Channel Message logo

Channel Message

OrganizationPopular
agentscope-ai
channel_message

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.

Overview

Publisheragentscope-ai
RepositoryQwenPaw
Skill namechannel_message
Stars
35.6K
Forks
3.2K
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by agentscope-ai on GitHub. Read the source before you install it.

Installation

Install the Channel Message AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/agentscope-ai/QwenPaw/tree/main/src/qwenpaw/agents/skills/channel_message-en
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/agentscope-ai/QwenPaw.git /tmp/QwenPaw
mkdir -p .claude/skills
cp -r /tmp/QwenPaw/src/qwenpaw/agents/skills/channel_message-en .claude/skills/channel_message
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Channel Message in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Channel Message on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Channel Message is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Channel Message

When to Use

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.

Should Use

  • The user explicitly asks to send to a specific channel/session
  • Proactively notifying the user after a task completes
  • Scheduled reminders, alerts, or status updates
  • Pushing async results back to an existing session
  • The user explicitly says "notify me when done"

Should Not Use

  • If you are simply replying in the current session, do not use qwenpaw channels send
  • You need a two-way conversation and expect an immediate reply
  • You do not know which target session to use
  • You are guessing target-user or target-session

Decision Rules

  1. Only use this when the user explicitly asks to send to a channel/session, or proactive notification is needed
  2. You must query sessions before sending
  3. Do not guess target-user or target-session
  4. If multiple sessions are found, prefer the most recently active one
  5. channel send is a one-way push — no user reply is returned

Most Common Commands

1) Query available sessions first

bash
qwenpaw chats list --agent-id <your_agent> --channel <channel>

You can also filter by user:

bash
qwenpaw chats list --agent-id <your_agent> --user-id <user_id>

2) Send a message

bash
qwenpaw channels send \
  --agent-id <your_agent> \
  --channel <channel> \
  --target-user <user_id> \
  --target-session <session_id> \
  --text "..."

Minimal Workflow

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)

Key Rules

Required Parameters

qwenpaw channels send requires all of the following:

  • --agent-id
  • --channel
  • --target-user
  • --target-session
  • --text

Must Query First

Before sending, run:

bash
qwenpaw chats list --agent-id <your_agent> --channel <channel>

Extract from the results:

  • user_id → --target-user
  • session_id → --target-session

If there are multiple candidate sessions, prefer the one with the most recent updated_at.

One-Way Push

qwenpaw channels send only sends — it does not wait for a reply.


Brief Examples

User explicitly asks to send to a channel

bash
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"

Task completion notification

bash
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"

Async result push-back

bash
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"

Common Mistakes

Mistake 1: Using channel send for a normal reply

If you are replying to the user in the current session, do not use qwenpaw channels send.

Mistake 2: Sending without querying sessions first

Do not guess target-user or target-session. First run:

bash
qwenpaw chats list --agent-id <your_agent> --channel <channel>

Mistake 3: Missing required parameters

All five are required: --agent-id, --channel, --target-user, --target-session, --text.

Mistake 4: Expecting a reply from send

There is no reply. It only pushes the message.

Mistake 5: Picking an arbitrary session when the user has multiple

Prefer the most recently active session.


Optional Commands

List all sessions

bash
qwenpaw chats list --agent-id <your_agent>

List sessions for a specific user

bash
qwenpaw chats list --agent-id <your_agent> --user-id <user_id>

List available channels

bash
qwenpaw channels list --agent-id <your_agent>

Difference from Agent Chat

  • qwenpaw agents chat: sends to another agent, two-way, returns a reply
  • qwenpaw channels send: sends to a user/session/channel, one-way, no reply

Selection principle:

  • Need to collaborate with another agent → qwenpaw agents chat
  • Need to proactively push a message to a user → qwenpaw channels send

Full Parameter Reference

qwenpaw chats list

Required parameters:

  • --agent-id: Agent ID

Optional parameters:

  • --channel: filter by channel
  • --user-id: filter by user
  • --base-url: override API address

qwenpaw channels send

Required 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 content

Optional parameters:

  • --base-url: override API address

Help

Use -h at any time to view detailed help:

bash
qwenpaw channels -h
qwenpaw channels send -h
qwenpaw chats -h
qwenpaw chats list -h

Frequently asked questions

What does the Channel Message AI skill do?

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.

Why use Channel Message on TypingMind?

Because you install it once and use it with any model. Channel Message is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Channel Message in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/agentscope-ai/QwenPaw/tree/main/src/qwenpaw/agents/skills/channel_message-en. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Channel Message?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Channel Message?

As many as you like. As long as a model supports skills, you can use Channel Message with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Channel Message AI skill free?

Yes. It is published on GitHub by agentscope-ai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇