Skip to main content
ClaudeWave
EN, English
Skill5.1k repo starsupdated 2mo ago

dingtalk-cli

**dingtalk-cli** is a skill that enables interaction with DingTalk, Alibaba's enterprise communication platform. It provides command-line access to messaging, DING alerts, contacts, documents, cloud storage, meeting rooms, approval workflows, attendance tracking, todos, reports, AI tables, and meeting minutes. Use this skill when the user requests any DingTalk operation, from sending messages to managing organizational workflows and accessing enterprise data.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/dtyq/magic /tmp/dingtalk-cli && cp -r /tmp/dingtalk-cli/backend/super-magic/agents/skills/dingtalk-cli ~/.claude/skills/dingtalk-cli
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# DingTalk CLI Skill Index

**Before doing anything**, you MUST load the `dws` skill first. It contains the full product reference, command syntax, intent routing decision tree, dangerous operation rules, and error handling guide. Do not proceed without reading it.

```
read_skills(skill_names=["dws"])
```

---

## Product Overview

| Product | Use for | CLI entry |
|---------|---------|-----------|
| `aiapp` | AI apps: create, query, update | `dws aiapp` |
| `aisearch` | AI search: find people by name, employee number, phone, department, responsibility, reporting lines | `dws aisearch` |
| `aitable` | AI tables: bases, tables, fields, records, views, charts, dashboards, import/export | `dws aitable` |
| `attendance` | Attendance: punch records, shift schedules, statistics | `dws attendance` |
| `calendar` | Calendar: events, attendees, meeting rooms, availability | `dws calendar` |
| `chat` | Conversations, group chats, bot messaging, single chat, Webhook, message history, direct/group message list, sender filters, unread conversations, keyword and advanced message search, read/send status, send/reply/forward/recall | `dws chat` |
| `contact` | Contacts: user lookup, department structure | `dws contact` |
| `devdoc` | DingTalk open platform developer documentation search | `dws devdoc` |
| `ding` | DING alerts: send/recall (in-app / SMS / phone) | `dws ding` |
| `doc` | DingTalk docs: search, read, write, block edit, comments, copy/move | `dws doc` |
| `drive` | Cloud drive: file list, upload, download, folders | `dws drive` |
| `live` | Live sessions: list and info | `dws live` |
| `mail` | Mail: search, view, send | `dws mail` |
| `minutes` | AI meeting minutes: list, summary, transcript, todos, mindmap | `dws minutes` |
| `oa` | OA approvals: pending, submitted, approve, reject, revoke | `dws oa` |
| `pat` | Behavior authorization management | `dws pat` |
| `report` | Logs/reports: create by template, inbox, sent, statistics | `dws report` |
| `sheet` | DingTalk spreadsheets: worksheets, cells, formulas, images, find/replace | `dws sheet` |
| `todo` | Todos: create, query, update, complete, delete | `dws todo` |
| `wiki` | DingTalk wiki spaces and knowledge-base nodes | `dws wiki` |

---

## Authentication

Before any DingTalk operation, verify auth status first:

```bash
dws auth status --format json
```

If `authenticated` is `false`, start the login flow. This environment has no browser (Docker/SSH), so always use the device flow:

```bash
dws auth login --device
```

The command outputs an authorization URL, then waits with the prompt `Waiting for user authorization`. At this point:
1. Show the authorization URL to the user
2. Ask the user to open the URL in a browser or DingTalk mobile app to complete authorization
3. The command will automatically detect the authorization and proceed

To force re-login (e.g. token expired):

```bash
dws auth login --device --force
```

---

## When Unsure About a Command

Always check `--help` before guessing parameters.

```bash
dws --help
dws <product> --help
dws <product> <command> --help
```

Examples:

```bash
dws chat --help
dws calendar event list --help
dws aitable record --help
```
agent-infoSkill

Query the list of all agents (employees) available to the current user. Use when generating code that requires a real agentId, or when the user asks "which agents/employees do I have".

ai-card-generatorSkill

|

antd-style-to-tailwindSkill

Migrate existing antd-style CSS-in-JS (createStyles) components to Tailwind CSS utility classes with full dark mode support, following the project's style system transition strategy. Use when the user asks to migrate, convert, or rewrite antd-style components to Tailwind, or when working on new components in files that already use antd-style.

browserSkill

Open and operate webpages in a real browser: navigate, read rendered content, inspect interactive elements, click, type, submit forms, press keys, select options, check boxes, hover, scroll, upload files, wait for page changes, manage pages, take and save screenshots, analyze visual layout, and inspect page errors and network activity.

canvas-designerSkill

Core canvas design skill covering project management, multimedia principles, AI image generation, web image search, and design marker processing. Load for any canvas design task. CRITICAL - When user message contains [@design_canvas_project:...] or [@design_marker:...] mentions, or when the user wants to generate video/animation/clip on a canvas project, you MUST load this skill first before any operations.

chat-historySkill

Use when details may have been lost after context compaction, or when the Agent needs to inspect earlier compacted messages or previously created sub-agents.

cli-managerSkill

Manage persistence for user-installed third-party CLI tools in the Super Magic sandbox. Use when the user wants to install, configure, adopt, restore, inspect, or remove a CLI, or when an external skill, webpage, or installer asks to run CLI install commands such as curl|sh, npm install -g, pipx install, uv tool install, go install, cargo install, or brew install. Do not persist runtime-provided CLIs.

code-review-expertSkill

Expert code review of current git changes with a senior engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements.