dingtalk_channel-en

Name: dingtalk_channel-en
Author: agentscope-ai

24kstars2.8kforks

How to install dingtalk_channel-en?

agentscope-ai/qwenpaw/dingtalk_channel-en

$npx -y skills add agentscope-ai/QwenPaw --skill dingtalk_channel-en

Installs into the current project.

Summary

Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and

Files · 1

View on GitHub

SKILL.md

1	# DingTalk Channel Auto-Connect (Headed Browser)
2
3	This skill automates the creation of a DingTalk application and the binding of a QwenPaw channel using a headed browser.
4
5	## Mandatory Rules
6
7	1. Must launch in headed browser mode:
8
9	```json
10	{"action": "start", "headed": true}
11	```
12
13	2. Must pause when a login gate is encountered:
14	- If the page displays a login screen (e.g., login prompt, QR code login, phone/password login), stop automated operations immediately.
15	- Clearly prompt the user to log in manually first, then wait for the user to reply with "logged in / continue".
16	- Do not proceed with subsequent steps until the user confirms.
17
18	3. Any application configuration change only takes effect after creating a new version and publishing:
19	- After configuring bot-related information, you must publish the bot.
20	- Whether creating a new application or modifying application information (name, description, icon, bot configuration, etc.), you must perform "create new version + publish" at the end.
21	- Do not claim the configuration is active if publishing has not been completed.
22
23	## Pre-Execution Confirmation (Must Do First)
24
25	Before starting automated clicks, initiate a "configuration confirmation" with the user, clearly informing them of customizable fields, image specifications, and default values. Use the following structured confirmation:
26
27	1. Allow the user to customize the following fields:
28	- Application name
29	- Application description
30	- Bot icon image URL or local path
31	- Bot message preview image URL or local path
32
33	2. Clearly state the image specifications (prominently):
34	- Bot icon: JPG/PNG only, `240*240px` or larger, `1:1` ratio, under `2MB`, no rounded corners.
35	- Bot message preview image: format `png/jpeg/jpg`, no more than `2MB`.
36
37	3. Clearly state the default values (used automatically if the user does not specify):
38	- Application name: `QwenPaw`
39	- Application description: `Your personal assistant`
40	- Bot icon: `https://img.alicdn.com/imgextra/i4/O1CN01M0iyHF1FVNzM9qjC0_!!6000000000492-2-tps-254-254.png`
41	- Bot message preview image: `https://img.alicdn.com/imgextra/i4/O1CN01M0iyHF1FVNzM9qjC0_!!6000000000492-2-tps-254-254.png`
42
43	4. If the user provides no custom values, you must first explicitly reply:
44	- "All default settings will be used (QwenPaw / Your personal assistant / default images). Proceeding now."
45
46	## Image Upload Strategy (Both link and path are supported)
47
48	1. If the user provides a local path, use it directly for upload.
49	2. If the user provides an image link, download it to a local temporary file first, then upload.
50	3. The upload action sequence must be:
51	- First click the page upload entry (to trigger the chooser)
52	- Then call `file_upload` with the local path array (`paths_json`)
53	4. If the upload fails due to image specification mismatch (dimensions, ratio, size, format):
54	- Immediately pause automation
55	- Clearly ask the user to manually upload a compliant image
56	- After the user confirms "uploaded / continue", resume from the current step
57
58	### Practical Upload Tips
59
60	1. The `paths_json` of `file_upload` must be a "JSON string array" -- note the escaping:
61
62	```json
63	{
64	"action": "file_upload",
65	"paths_json": "[\"xxx.png\"]",
66	"frame_selector": "iframe[src*=\"/fe/app?isHideOuterFrame=true\"]"
67	}
68	```
69
70	2. If the page is within an iframe, prefer including `frame_selector`; otherwise the upload control may not be found or the chooser may not trigger.
71
72	3. You must click the upload entry before calling `file_upload`; calling it directly will result in:
73	- `No chooser. Click upload then file_upload.`
74
75	4. Common structural features of the bot icon area that can be used for locating elements (examples; these may appear as Chinese UI labels in the DingTalk console):
76	- `text: "* 机器人图标"` (Bot Icon)
77	- `button: "使用应用图标"` (Use App Icon)
78	- `button: "avatar"` (usually contains `img "avatar"` inside)
79
80	5. When the snapshot shows both "使用应用图标" ("Use App Icon") and "avatar", prefer clicking the `avatar` button to trigger the upload, then call `file_upload`.
81
82	## Automation Flow
83
84	### Step 1: Open the DingTalk Developer Console
85
86	1. Launch the browser in headed mode (`headed: true`)
87	2. Navigate to `https://open-dev.dingtalk.com/`
88	3. Call `snapshot` to check if login is required
89
90	If login is required, pause with the following message:
91
92	> Login to the DingTalk Developer Console is required. I have paused automated operations. Please complete the login in the opened browser. Reply "continue" when done,

People who liked this also viewed

6 picks

Type

dingtalk_channel-en

24kstars2.8kforks

View on GitHub

How to install dingtalk_channel-en?

agentscope-ai/qwenpaw/dingtalk_channel-en

$npx -y skills add agentscope-ai/QwenPaw --skill dingtalk_channel-en

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# DingTalk Channel Auto-Connect (Headed Browser)
2
3	This skill automates the creation of a DingTalk application and the binding of a QwenPaw channel using a headed browser.
4
5	## Mandatory Rules
6
7	1. Must launch in headed browser mode:
8
9	```json
10	{"action": "start", "headed": true}
11	```
12
13	2. Must pause when a login gate is encountered:
14	- If the page displays a login screen (e.g., login prompt, QR code login, phone/password login), stop automated operations immediately.
15	- Clearly prompt the user to log in manually first, then wait for the user to reply with "logged in / continue".
16	- Do not proceed with subsequent steps until the user confirms.
17
18	3. Any application configuration change only takes effect after creating a new version and publishing:
19	- After configuring bot-related information, you must publish the bot.
20	- Whether creating a new application or modifying application information (name, description, icon, bot configuration, etc.), you must perform "create new version + publish" at the end.
21	- Do not claim the configuration is active if publishing has not been completed.
22
23	## Pre-Execution Confirmation (Must Do First)
24
25	Before starting automated clicks, initiate a "configuration confirmation" with the user, clearly informing them of customizable fields, image specifications, and default values. Use the following structured confirmation:
26
27	1. Allow the user to customize the following fields:
28	- Application name
29	- Application description
30	- Bot icon image URL or local path
31	- Bot message preview image URL or local path
32
33	2. Clearly state the image specifications (prominently):
34	- Bot icon: JPG/PNG only, `240*240px` or larger, `1:1` ratio, under `2MB`, no rounded corners.
35	- Bot message preview image: format `png/jpeg/jpg`, no more than `2MB`.
36
37	3. Clearly state the default values (used automatically if the user does not specify):
38	- Application name: `QwenPaw`
39	- Application description: `Your personal assistant`
40	- Bot icon: `https://img.alicdn.com/imgextra/i4/O1CN01M0iyHF1FVNzM9qjC0_!!6000000000492-2-tps-254-254.png`
41	- Bot message preview image: `https://img.alicdn.com/imgextra/i4/O1CN01M0iyHF1FVNzM9qjC0_!!6000000000492-2-tps-254-254.png`
42
43	4. If the user provides no custom values, you must first explicitly reply:
44	- "All default settings will be used (QwenPaw / Your personal assistant / default images). Proceeding now."
45
46	## Image Upload Strategy (Both link and path are supported)
47
48	1. If the user provides a local path, use it directly for upload.
49	2. If the user provides an image link, download it to a local temporary file first, then upload.
50	3. The upload action sequence must be:
51	- First click the page upload entry (to trigger the chooser)
52	- Then call `file_upload` with the local path array (`paths_json`)
53	4. If the upload fails due to image specification mismatch (dimensions, ratio, size, format):
54	- Immediately pause automation
55	- Clearly ask the user to manually upload a compliant image
56	- After the user confirms "uploaded / continue", resume from the current step
57
58	### Practical Upload Tips
59
60	1. The `paths_json` of `file_upload` must be a "JSON string array" -- note the escaping:
61
62	```json
63	{
64	"action": "file_upload",
65	"paths_json": "[\"xxx.png\"]",
66	"frame_selector": "iframe[src*=\"/fe/app?isHideOuterFrame=true\"]"
67	}
68	```
69
70	2. If the page is within an iframe, prefer including `frame_selector`; otherwise the upload control may not be found or the chooser may not trigger.
71
72	3. You must click the upload entry before calling `file_upload`; calling it directly will result in:
73	- `No chooser. Click upload then file_upload.`
74
75	4. Common structural features of the bot icon area that can be used for locating elements (examples; these may appear as Chinese UI labels in the DingTalk console):
76	- `text: "* 机器人图标"` (Bot Icon)
77	- `button: "使用应用图标"` (Use App Icon)
78	- `button: "avatar"` (usually contains `img "avatar"` inside)
79
80	5. When the snapshot shows both "使用应用图标" ("Use App Icon") and "avatar", prefer clicking the `avatar` button to trigger the upload, then call `file_upload`.
81
82	## Automation Flow
83
84	### Step 1: Open the DingTalk Developer Console
85
86	1. Launch the browser in headed mode (`headed: true`)
87	2. Navigate to `https://open-dev.dingtalk.com/`
88	3. Call `snapshot` to check if login is required
89
90	If login is required, pause with the following message:
91
92	> Login to the DingTalk Developer Console is required. I have paused automated operations. Please complete the login in the opened browser. Reply "continue" when done,

People who liked this also viewed

6 picks

Type