dws

Original🇨🇳 Chinese
Translated
27 scripts

Manage DingTalk product capabilities (AI Table/Calendar/Contacts/Documents/Robots/Todo/Email/Meeting Minutes/AI Applications/Approvals/Work Reports/Drive, etc.). Use this when users need to operate table data, manage schedules and meetings, query contacts, send message notifications, handle approval processes, view meeting minute summaries, create applications/systems/management backends/business tools, view daily/weekly reports, or manage DingTalk Drive files.

7installs
Added on

NPX Install

npx skill4agent add stvlynn/dingtalk-wukong-skills dws

SKILL.md Content (Chinese)

View Translation Comparison →

DingTalk Full Product Skill

Manage DingTalk product capabilities via the
dws
command.

STRICTLY PROHIBITED (NEVER DO)

  • NEVER use methods other than the dws command for operations (curl, HTTP API, browsers are prohibited)
  • NEVER fabricate identifiers like UUID or ID; must extract them from command returns
  • NEVER guess field names/parameter values; must query and confirm before operations

STRICTLY REQUIRED (MUST DO)

  • All commands must include
    --format json
    to get parsable output
  • Add
    --yes
    and confirm with the user before performing delete operations
  • Batch operations must not exceed 100 records at a time
  • All commands must strictly follow the parameter formats specified in the corresponding product reference documents (e.g., if there is a parameter value, at least one space must separate the parameter and its value)

Product Overview

ProductPurposeReference Document
aitable
AI Table: CRUD operations for tables/data tables/fields/records, template searchaitable.md
calendar
Calendar: Schedule/participant/conference room/busy-free querycalendar.md
contact
Contacts: User queries(current user/search/details)/department queries(search/sub-departments/member lists)contact.md
doc
Documents: Search/browse/read/create/update documents, folder management, block-level editingdoc.md
chat
Group Chat: Group management(creation/search/member addition/removal/name modification), messages(pull/send/bot mass sending/Webhook), bot searchchat.md
todo
Todo: Creation(with priority/deadline)/query/modification/mark as complete/deletetodo.md
mail
Email: Email query/search/view/sendmail.md
minutes
AI Meeting Minutes: List/summary/transcription/keyword/title modificationminutes.md
report
Work Reports: Inbox/sent/templates view/details/read statisticsreport.md
drive
DingTalk Drive: Browse files/metadata/download/create folders/upload filesdrive.md
ding
DING Messages: Send/recall(in-app/SMS/phone call)ding.md
devdoc
Open Platform Documents: Search development documentssimple.md
conference
Video Conference: Schedule conferencessimple.md
aiapp
AI Applications: Create/query/modify AI applicationsaiapp.md
live
Live Streaming: View live stream listsimple.md
oa
OA Approval: Pending tasks/details/approve/revoke/records/initiated tasksoa.md
attendance
Attendance: Check-in records/schedule queryattendance.md

Intent Judgment Decision Tree

When the user mentions "table/multi-dimensional table/AI table/record/data" →
aitable
When the user mentions "schedule/calendar/conference room/appointment" →
calendar
When the user mentions "contacts/colleagues/department/organizational structure" →
contact
When the user mentions "document/knowledge base/write document" →
doc
When the user mentions "todo/TODO/task reminder" →
todo
When the user mentions "mail/email" →
mail
When the user mentions "meeting minutes/conference recording/transcription/AI summary" or provides a meeting minute URL (e.g.,
https://shanji.dingtalk.com/*
) →
minutes
When the user mentions "help me make/build/generate/generate system/AI application/create application/intelligent application" →
aiapp
When the user mentions "DING/urgent message/phone reminder" →
ding
When the user mentions "attendance/check-in/schedule" →
attendance
When the user mentions "group chat/group message/group member/chat history/create group/bot send message/Webhook/notification" →
chat
When the user mentions "approval/OA" →
oa
When the user mentions "development/API/call error document" →
devdoc
When the user mentions "campus recruitment/post position/my candidates" →
ai_sincere_hire
When the user mentions "video conference/schedule conference" →
conference
When the user mentions "live streaming" →
live
When the user mentions "work report/daily report/weekly report/work report statistics" →
report
When the user mentions "DingTalk Drive/file/cloud drive/download file/upload file" →
drive
When the user mentions "enterprise credit/industrial and commercial information/shareholders/judicial documents/risk/trademark/patent/bidding/contact information/KP" →
credit
When the user mentions "legal consultation/laws/legal cases/statutes/legal precedents/legal basis" →
law
Key Distinctions: aitable(data tables) vs doc(document editing) Key Distinctions: report(DingTalk work reports/daily/weekly reports) vs doc(document editing) vs todo(todo tasks) Key Distinctions: drive(DingTalk Drive file storage/upload/download) vs doc(DingTalk Document content read/write/knowledge base space) Key Distinctions: conference(video conference scheduling) vs calendar event(calendar schedule management) Key Distinctions: chat message send(personal identity mass sending) vs send-by-bot(bot message sending) vs send-by-webhook(Webhook alerts)
For more confusing scenarios and user expression examples, see intent-guide.md

Core Process

As an intelligent assistant, your primary task is to understand the user's true and complete intent, rather than simply executing commands. Before selecting a
dws
product command, you must strictly follow these three steps:
  1. Intent Classification: First, determine which category the core verb/action in the user's instruction belongs to. This is more important than focusing on nouns.
  2. Ambiguity Handling and Information Inquiry: If the user's instruction is ambiguous or contains keywords from multiple products, under no circumstances should you guess. You must actively ask the user to clarify their intent. This is your core value as an intelligent assistant rather than a command executor.
  3. Accurate Product Mapping: After completing the first two steps and clarifying the intent, refer to the Product Overview and Intent Judgment Decision Tree to select the appropriate product.
  4. Fully read the product reference documents, and implement the user's intent by writing code or directly calling commands.

Error Handling

  1. When encountering an error, retry once with
    --verbose
  2. If it still fails, report the error message to the user
  3. Prohibit trying alternative solutions on your own
  4. If identity verification fails, you can use dws auth login to log in

Detailed References (Read on Demand)

  • references/products/ — Detailed reference for each product command
  • references/intent-guide.md — Intent routing guide (comparison of confusing scenarios)
  • references/global-reference.md — Global flags, authentication, output format
  • references/field-rules.md — AI Table field type rules
  • references/error-codes.md — Error codes + debugging process
  • scripts/ — AI Table batch operation scripts