Kingdee K3 Cloud Purchase Table Schema Query
Paste the following prompt into your AI chat to install this skill:
Follow https://skillhub.cn/install/skillhub.md to install @user_2de6ec79/kingdee-schema.
About this skill
Problem
In Kingdee K3 Cloud development, table names, fields, multilingual tables, and upstream/downstream links are often handled through tribal knowledge. Naming patterns such as T_PUR_POORDER, T_PUR_RECEIVE, _L, _LK, and ENTRY carry business meaning, but developers can easily get joins wrong. This skill organizes schema references for 61 core purchase-management tables to answer questions like “What fields does the purchase order have?”, “How do receive notices link to purchase orders?”, and “How should multilingual tables be queried?”.
How it works
- Schema lookup: Use a table name or Chinese label to inspect field names, types, lengths, and definitions.
- Relation lookup: Explain how master tables, entry tables, multilingual tables, and
_LKrelation tables connect, such asT_PUR_POORDERENTRYjoining the master byFID, and_LKtables linking upstream records byFSIDtoFENTRYID. - SQL guidance: Provide common query patterns for purchase orders, receipts, stock-in, and multilingual joins, including
FLOCALEID=2052for Simplified Chinese.
Boundary: The references are based on a specific K3 Cloud version. Validate production SQL in a test environment first, back up data before changes, and compare against the live database if schemas differ.
Use Cases
- Confirm T_PUR_POORDER master, entry, and field types before writing purchase-order SQL.
- Trace purchase order to receive notice links via _LK tables and FSID to FENTRYID joins.
- Check _L table joins and FLOCALEID=2052 before querying localized purchase-order names.
- Explain T_PUR_INSTOCKENTRY fields and status values when answering business questions.
Best For
- Kingdee ERP developers debugging purchase order, receive, and stock-in joins.
- Implementation consultants explaining purchase table fields and status values to business users.
- Data analysts confirming table structure before writing purchase-document SQL.
- Data engineers validating production SQL field and relation assumptions.
Related Skills
A one-shot coding agent built on Claude Code CLI that runs non-interactively, supports a specified workdir, and can be monitored in the foreground or background.
Preview and confirm file sorting by extension, with recursive cleanup, ignore rules, and transactional rollback.
An engineering assistant for static HTML/CSS/JS pages, design-token extraction, IE8-compatible review, and structured delivery.
An engineering workflow for requirement analysis, scenario modeling, risk planning, quality gates, testing, and knowledge capture, with lightweight, standard, and full modes.