[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CRXEDFTNYARFS63HVB9SVX":3,"skill-same:01M6CRXEDFTNYARFS63HVB9SVX":73},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":58,"install":59,"resources":72},"01M6CRXEDFTNYARFS63HVB9SVX","multi_agent_collaboration",null,"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.","agentscope-ai\u002FQwenPaw","agentscope-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211762292?v=4","01M6CRT6543BZGGVK3P85GC08Q","AgentScope-AI","01M6CRT698G78F0SPC659YEK6E",37745,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fmulti_agent_collaboration-en\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"multi agent collaboration","collaboration","agent collaboration","multi agent","multi","when","qwenpaw","expertise","for","replies","with","chat","use","user","context","list","first","communication","2026-11-10 10:12:30",false,"---\nname: multi_agent_collaboration\ndescription: 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.\nmetadata:\n  builtin_skill_version: \"1.4\"\n  qwenpaw:\n    emoji: \"?\"\n---\n\n# Multi-Agent Collaboration\n\n## When to Use\n\nUse this skill when you **need another agent's expertise, context, workspace content, or collaborative support**.\nIf the **user explicitly asks a specific agent to participate\u002Fassist\u002Fanswer**, you should also use this skill.\n\n### Should Use\n- The current task is clearly better suited for a specialized agent\n- You need another agent's workspace \u002F files \u002F context\n- You need a second opinion or expert review\n- The user explicitly asks for a specific agent to participate or to invoke another agent\n\n### Should Not Use\n- You can complete the task on your own and the user has not explicitly asked to invoke another agent\n- It is just a normal Q&A that does not require a specialized agent\n- Information is insufficient -- you should ask the user for clarification first\n- You just received a message from Agent B -- **do not call Agent B again** to avoid loops\n\n## Decision Rules\n\n1. **If the user explicitly requests invoking another agent, prioritize following the request**\n2. **Otherwise, if you can do it yourself, do not invoke another agent**\n3. **Check agents before invoking -- do not guess IDs**\n4. **When context continuation is needed, you must pass `--session-id`**\n5. **Do not call back the source agent**\n\n---\n\n## Most Common Commands\n\n### 1) First Query Available Agents\n\n```bash\nqwenpaw agents list\n```\n\n### 2) Start a New Conversation (Real-time Mode)\n\n```bash\nqwenpaw agents chat \\\n  --from-agent \u003Cyour_agent> \\\n  --to-agent \u003Ctarget_agent> \\\n  --text \"[Agent \u003Cyour_agent> requesting] ...\"\n```\n\n### 3) Submit a Complex Task (Background Mode)\n\n**Complex tasks** include: data analysis, report generation, batch processing, external API calls, etc.\n\n```bash\nqwenpaw agents chat --background \\\n  --from-agent \u003Cyour_agent> \\\n  --to-agent \u003Ctarget_agent> \\\n  --text \"[Agent \u003Cyour_agent> requesting] ...\"\n```\n\n**Output**:\n```\n[TASK_ID: xxx-xxx-xxx]\n[SESSION: ...]\n```\n\n### 4) Query Background Task Status\n\n```bash\nqwenpaw agents chat --background --task-id \u003Ctask_id>\n```\n\n**Important**: Do not query frequently! After submitting a task:\n1. **Do not block** - Continue handling other tasks or work\n2. **Wait a reasonable time before querying** - Choose based on task complexity:\n   - Simple analysis: query after 10-20 seconds\n   - Complex analysis: query after 30-60 seconds\n   - Batch processing: query after 1-3 minutes\n3. **During the wait** - You can reply to the user, handle other requests, or execute other tasks\n\n### 5) Continue an Existing Conversation\n\n```bash\nqwenpaw agents chat \\\n  --from-agent \u003Cyour_agent> \\\n  --to-agent \u003Ctarget_agent> \\\n  --session-id \"\u003Csession_id>\" \\\n  --text \"[Agent \u003Cyour_agent> requesting] ...\"\n```\n\n**Key points**:\n- Not passing `--session-id` = new conversation\n- Passing `--session-id` = continue conversation (context preserved)\n- Use `--background` for complex tasks; record the task_id after submission\n\n---\n\n## Task Mode Selection\n\n### Real-time Mode vs Background Mode\n\n| Task Type | Mode to Use | Command |\n|-----------|-------------|---------|\n| Simple quick query | Real-time mode | `qwenpaw agents chat` |\n| Complex task (data analysis, batch processing, etc.) | Background mode | `qwenpaw agents chat --background` |\n\n**Examples of complex tasks**:\n- Analyzing large amounts of data or log files\n- Generating detailed reports\n- Batch processing files (10+ files)\n- Calling slow external APIs\n- Independent tasks that need parallel execution\n\n**Decision criteria**: If you are unsure how long a task will take, or if the task is complex, prefer background mode.\n\n---\n\n## Minimal Workflow\n\n### Real-time Mode Workflow\n\n```\n1. Determine whether another agent is needed, or whether the user explicitly requested it\n2. qwenpaw agents list\n3. qwenpaw agents chat to start a conversation\n4. Record [SESSION: ...] from the output\n5. Include --session-id when context continuation is needed later\n```\n\n### Background Mode Workflow\n\n```\n1. Determine whether the task is complex (data analysis, report generation, etc.)\n2. qwenpaw agents list\n3. qwenpaw agents chat --background to submit the task\n4. Record [TASK_ID: ...] from the output\n5. Continue handling other work\n6. Wait a reasonable time (30-60 seconds) before querying status\n7. Use --background --task-id to query results\n```\n\n---\n\n## Key Rules\n\n### Required Parameters\n\n`qwenpaw agents chat` must include all of the following:\n- `--from-agent`\n- `--to-agent`\n- `--text`\n\n### Identity Prefix\n\nMessages should begin with the following prefix:\n\n```text\n[Agent my_agent requesting] ...\n```\n\n### Session Reuse\n\nThe first call will return:\n\n```text\n[SESSION: your_agent:to:target_agent:...]\n```\n\nFor subsequent follow-ups, you must copy this session_id and pass it via `--session-id`.\n\n---\n\n## Brief Examples\n\n### User Explicitly Requests Invoking Another Agent\n\n```bash\nqwenpaw agents list\n\nqwenpaw agents chat \\\n  --from-agent scheduler_bot \\\n  --to-agent finance_bot \\\n  --text \"[Agent scheduler_bot requesting] User explicitly asked to consult finance_bot. Please answer what pending financial tasks are there.\"\n```\n\n### New Conversation\n\n```bash\nqwenpaw agents chat \\\n  --from-agent scheduler_bot \\\n  --to-agent finance_bot \\\n  --text \"[Agent scheduler_bot requesting] What pending financial tasks are there today?\"\n```\n\n### Continue Conversation\n\n```bash\nqwenpaw agents chat \\\n  --from-agent scheduler_bot \\\n  --to-agent finance_bot \\\n  --session-id \"scheduler_bot:to:finance_bot:1710912345:a1b2c3d4\" \\\n  --text \"[Agent scheduler_bot requesting] Expand on item 2\"\n```\n\n---\n\n## Common Mistakes\n\n### Mistake 1: Not checking agents first\n\nDo not guess agent IDs. First run:\n\n```bash\nqwenpaw agents list\n```\n\n### Mistake 2: Wanting to continue a conversation but not passing session-id\n\nThis will create a new conversation, losing context.\n\n### Mistake 3: Calling back the source agent\n\nIf you just received a message from Agent B, do not call Agent B again.\n\n---\n\n## Optional Commands\n\n### View Existing Sessions\n\n```bash\nqwenpaw chats list --agent-id \u003Cyour_agent>\n```\n\n### Streaming Output\n\n```bash\nqwenpaw agents chat \\\n  --from-agent \u003Cyour_agent> \\\n  --to-agent \u003Ctarget_agent> \\\n  --mode stream \\\n  --text \"[Agent \u003Cyour_agent> requesting] ...\"\n```\n\n### JSON Output\n\n```bash\nqwenpaw agents chat \\\n  --from-agent \u003Cyour_agent> \\\n  --to-agent \u003Ctarget_agent> \\\n  --json-output \\\n  --text \"[Agent \u003Cyour_agent> requesting] ...\"\n```\n\n---\n\n## Full Parameter Reference\n\n### qwenpaw agents list\n\n**Parameters**:\n- `--base-url` (optional): Override the API address\n\n**No required parameters** -- just run it directly.\n\n### qwenpaw agents chat\n\n**Required parameters** (real-time mode):\n- `--from-agent`: Sender agent ID\n- `--to-agent`: Target agent ID\n- `--text`: Message content\n\n**Background task parameters**:\n- `--background`: Background task mode\n- `--task-id`: Query task status (used together with --background)\n\n**Optional parameters**:\n- `--session-id`: Reuse session context (copy from previous output)\n- `--new-session`: Force create a new session (even if session-id is passed)\n- `--mode`: stream (streaming) or final (complete, default)\n- `--timeout`: Timeout in seconds (default 300)\n- `--json-output`: Output full JSON instead of plain text\n- `--base-url`: Override the API address\n\n---\n\n## Background Task Mode Details\n\n### When to Use Background Mode?\n\nWhen the task is a **complex task**, use `--background` to submit it to the background:\n\n**Should use background mode**:\n- Data analysis (analyzing logs, computing statistics)\n- Report generation (generating long reports or documents)\n- Batch processing (processing multiple files)\n- External API calls (calling slow services)\n- Complex tasks with uncertain duration\n\n**Does not need background mode**:\n- Simple quick queries\n- Tasks that are clearly going to complete quickly\n\n### Background Task Examples\n\n#### Submitting a Complex Task\n\n```bash\nqwenpaw agents chat --background \\\n  --from-agent scheduler \\\n  --to-agent data_analyst \\\n  --text \"[Agent scheduler requesting] Analyze user behavior in \u002Fdata\u002Flogs\u002F2026-03-26.log and generate a detailed report\"\n```\n\n**Output**:\n```\n[TASK_ID: 20802ea3-832d-4fb4-86f0-666ad79fcc80]\n[SESSION: scheduler:to:data_analyst:1774516703206:ec02e542]\n\n✅ Task submitted successfully\n\nCheck status with:\n  qwenpaw agents chat --background --task-id 20802ea3-...\n```\n\n#### Querying Task Status\n\n**Important**: Do not block after submitting!\n\n1. **Continue handling other work** - Reply to other user questions, execute other tasks\n2. **Query at the right time** - After finishing other work, or when the user asks about progress\n3. **If you must wait** - Use a reasonable interval (10-60 seconds); do not query immediately\n\n```bash\n# Method 1: Query after handling other tasks (recommended)\n# After submitting the task, continue with the user's other requests\n# Query at an appropriate time:\nqwenpaw agents chat --background \\\n  --task-id 20802ea3-832d-4fb4-86f0-666ad79fcc80\n\n# Method 2: If you must wait, use a reasonable interval\nsleep 30 && qwenpaw agents chat --background \\\n  --task-id 20802ea3-832d-4fb4-86f0-666ad79fcc80\n```\n\n**Status Descriptions**:\n\nTask status has two layers:\n- **Outer status** (API response): `submitted` -> `pending` -> `running` -> `finished`\n- **Inner status** (only when outer status is `finished`): `completed` (success) or `failed` (failure)\n\n**Possible outputs**:\n\n1. **Submitted** (may be seen when querying immediately after submission):\n```\n[TASK_ID: 20802ea3-832d-4fb4-86f0-666ad79fcc80]\n[STATUS: submitted]\n\n? Task submitted, waiting to start...\n\n? Don't wait - continue with other work!\n   Check again in a few seconds:\n  qwenpaw agents chat --background --task-id 20802ea3-...\n```\n\n2. **Pending**:\n```\n[TASK_ID: 20802ea3-832d-4fb4-86f0-666ad79fcc80]\n[STATUS: pending]\n\n⏸️  Task is pending in queue...\n\n? Don't wait - handle other work first!\n   Check again in a few seconds:\n  qwenpaw agents chat --background --task-id 20802ea3-...\n```\n\n4. **Running**:\n```\n[TASK_ID: 20802ea3-832d-4fb4-86f0-666ad79fcc80]\n[STATUS: running]\n\n⏳ Task is still running...\n   Started at: 1774516703\n\n? Don't wait - continue with other tasks first!\n   Check again later (10-30s):\n  qwenpaw agents chat --background --task-id 20802ea3-...\n```\n\n5. **Completed successfully**:\n```\n[TASK_ID: 20802ea3-832d-4fb4-86f0-666ad79fcc80]\n[STATUS: finished]\n\n✅ Task completed\n\n(Task result content...)\n```\n\n6. **Failed**:\n```\n[TASK_ID: 20802ea3-832d-4fb4-86f0-666ad79fcc80]\n[STATUS: finished]\n\n❌ Task failed\n\nError: (Error message...)\n```\n\n### Query Interval Strategy\n\n**Do not query frequently!** After submitting a task, you should:\n\n1. **Continue handling other work** - Do not block; go complete other tasks\n2. **Wait a reasonable time before querying** - Choose the interval based on task complexity\n3. **Avoid blocking the current flow** - This is the core value of background tasks\n\n| Task Type | Suggested First Query | Subsequent Interval | What to Do While Waiting |\n|-----------|----------------------|--------------------|-----------------------|\n| Simple analysis | After 10 seconds | 5-10 seconds | Handle other user requests |\n| Complex analysis | After 30 seconds | 10-20 seconds | Complete other parts of the current conversation |\n| Batch processing | After 1 minute | 20-30 seconds | Execute other independent tasks |\n| Very large tasks | After 2 minutes | 30-60 seconds | Continue with the user's other work |\n\n#### Recommended Approach\n\n**Method 1: Query after handling other tasks** (recommended)\n```bash\n# 1. Submit the task, record the task_id\nqwenpaw agents chat --background ...\n# Returns task_id\n\n# 2. Continue handling the user's other requests or tasks\n# (e.g., answer other questions, perform other operations)\n\n# 3. Query the result at an appropriate time\n# (e.g., after finishing the current task, or when the user asks about progress)\nqwenpaw agents chat --background --task-id \u003Cid>\n```\n\n**Method 2: Timed polling** (if you must wait)\n```bash\n# Incrementally increasing intervals, fast first then slow\nsleep 10 && qwenpaw agents chat --background --task-id \u003Cid>\nsleep 20 && qwenpaw agents chat --background --task-id \u003Cid>\nsleep 30 && qwenpaw agents chat --background --task-id \u003Cid>\n```\n\n#### Do Not Do This\n\n```bash\n# Wrong: querying too frequently\nwhile true; do\n    qwenpaw agents chat --background --task-id \u003Cid>\n    sleep 1  # Too frequent!\ndone\n```\n\n---\n\n## Help Information\n\nUse `-h` at any time to view detailed help:\n\n```bash\nqwenpaw agents -h\nqwenpaw agents list -h\nqwenpaw agents chat -h\n```\n","# Multi-Agent Collaboration\n\n## When to Use\n\nUse this skill when you **need another agent's expertise, context, workspace content, or collaborative support**.\nIf the **user explicitly asks a specific agent to participate\u002Fassist\u002Fanswer**, you should also use this skill.\n\n### Should Use\n- The current task is clearly better suited for a specialized agent\n- You need another agent's workspace \u002F files \u002F context\n- You need a second opinion or expert review\n- The user explicitly asks for a specific agent to participate or to invoke another agent\n\n### Should Not Use\n- You can complete the task on your own and the user has not explicitly asked to invoke another agent\n- It is just a normal Q&A that does not require a specialized agent\n- Information is insufficient -- you should ask the user for clarification first\n- You just received a message from Agent B -- **do not call Agent B again** to avoid loops\n\n## Decision Rules\n\n1. **If the user explicitly requests invoking another agent, prioritize following the request**\n2. **Otherwise, if you can do it yourself, do not invoke another agent**\n3. **Check agents before invoking -- do not guess IDs**\n4. **When context continuation is needed, you must pass `--session-id`**\n5. **Do not call back the source agent**\n\n---\n\n## Most Common Commands\n\n### 1) First Query Available Agents\n\n```bash\nqwenpaw agents list\n```\n\n### 2) Start a New Conversation (Real-time Mode)\n\n```bash\nqwenpaw agents chat \\\n  --from-agent \u003Cyour_agent> \\\n  --to-agent \u003Ctarget_agent> \\\n  --text \"[Agent \u003Cyour_agent> requesting] ...\"\n```\n\n### 3) Submit a Complex Task (Background Mode)\n\n**Complex tasks** include: data analysis, report generation, batch processing, external API calls, etc.\n\n```bash\nqwenpaw agents chat --background \\\n  --from-agent \u003Cyour_agent> \\\n  --to-agent \u003Ctarget_agent> \\\n  --text \"[Agent \u003Cyour_agent> requesting] ...\"\n```\n\n**Output**:\n```\n[TASK_ID: xxx-xxx-xxx]\n[SESSION: ...]\n```\n\n### 4) Query Background Task Status\n\n```bash\nqwenpaw agents chat --background --task-id \u003Ctask_id>\n```\n\n**Important**: Do not query frequently! After submitting a task:\n1. **Do not block** - Continue handling other tasks or work\n2. **Wait a reasonable time before querying** - Choose based on task complexity:\n   - Simple analysis: query after 10-20 seconds\n   - Complex analysis: query after 30-60 seconds\n   - Batch processing: query after 1-3 minutes\n3. **During the wait** - You can reply to the user, handle other requests, or execute other tasks\n\n### 5) Continue an Existing Conversation\n\n```bash\nqwenpaw agents chat \\\n  --from-agent \u003Cyour_agent> \\\n  --to-agent \u003Ctarget_agent> \\\n  --session-id \"\u003Csession_id>\" \\\n  --text \"[Agent \u003Cyour_agent> requesting] ...\"\n```\n\n**Key points**:\n- Not passing `--session-id` = new conversation\n- Passing `--session-id` = continue conversation (context preserved)\n- Use `--background` for complex tasks; record the task_id after submission\n\n---\n\n## Task Mode Selection\n\n### Real-time Mode vs Background Mode\n\n| Task Type | Mode to Use | Command |\n|-----------|-------------|---------|\n| Simple quick query | Real-time mode | `qwenpaw agents chat` |\n| Complex task (data analysis, batch processing, etc.) | Background mode | `qwenpaw agents chat --background` |\n\n**Examples of complex tasks**:\n- Analyzing large amounts of data or log files\n- Generating detailed reports\n- Batch processing files (10+ files)\n- Calling slow external APIs\n- Independent tasks that need parallel execution\n\n**Decision criteria**: If you are unsure how long a task will take, or if the task is complex, prefer background mode.\n\n---\n\n## Minimal Workflow\n\n### Real-time Mode Workflow\n\n```\n1. Determine whether another agent is needed, or whether the user explicitly requested it\n2. qwenpaw agents list\n3. qwenpaw agents chat to start a conversation\n4. Record [SESSION: ...] from the output\n5. Include --session-id when context continuation is needed later\n```\n\n### Background Mode Workflow\n\n```\n1. Determine whether the task is complex (data analysis, report generation, etc.)\n2. qwenpaw agents list\n3. qwenpaw agents chat --background to submit the task\n4. Record [TASK_ID: ...] from the output\n5. Continue handling other work\n6. Wait a reasonable time (30-60 seconds) before querying status\n7. Use --background --task-id to query results\n```\n\n---\n\n## Key Rules\n\n### Required Parameters\n\n`qwenpaw agents chat` must include all of the following:\n- `--from-agent`\n- `--to-agent`\n- `--text`\n\n### Identity Prefix\n\nMessages should begin with the following prefix:\n\n```text\n[Agent my_agent requesting] ...\n```\n\n### Session Reuse\n\nThe first call will return:\n\n```text\n[SESSION: your_agent:to:target_agent:...]\n```\n\nFor subsequent follow-ups, you must copy this session_id and pass it via `--session-id`.\n\n---\n\n## Brief Examples\n\n### User Explicitly Requests Invoking Another Agent\n\n```bash\nqwenpaw agents list\n\nqwenpaw agents chat \\\n  --from-agent scheduler_bot \\\n  --to-agent finance_bot \\\n  --text \"[Agent scheduler_bot requesting] User explicitly asked to consult finance_bot. Please answer what pending financial tasks are there.\"\n```\n\n### New Conversation\n\n```bash\nqwenpaw agents chat \\\n  --from-agent scheduler_bot \\\n  --to-agent finance_bot \\\n  --text \"[Agent scheduler_bot requesting] What pending financial tasks are there today?\"\n```\n\n### Continue Conversation\n\n```bash\nqwenpaw agents chat \\\n  --from-agent scheduler_bot \\\n  --to-agent finance_bot \\\n  --session-id \"scheduler_bot:to:finance_bot:1710912345:a1b2c3d4\" \\\n  --text \"[Agent scheduler_bot requesting] Expand on item 2\"\n```\n\n---\n\n## Common Mistakes\n\n### Mistake 1: Not checking agents first\n\nDo not guess agent IDs. First run:\n\n```bash\nqwenpaw agents list\n```\n\n### Mistake 2: Wanting to continue a conversation but not passing session-id\n\nThis will create a new conversation, losing context.\n\n### Mistake 3: Calling back the source agent\n\nIf you just received a message from Agent B, do not call Agent B again.\n\n---\n\n## Optional Commands\n\n### View Existing Sessions\n\n```bash\nqwenpaw chats list --agent-id \u003Cyour_agent>\n```\n\n### Streaming Output\n\n```bash\nqwenpaw agents chat \\\n  --from-agent \u003Cyour_agent> \\\n  --to-agent \u003Ctarget_agent> \\\n  --mode stream \\\n  --text \"[Agent \u003Cyour_agent> requesting] ...\"\n```\n\n### JSON Output\n\n```bash\nqwenpaw agents chat \\\n  --from-agent \u003Cyour_agent> \\\n  --to-agent \u003Ctarget_agent> \\\n  --json-output \\\n  --text \"[Agent \u003Cyour_agent> requesting] ...\"\n```\n\n---\n\n## Full Parameter Reference\n\n### qwenpaw agents list\n\n**Parameters**:\n- `--base-url` (optional): Override the API address\n\n**No required parameters** -- just run it directly.\n\n### qwenpaw agents chat\n\n**Required parameters** (real-time mode):\n- `--from-agent`: Sender agent ID\n- `--to-agent`: Target agent ID\n- `--text`: Message content\n\n**Background task parameters**:\n- `--background`: Background task mode\n- `--task-id`: Query task status (used together with --background)\n\n**Optional parameters**:\n- `--session-id`: Reuse session context (copy from previous output)\n- `--new-session`: Force create a new session (even if session-id is passed)\n- `--mode`: stream (streaming) or final (complete, default)\n- `--timeout`: Timeout in seconds (default 300)\n- `--json-output`: Output full JSON instead of plain text\n- `--base-url`: Override the API address\n\n---\n\n## Background Task Mode Details\n\n### When to Use Background Mode?\n\nWhen the task is a **complex task**, use `--background` to submit it to the background:\n\n**Should use background mode**:\n- Data analysis (analyzing logs, computing statistics)\n- Report generation (generating long reports or documents)\n- Batch processing (processing multiple files)\n- External API calls (calling slow services)\n- Complex tasks with uncertain duration\n\n**Does not need background mode**:\n- Simple quick queries\n- Tasks that are clearly going to complete quickly\n\n### Background Task Examples\n\n#### Submitting a Complex Task\n\n```bash\nqwenpaw agents chat --background \\\n  --from-agent scheduler \\\n  --to-agent data_analyst \\\n  --text \"[Agent scheduler requesting] Analyze user behavior in \u002Fdata\u002Flogs\u002F2026-03-26.log and generate a detailed report\"\n```\n\n**Output**:\n```\n[TASK_ID: 20802ea3-832d-4fb4-86f0-666ad79fcc80]\n[SESSION: scheduler:to:data_analyst:1774516703206:ec02e542]\n\n✅ Task submitted successfully\n\nCheck status with:\n  qwenpaw agents chat --background --task-id 20802ea3-...\n```\n\n#### Querying Task Status\n\n**Important**: Do not block after submitting!\n\n1. **Continue handling other work** - Reply to other user questions, execute other tasks\n2. **Query at the right time** - After finishing other work, or when the user asks about progress\n3. **If you must wait** - Use a reasonable interval (10-60 seconds); do not query immediately\n\n```bash\n# Method 1: Query after handling other tasks (recommended)\n# After submitting the task, continue with the user's other requests\n# Query at an appropriate time:\nqwenpaw agents chat --background \\\n  --task-id 20802ea3-832d-4fb4-86f0-666ad79fcc80\n\n# Method 2: If you must wait, use a reasonable interval\nsleep 30 && qwenpaw agents chat --background \\\n  --task-id 20802ea3-832d-4fb4-86f0-666ad79fcc80\n```\n\n**Status Descriptions**:\n\nTask status has two layers:\n- **Outer status** (API response): `submitted` -> `pending` -> `running` -> `finished`\n- **Inner status** (only when outer status is `finished`): `completed` (success) or `failed` (failure)\n\n**Possible outputs**:\n\n1. **Submitted** (may be seen when querying immediately after submission):\n```\n[TASK_ID: 20802ea3-832d-4fb4-86f0-666ad79fcc80]\n[STATUS: submitted]\n\n? Task submitted, waiting to start...\n\n? Don't wait - continue with other work!\n   Check again in a few seconds:\n  qwenpaw agents chat --background --task-id 20802ea3-...\n```\n\n2. **Pending**:\n```\n[TASK_ID: 20802ea3-832d-4fb4-86f0-666ad79fcc80]\n[STATUS: pending]\n\n⏸️  Task is pending in queue...\n\n? Don't wait - handle other work first!\n   Check again in a few seconds:\n  qwenpaw agents chat --background --task-id 20802ea3-...\n```\n\n4. **Running**:\n```\n[TASK_ID: 20802ea3-832d-4fb4-86f0-666ad79fcc80]\n[STATUS: running]\n\n⏳ Task is still running...\n   Started at: 1774516703\n\n? Don't wait - continue with other tasks first!\n   Check again later (10-30s):\n  qwenpaw agents chat --background --task-id 20802ea3-...\n```\n\n5. **Completed successfully**:\n```\n[TASK_ID: 20802ea3-832d-4fb4-86f0-666ad79fcc80]\n[STATUS: finished]\n\n✅ Task completed\n\n(Task result content...)\n```\n\n6. **Failed**:\n```\n[TASK_ID: 20802ea3-832d-4fb4-86f0-666ad79fcc80]\n[STATUS: finished]\n\n❌ Task failed\n\nError: (Error message...)\n```\n\n### Query Interval Strategy\n\n**Do not query frequently!** After submitting a task, you should:\n\n1. **Continue handling other work** - Do not block; go complete other tasks\n2. **Wait a reasonable time before querying** - Choose the interval based on task complexity\n3. **Avoid blocking the current flow** - This is the core value of background tasks\n\n| Task Type | Suggested First Query | Subsequent Interval | What to Do While Waiting |\n|-----------|----------------------|--------------------|-----------------------|\n| Simple analysis | After 10 seconds | 5-10 seconds | Handle other user requests |\n| Complex analysis | After 30 seconds | 10-20 seconds | Complete other parts of the current conversation |\n| Batch processing | After 1 minute | 20-30 seconds | Execute other independent tasks |\n| Very large tasks | After 2 minutes | 30-60 seconds | Continue with the user's other work |\n\n#### Recommended Approach\n\n**Method 1: Query after handling other tasks** (recommended)\n```bash\n# 1. Submit the task, record the task_id\nqwenpaw agents chat --background ...\n# Returns task_id\n\n# 2. Continue handling the user's other requests or tasks\n# (e.g., answer other questions, perform other operations)\n\n# 3. Query the result at an appropriate time\n# (e.g., after finishing the current task, or when the user asks about progress)\nqwenpaw agents chat --background --task-id \u003Cid>\n```\n\n**Method 2: Timed polling** (if you must wait)\n```bash\n# Incrementally increasing intervals, fast first then slow\nsleep 10 && qwenpaw agents chat --background --task-id \u003Cid>\nsleep 20 && qwenpaw agents chat --background --task-id \u003Cid>\nsleep 30 && qwenpaw agents chat --background --task-id \u003Cid>\n```\n\n#### Do Not Do This\n\n```bash\n# Wrong: querying too frequently\nwhile true; do\n    qwenpaw agents chat --background --task-id \u003Cid>\n    sleep 1  # Too frequent!\ndone\n```\n\n---\n\n## Help Information\n\nUse `-h` at any time to view detailed help:\n\n```bash\nqwenpaw agents -h\nqwenpaw agents list -h\nqwenpaw agents chat -h\n```\n",{"name":5,"metadata":47,"description":7},{"qwenpaw":48,"builtin_skill_version":50},{"emoji":49},"?","1.4","main","c26d31c0688aa9cce9bc1aef688177d2e14e25df","src\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fmulti_agent_collaboration-en",3285,"https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw","http:\u002F\u002Fqwenpaw.agentscope.io\u002F","https:\u002F\u002Fgithub.com\u002Fagentscope-ai","2026-11-13 15:25:45",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add agentscope-ai\u002FQwenPaw --skill multi_agent_collaboration",{"tool":65,"command":66},"bunx","bunx skills add agentscope-ai\u002FQwenPaw --skill multi_agent_collaboration",{"tool":68,"command":69},"pnpm","pnpm dlx skills add agentscope-ai\u002FQwenPaw --skill multi_agent_collaboration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Fskills\u002Fmulti_agent_collaboration-en\u002FSKILL.md",true,[],[74,88,101,111,123,141],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":81,"publishedAt":42},"01M6CRZ8QQ6RWS9P0PBDZDZSY8","portable-qoder","A stable standalone Qoder fixture Skill.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fportability\u002Fqoder-mini\u002Fskills\u002Fportable-qoder\u002FSKILL.md",[80],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[82,83,84,85,86,87],"portable","qoder","portable qoder","fixture skill","fixture","standalone",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":99,"publishedAt":42},"01M6CRZ61PNG319SVCYZZVC7HA","report","Report fixture status.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fportability\u002Fqoder-mini\u002Fplugins\u002Fcustom\u002Fmini-plugin-0.1.0\u002Fskills\u002Freport\u002FSKILL.md",[94],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000034","行政与办公人员","PROFESSION","适用职业",[90,100,86],"status",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":108,"publishedAt":42},"01M6CRZ3PTN8ZGW30RHF081Z00","portable-skill","A stable standalone Codex fixture Skill.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fportability\u002Fcodex-mini\u002Fskills\u002Fportable-skill\u002FSKILL.md",[107],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[82,109,110,85,86,87],"portable skill","codex",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":42},"01M6CRZ1DNK71D5M63SQ3SPTMH","building-native-ui","Build a small native interface.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fportability\u002Fcodex-mini\u002Fplugins\u002Fcache\u002Fmini-market\u002Fexpo\u002F1.0.0\u002Fskills\u002Fbuilding-native-ui\u002FSKILL.md",[],[118,119,120,121,122],"native","ui","building native ui","build","interface",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":130,"publishedAt":42},"01M6CRYYTRG56E165X66FRWZC8","browser_visible","当用户需要控制 browser 的浏览器启动方式时，使用本 skill。browser 默认由 Playwright 直接管理、不开放调试端口（需让其他本地工具附加时显式传 `cdp_port`）；`headed` 控制是否显示窗口，`private_mode` 保留用于兼容、不再改变默认行为，`browser_args` 传入额外的 Chromium 启动参数，`executable_path` 指定自定义浏览器可执行文件路径。","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Ftools\u002Fdeprecated_browser\u002Fskills\u002Fbrowser_visible-zh\u002FSKILL.md",[129],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[131,132,133,134,135,136,137,138,139,140],"browser visible","browser","path","chromium","playwright","cdp","port","文件","工具","mode",{"skillNo":142,"name":125,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":147,"publishedAt":42},"01M6CRYVQ9DMBB2EN4JFWC4R7F","Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit `cdp_port` to let another local tool attach); `headed` controls whether the window is visible, and `private_mode` is kept for backward compatibility and no longer changes the default.","https:\u002F\u002Fgithub.com\u002Fagentscope-ai\u002FQwenPaw\u002Fblob\u002Fmain\u002Fsrc\u002Fqwenpaw\u002Fagents\u002Ftools\u002Fdeprecated_browser\u002Fskills\u002Fbrowser_visible-en\u002FSKILL.md",[146],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[131,132,37,148,149,36,150,151,152,29,153,154,155,137,140,32,156,157,158,136,159,135],"compatibility","default","tool","debugging","launch","local","control","controls","changes","window","managed","attach"]