阿里云 CLI 中文文档镜像检索与命令辅助:先走章节索引,再下钻正文页面,给出命令前必须有本地文档证据。
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill to proactively send a one-way message to a user/session/channel, usually only when the user explicitly asks to send to a channel/session or when proactive notification is needed. First query sessions with qwenpaw chats list, then push with qwenpaw channels send.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Use this skill only when the user explicitly asks you to send a message to a channel/session, or when you need to proactively push a notification (e.g., task completion, reminders, alerts). This is a one-way send — no reply is returned.
qwenpaw channels sendtarget-user or target-sessiontarget-user or target-sessionchannel send is a one-way push — no user reply is returnedqwenpaw chats list --agent-id <your_agent> --channel <channel>
You can also filter by user:
qwenpaw chats list --agent-id <your_agent> --user-id <user_id>
qwenpaw channels send \
--agent-id <your_agent> \
--channel <channel> \
--target-user <user_id> \
--target-session <session_id> \
--text "..."
1. Determine: is the user explicitly requesting a send, or is proactive notification needed?
2. qwenpaw chats list — query the target session
3. Extract user_id and session_id from the results
4. If multiple sessions exist, prefer the most recently active one
5. qwenpaw channels send — send the message
6. Done (no reply)
qwenpaw channels send requires all of the following:
--agent-id--channel--target-user--target-session--textBefore sending, run:
qwenpaw chats list --agent-id <your_agent> --channel <channel>
Extract from the results:
user_id → --target-usersession_id → --target-sessionIf there are multiple candidate sessions, prefer the one with the most recent updated_at.
qwenpaw channels send only sends — it does not wait for a reply.
qwenpaw chats list --agent-id notify_bot --channel feishu
qwenpaw channels send \
--agent-id notify_bot \
--channel feishu \
--target-user manager_id \
--target-session manager_session \
--text "Weekly report is ready, please review"
qwenpaw chats list --agent-id task_bot --channel console
qwenpaw channels send \
--agent-id task_bot \
--channel console \
--target-user alice \
--target-session alice_console_001 \
--text "Task completed"
qwenpaw chats list --agent-id analyst_bot --user-id alice
qwenpaw channels send \
--agent-id analyst_bot \
--channel console \
--target-user alice \
--target-session alice_console_001 \
--text "Data analysis is complete. Results saved to report.pdf"
If you are replying to the user in the current session, do not use qwenpaw channels send.
Do not guess target-user or target-session. First run:
qwenpaw chats list --agent-id <your_agent> --channel <channel>
All five are required: --agent-id, --channel, --target-user, --target-session, --text.
There is no reply. It only pushes the message.
Prefer the most recently active session.
qwenpaw chats list --agent-id <your_agent>
qwenpaw chats list --agent-id <your_agent> --user-id <user_id>
qwenpaw channels list --agent-id <your_agent>
Selection principle:
qwenpaw agents chatqwenpaw channels sendRequired parameters:
--agent-id: Agent IDOptional parameters:
--channel: filter by channel--user-id: filter by user--base-url: override API addressRequired parameters (5):
--agent-id: sender agent ID--channel: target channel (console/dingtalk/feishu/discord/imessage/qq/...)--target-user: target user ID (obtained from qwenpaw chats list)--target-session: target session ID (obtained from qwenpaw chats list)--text: message contentOptional parameters:
--base-url: override API addressUse -h at any time to view detailed help:
qwenpaw channels -h
qwenpaw channels send -h
qwenpaw chats -h
qwenpaw chats list -h
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
阿里云 CLI 中文文档镜像检索与命令辅助:先走章节索引,再下钻正文页面,给出命令前必须有本地文档证据。
日本語の概要は準備中です。原文の説明を表示しています。
Drive a live browser with async Python against QwenPaw's builtin Browser SDK. The full reference is below; re-load this browser skill after context compaction.
日本語の概要は準備中です。原文の説明を表示しています。
用异步 Python 调用 QwenPaw 内置 Browser SDK 驱动真实浏览器。完整参考在下方;上下文压缩后请重新加载此 browser skill。
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a `cdp_port`, or share a single browser across multiple agents/tools. By default browser opens no debugging port; pass an explicit `cdp_port` only when the user wants another local tool to attach.
日本語の概要は準備中です。原文の説明を表示しています。
当用户明确希望连接到已运行的 Chrome 浏览器、扫描本地 CDP 端口、显式指定 `cdp_port`,或让多个 agent / 工具共享同一个浏览器时,使用本 skill。browser 默认不开放调试端口;仅当用户明确希望其他本地工具附加时才显式传入 `cdp_port`。
日本語の概要は準備中です。原文の説明を表示しています。
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.
日本語の概要は準備中です。原文の説明を表示しています。