貿易模組文檔,用於程式開發參考。當用戶詢問貿易模組的功能、流程、操作步驟時使用。
SKILL.md
Full skill instructions
ERP 貿易模組文檔查詢
何時使用此 Skill
當用戶詢問關於 DataWin ERP 貿易模組的問題時:
- 業務流程(訂單、採購、出貨等)
- 功能操作(應收帳款、應付帳款等)
- 系統設定(公司、權限、幣別等)
- 資料結構和欄位說明
- 程式開發參考
查詢流程
第一步:讀取關鍵字索引
必須先讀取 docs-index/trade-module/keywords.json 來定位相關章節。
這個文件只有 ~825 tokens,包含所有關鍵字到章節的映射。
第二步:匹配關鍵字
根據用戶的問題,從 keywords.json 找出相關章節:
| 用戶問題 | 搜索關鍵字 | 相關章節 |
|---|---|---|
| "如何處理應收帳款?" | 應收、帳款 | ch23 |
| "訂單怎麼建立?" | 訂單 | ch12, ch20 |
| "出貨流程是什麼?" | 出貨 | ch12, ch14, ch18 |
| "如何設定公司資料?" | 系統設定、公司 | ch07 |
| "客戶資料在哪裡維護?" | 客戶 | ch08 |
第三步:載入章節內容
只載入相關的章節(通常 1-3 個):
讀取:docs-index/trade-module/chunks/ch23.md
Token 消耗:~1,161 tokens(平均每章)
第四步:回答問題
基於載入的章節內容,給出準確的答案,並引用章節來源。
關鍵字索引
<keywords> 以下是常用關鍵字映射(完整列表請讀取 keywords.json):系統基礎
- 上線、流程、功能鍵、查詢 → ch01-ch05
- 系統設定、公司、權限、幣別 → ch07
- 客戶、廠商、產品 → ch08
日常作業
- 報價 → ch11, ch17
- 訂單、採購、出貨 → ch12
- 組合、分批、分開包裝 → ch13-ch15
- INVOICE → ch18
- 追蹤查詢 → ch19-ch21
帳款管理
- 應收、應付 → ch23, ch24
- 收支、預收、預付、訂金 → ch25, ch26
- 加扣款、信用狀 → ch27, ch28
其他功能
- 備份、歷史、覆核、關帳 → ch30-ch32
- EXCEL、傳輸、排程、傳真 → ch34-ch37
- Q&A → ch38, ch39 </keywords>
Token 消耗估算
| 操作 | Token 消耗 |
|---|---|
| 讀取 keywords.json | ~825 |
| 讀取單個章節 | ~1,161 |
| 典型查詢(1 章) | ~2,000 |
| 複雜查詢(3 章) | ~4,300 |
| 如果讀整個 HTML | ~210,000 |
範例使用
範例 1:應收帳款
用戶: 「應收帳款怎麼處理?」
AI 操作:
- 讀取
keywords.json(~825 tokens) - 找到 "應收" → ch23
- 讀取
chunks/ch23.md(~1,161 tokens) - 回答問題
總消耗: ~2,000 tokens(節省 99%)
範例 2:出貨流程
用戶: 「出貨的完整流程是什麼?」
AI 操作:
- 讀取
keywords.json(~825 tokens) - 找到 "出貨" → ch12, ch14, ch18
- 讀取
chunks/ch12.md,chunks/ch14.md,chunks/ch18.md(~3,500 tokens) - 回答問題
總消耗: ~4,300 tokens(節省 98%)
注意事項
- 永遠先讀 keywords.json - 不要直接讀章節,這樣會浪費 token
- 只載入需要的章節 - 通常 1-3 個章節就足夠回答問題
- 引用來源 - 回答時說明內容來自哪個章節(如:
ch23.md:23) - 如果找不到關鍵字 - 可以讀取
toc.json查看完整目錄結構
檔案路徑
C:\真桌面\Claude code\ERP explore\docs-index\trade-module\
├── keywords.json # 關鍵字索引
├── toc.json # 完整目錄
└── chunks/ # 39 個章節內容
├── ch01.md
├── ch02.md
...
└── ch39.md
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
