chat_with_agent-en

Name: chat_with_agent-en
Author: agentscope-ai

24kstars2.8kforks

How to install chat_with_agent-en?

agentscope-ai/qwenpaw/chat_with_agent-en

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

Installs into the current project.

Summary

Use this skill when you need to consult another agent, ask for help, or involve a specific agent the user asked for.

Files · 1

View on GitHub

SKILL.md

1	# Chat with Agent
2
3	## When to Use
4
5	Use this skill when you need to ask another agent a question, seek help, request a plan, request a review, request decision support, or engage in any form of communication.
6	If the user explicitly asks to talk to a specific agent, you should also use this skill.
7
8	### Should Use
9
10	- You need another agent's expertise, judgment, or second opinion
11	- You need to request a plan, review, or recommendation from an agent
12	- The user explicitly asks a specific agent to participate, assist, or answer
13	- You need to continue an existing agent session while preserving context
14
15	### Should Not Use
16
17	- You can complete the task yourself and the user has not explicitly asked to involve another agent
18	- It is a simple Q&A that does not require a specialized agent
19	- The target agent is unclear — you should ask for clarification or list available agents first
20	- You just received a message from an agent and are about to immediately call back the same agent, which may cause a loop
21
22	## Decision Rules
23
24	1. If the user explicitly requests a specific agent, follow that request — but still look up the agent first; do not guess the ID
25	2. If you can complete the task yourself, do not call another agent
26	3. When continuing a conversation, you must pass `session_id`
27	4. By default, prefer using `list_agents()` and `chat_with_agent(...)` for foreground conversations — do not resort to other methods
28	5. If the task should run in the background, use `submit_to_agent(...)` to submit it, then `check_agent_task(...)` to check the status
29
30	## Usage Flow
31
32	Follow this flow strictly when using this skill:
33
34	1) Ensure your tool list includes both `list_agents()` and `chat_with_agent(...)` built-in tools
35
36	- These two tools are the foundation for communicating with other agents — do not remove or disable them
37	- If you do not have these tools, inform the user that you need them to talk to other agents, and ask the user to add them
38
39	2) Use `list_agents()` to view the currently available agents, and select one by extracting its ID
40
41	- Choose the most appropriate agent based on the user's needs and each agent's description
42	- If no suitable agent is found and you are not the Default Agent, use the Default Agent
43	- Otherwise, inform the user that no suitable agent is available, and suggest they create a new agent or adjust existing agent descriptions for better matching
44
45	3) Call `chat_with_agent(...)` to initiate a foreground conversation. Key parameters include:
46	- `to_agent`: the target agent's ID (note: this is the ID, not the name)
47	- `text`: what you want to say to the target agent
48	- `session_id`: (optional) if you need multiple rounds of conversation with the same agent, pass the same `session_id` starting from the second round to maintain context continuity
49	- `timeout`: (optional) estimated time needed for the foreground wait, to avoid premature timeouts
50
51	4) If the task is better suited for background execution, use the background tool path:
52	- `submit_to_agent(...)`: submit a background task — only requires `to_agent`, `text`, and optionally `session_id`
53	- `check_agent_task(...)`: check task status by `task_id`; returns the final result when complete
54
55	## Minimal Call Examples
56
57	### New Conversation
58
59	```text
60	list_agents()
61
62	chat_with_agent(
63	to_agent="<target_agent_id>",
64	text="[Agent <your_agent_id> requesting] I need your help determining the approach for this issue.",
65	)
66	```
67
68	### Continuing an Existing Conversation
69
70	```text
71	chat_with_agent(
72	to_agent="<target_agent_id>",
73	text="[Agent <your_agent_id> requesting] Please continue expanding on point 2 based on the previous conclusion.",
74	session_id="<previous_session_id>",
75	)
76	```
77
78	### Background Submission and Status Check
79
80	```text
81	submit_to_agent(
82	to_agent="<target_agent_id>",
83	text="[Agent <your_agent_id> requesting] Please complete this longer task in the background.",
84	)
85
86	check_agent_task(
87	task_id="<task_id>",
88	)
89	```
90
91
92	## Important Notes
93
94	- Add a conversation identifier: it is recommended to start your message with:
95
96	```text
97	[Agent <your_agent_id> requesting]
98	```
99	This helps the other agent clearly identify who is speaking, improving communication efficiency and accuracy.
100
101
102	- Reuse sessions wisely: if you need multiple rounds of conversation with the same agent, be sure to pass the same `session_id` to maintain context continuity. Otherwise, each call is treated as a new conversation, and the other agent may not correctly understand your needs. You can obtain the `session_id` from the first round's response, for example:
103
104	```text
105	[SESSION: xxx]
106	```
107
108	where `xxx` is the `session_id` value. This value is typically system-generated and has a long, unique format. Save this `session_id` and

People who liked this also viewed

6 picks

Type

chat_with_agent-en

24kstars2.8kforks

View on GitHub

How to install chat_with_agent-en?

agentscope-ai/qwenpaw/chat_with_agent-en

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

Installs into the current project.

Summary

Use this skill when you need to consult another agent, ask for help, or involve a specific agent the user asked for.

Files · 1

View on GitHub

SKILL.md

1	# Chat with Agent
2
3	## When to Use
4
5	Use this skill when you need to ask another agent a question, seek help, request a plan, request a review, request decision support, or engage in any form of communication.
6	If the user explicitly asks to talk to a specific agent, you should also use this skill.
7
8	### Should Use
9
10	- You need another agent's expertise, judgment, or second opinion
11	- You need to request a plan, review, or recommendation from an agent
12	- The user explicitly asks a specific agent to participate, assist, or answer
13	- You need to continue an existing agent session while preserving context
14
15	### Should Not Use
16
17	- You can complete the task yourself and the user has not explicitly asked to involve another agent
18	- It is a simple Q&A that does not require a specialized agent
19	- The target agent is unclear — you should ask for clarification or list available agents first
20	- You just received a message from an agent and are about to immediately call back the same agent, which may cause a loop
21
22	## Decision Rules
23
24	1. If the user explicitly requests a specific agent, follow that request — but still look up the agent first; do not guess the ID
25	2. If you can complete the task yourself, do not call another agent
26	3. When continuing a conversation, you must pass `session_id`
27	4. By default, prefer using `list_agents()` and `chat_with_agent(...)` for foreground conversations — do not resort to other methods
28	5. If the task should run in the background, use `submit_to_agent(...)` to submit it, then `check_agent_task(...)` to check the status
29
30	## Usage Flow
31
32	Follow this flow strictly when using this skill:
33
34	1) Ensure your tool list includes both `list_agents()` and `chat_with_agent(...)` built-in tools
35
36	- These two tools are the foundation for communicating with other agents — do not remove or disable them
37	- If you do not have these tools, inform the user that you need them to talk to other agents, and ask the user to add them
38
39	2) Use `list_agents()` to view the currently available agents, and select one by extracting its ID
40
41	- Choose the most appropriate agent based on the user's needs and each agent's description
42	- If no suitable agent is found and you are not the Default Agent, use the Default Agent
43	- Otherwise, inform the user that no suitable agent is available, and suggest they create a new agent or adjust existing agent descriptions for better matching
44
45	3) Call `chat_with_agent(...)` to initiate a foreground conversation. Key parameters include:
46	- `to_agent`: the target agent's ID (note: this is the ID, not the name)
47	- `text`: what you want to say to the target agent
48	- `session_id`: (optional) if you need multiple rounds of conversation with the same agent, pass the same `session_id` starting from the second round to maintain context continuity
49	- `timeout`: (optional) estimated time needed for the foreground wait, to avoid premature timeouts
50
51	4) If the task is better suited for background execution, use the background tool path:
52	- `submit_to_agent(...)`: submit a background task — only requires `to_agent`, `text`, and optionally `session_id`
53	- `check_agent_task(...)`: check task status by `task_id`; returns the final result when complete
54
55	## Minimal Call Examples
56
57	### New Conversation
58
59	```text
60	list_agents()
61
62	chat_with_agent(
63	to_agent="<target_agent_id>",
64	text="[Agent <your_agent_id> requesting] I need your help determining the approach for this issue.",
65	)
66	```
67
68	### Continuing an Existing Conversation
69
70	```text
71	chat_with_agent(
72	to_agent="<target_agent_id>",
73	text="[Agent <your_agent_id> requesting] Please continue expanding on point 2 based on the previous conclusion.",
74	session_id="<previous_session_id>",
75	)
76	```
77
78	### Background Submission and Status Check
79
80	```text
81	submit_to_agent(
82	to_agent="<target_agent_id>",
83	text="[Agent <your_agent_id> requesting] Please complete this longer task in the background.",
84	)
85
86	check_agent_task(
87	task_id="<task_id>",
88	)
89	```
90
91
92	## Important Notes
93
94	- Add a conversation identifier: it is recommended to start your message with:
95
96	```text
97	[Agent <your_agent_id> requesting]
98	```
99	This helps the other agent clearly identify who is speaking, improving communication efficiency and accuracy.
100
101
102	- Reuse sessions wisely: if you need multiple rounds of conversation with the same agent, be sure to pass the same `session_id` to maintain context continuity. Otherwise, each call is treated as a new conversation, and the other agent may not correctly understand your needs. You can obtain the `session_id` from the first round's response, for example:
103
104	```text
105	[SESSION: xxx]
106	```
107
108	where `xxx` is the `session_id` value. This value is typically system-generated and has a long, unique format. Save this `session_id` and

People who liked this also viewed

6 picks

Type