multi_agent_collaboration-en

Name: multi_agent_collaboration-en
Author: agentscope-ai

24kstars2.8kforks

How to install multi_agent_collaboration-en?

agentscope-ai/qwenpaw/multi_agent_collaboration-en

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

Installs into the current project.

Summary

Use this skill when another agent's expertise or context is needed, or when the user explicitly asks to involve another agent. First list agents, then use qwenpaw agents chat for two-way communication with replies.

Files · 1

View on GitHub

SKILL.md

1	# Multi-Agent Collaboration
2
3	## When to Use
4
5	Use this skill when you need another agent's expertise, context, workspace content, or collaborative support.
6	If the user explicitly asks a specific agent to participate/assist/answer, you should also use this skill.
7
8	### Should Use
9	- The current task is clearly better suited for a specialized agent
10	- You need another agent's workspace / files / context
11	- You need a second opinion or expert review
12	- The user explicitly asks for a specific agent to participate or to invoke another agent
13
14	### Should Not Use
15	- You can complete the task on your own and the user has not explicitly asked to invoke another agent
16	- It is just a normal Q&A that does not require a specialized agent
17	- Information is insufficient -- you should ask the user for clarification first
18	- You just received a message from Agent B -- do not call Agent B again to avoid loops
19
20	## Decision Rules
21
22	1. If the user explicitly requests invoking another agent, prioritize following the request
23	2. Otherwise, if you can do it yourself, do not invoke another agent
24	3. Check agents before invoking -- do not guess IDs
25	4. When context continuation is needed, you must pass `--session-id`
26	5. Do not call back the source agent
27
28	---
29
30	## Most Common Commands
31
32	### 1) First Query Available Agents
33
34	```bash
35	qwenpaw agents list
36	```
37
38	### 2) Start a New Conversation (Real-time Mode)
39
40	```bash
41	qwenpaw agents chat \
42	--from-agent <your_agent> \
43	--to-agent <target_agent> \
44	--text "[Agent <your_agent> requesting] ..."
45	```
46
47	### 3) Submit a Complex Task (Background Mode)
48
49	Complex tasks include: data analysis, report generation, batch processing, external API calls, etc.
50
51	```bash
52	qwenpaw agents chat --background \
53	--from-agent <your_agent> \
54	--to-agent <target_agent> \
55	--text "[Agent <your_agent> requesting] ..."
56	```
57
58	Output:
59	```
60	[TASK_ID: xxx-xxx-xxx]
61	[SESSION: ...]
62	```
63
64	### 4) Query Background Task Status
65
66	```bash
67	qwenpaw agents chat --background --task-id <task_id>
68	```
69
70	Important: Do not query frequently! After submitting a task:
71	1. Do not block - Continue handling other tasks or work
72	2. Wait a reasonable time before querying - Choose based on task complexity:
73	- Simple analysis: query after 10-20 seconds
74	- Complex analysis: query after 30-60 seconds
75	- Batch processing: query after 1-3 minutes
76	3. During the wait - You can reply to the user, handle other requests, or execute other tasks
77
78	### 5) Continue an Existing Conversation
79
80	```bash
81	qwenpaw agents chat \
82	--from-agent <your_agent> \
83	--to-agent <target_agent> \
84	--session-id "<session_id>" \
85	--text "[Agent <your_agent> requesting] ..."
86	```
87
88	Key points:
89	- Not passing `--session-id` = new conversation
90	- Passing `--session-id` = continue conversation (context preserved)
91	- Use `--background` for complex tasks; record the task_id after submission
92
93	---
94
95	## Task Mode Selection
96
97	### Real-time Mode vs Background Mode
98
99	\| Task Type \| Mode to Use \| Command \|
100	\|-----------\|-------------\|---------\|
101	\| Simple quick query \| Real-time mode \| `qwenpaw agents chat` \|
102	\| Complex task (data analysis, batch processing, etc.) \| Background mode \| `qwenpaw agents chat --background` \|
103
104	Examples of complex tasks:
105	- Analyzing large amounts of data or log files
106	- Generating detailed reports
107	- Batch processing files (10+ files)
108	- Calling slow external APIs
109	- Independent tasks that need parallel execution
110
111	Decision criteria: If you are unsure how long a task will take, or if the task is complex, prefer background mode.
112
113	---
114
115	## Minimal Workflow
116
117	### Real-time Mode Workflow
118
119	```
120	1. Determine whether another agent is needed, or whether the user explicitly requested it
121	2. qwenpaw agents list
122	3. qwenpaw agents chat to start a conversation
123	4. Record [SESSION: ...] from the output
124	5. Include --session-id when context continuation is needed later
125	```
126
127	### Background Mode Workflow
128
129	```
130	1. Determine whether the task is complex (data analysis, report generation, etc.)
131	2. qwenpaw agents list
132	3. qwenpaw agents chat --background to submit the task
133	4. Record [TASK_ID: ...] from the output
134	5. Continue handling other work
135	6. Wait a reasonable time (30-60 seconds) before querying status
136	7. Use --background --task-id to query results
137	```
138
139	---
140
141	## Key Rules
142
143	### Required Parameters
144
145	`qwenpaw agents chat` must include all of the following:
146	- `--from-agent`
147	- `--to-agent`
148	- `--text`
149
150	### Identity Prefix
151
152	Messages should begin with the following prefix:
153
154	```text
155	[Agent my_agent requesting] ...
156	```
157
158	### Session Reuse
159
160	The first call will return:
161
162	```text
163	[SESSION: your_agent:to:target_agent:...]
164	```
165
166	For subsequent f

People who liked this also viewed

6 picks

Type

multi_agent_collaboration-en

24kstars2.8kforks

View on GitHub

How to install multi_agent_collaboration-en?

agentscope-ai/qwenpaw/multi_agent_collaboration-en

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Multi-Agent Collaboration
2
3	## When to Use
4
5	Use this skill when you need another agent's expertise, context, workspace content, or collaborative support.
6	If the user explicitly asks a specific agent to participate/assist/answer, you should also use this skill.
7
8	### Should Use
9	- The current task is clearly better suited for a specialized agent
10	- You need another agent's workspace / files / context
11	- You need a second opinion or expert review
12	- The user explicitly asks for a specific agent to participate or to invoke another agent
13
14	### Should Not Use
15	- You can complete the task on your own and the user has not explicitly asked to invoke another agent
16	- It is just a normal Q&A that does not require a specialized agent
17	- Information is insufficient -- you should ask the user for clarification first
18	- You just received a message from Agent B -- do not call Agent B again to avoid loops
19
20	## Decision Rules
21
22	1. If the user explicitly requests invoking another agent, prioritize following the request
23	2. Otherwise, if you can do it yourself, do not invoke another agent
24	3. Check agents before invoking -- do not guess IDs
25	4. When context continuation is needed, you must pass `--session-id`
26	5. Do not call back the source agent
27
28	---
29
30	## Most Common Commands
31
32	### 1) First Query Available Agents
33
34	```bash
35	qwenpaw agents list
36	```
37
38	### 2) Start a New Conversation (Real-time Mode)
39
40	```bash
41	qwenpaw agents chat \
42	--from-agent <your_agent> \
43	--to-agent <target_agent> \
44	--text "[Agent <your_agent> requesting] ..."
45	```
46
47	### 3) Submit a Complex Task (Background Mode)
48
49	Complex tasks include: data analysis, report generation, batch processing, external API calls, etc.
50
51	```bash
52	qwenpaw agents chat --background \
53	--from-agent <your_agent> \
54	--to-agent <target_agent> \
55	--text "[Agent <your_agent> requesting] ..."
56	```
57
58	Output:
59	```
60	[TASK_ID: xxx-xxx-xxx]
61	[SESSION: ...]
62	```
63
64	### 4) Query Background Task Status
65
66	```bash
67	qwenpaw agents chat --background --task-id <task_id>
68	```
69
70	Important: Do not query frequently! After submitting a task:
71	1. Do not block - Continue handling other tasks or work
72	2. Wait a reasonable time before querying - Choose based on task complexity:
73	- Simple analysis: query after 10-20 seconds
74	- Complex analysis: query after 30-60 seconds
75	- Batch processing: query after 1-3 minutes
76	3. During the wait - You can reply to the user, handle other requests, or execute other tasks
77
78	### 5) Continue an Existing Conversation
79
80	```bash
81	qwenpaw agents chat \
82	--from-agent <your_agent> \
83	--to-agent <target_agent> \
84	--session-id "<session_id>" \
85	--text "[Agent <your_agent> requesting] ..."
86	```
87
88	Key points:
89	- Not passing `--session-id` = new conversation
90	- Passing `--session-id` = continue conversation (context preserved)
91	- Use `--background` for complex tasks; record the task_id after submission
92
93	---
94
95	## Task Mode Selection
96
97	### Real-time Mode vs Background Mode
98
99	\| Task Type \| Mode to Use \| Command \|
100	\|-----------\|-------------\|---------\|
101	\| Simple quick query \| Real-time mode \| `qwenpaw agents chat` \|
102	\| Complex task (data analysis, batch processing, etc.) \| Background mode \| `qwenpaw agents chat --background` \|
103
104	Examples of complex tasks:
105	- Analyzing large amounts of data or log files
106	- Generating detailed reports
107	- Batch processing files (10+ files)
108	- Calling slow external APIs
109	- Independent tasks that need parallel execution
110
111	Decision criteria: If you are unsure how long a task will take, or if the task is complex, prefer background mode.
112
113	---
114
115	## Minimal Workflow
116
117	### Real-time Mode Workflow
118
119	```
120	1. Determine whether another agent is needed, or whether the user explicitly requested it
121	2. qwenpaw agents list
122	3. qwenpaw agents chat to start a conversation
123	4. Record [SESSION: ...] from the output
124	5. Include --session-id when context continuation is needed later
125	```
126
127	### Background Mode Workflow
128
129	```
130	1. Determine whether the task is complex (data analysis, report generation, etc.)
131	2. qwenpaw agents list
132	3. qwenpaw agents chat --background to submit the task
133	4. Record [TASK_ID: ...] from the output
134	5. Continue handling other work
135	6. Wait a reasonable time (30-60 seconds) before querying status
136	7. Use --background --task-id to query results
137	```
138
139	---
140
141	## Key Rules
142
143	### Required Parameters
144
145	`qwenpaw agents chat` must include all of the following:
146	- `--from-agent`
147	- `--to-agent`
148	- `--text`
149
150	### Identity Prefix
151
152	Messages should begin with the following prefix:
153
154	```text
155	[Agent my_agent requesting] ...
156	```
157
158	### Session Reuse
159
160	The first call will return:
161
162	```text
163	[SESSION: your_agent:to:target_agent:...]
164	```
165
166	For subsequent f

People who liked this also viewed

6 picks

Type