Chat With Agent logo

Chat With Agent

OrganizationPopular
agentscope-ai
chat_with_agent

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

Overview

Publisheragentscope-ai
RepositoryQwenPaw
Skill namechat_with_agent
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 Chat With Agent 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/chat_with_agent-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/chat_with_agent-en .claude/skills/chat_with_agent
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Chat With Agent 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 Chat With Agent 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 Chat With Agent 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.

Chat with Agent

When to Use

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. If the user explicitly asks to talk to a specific agent, you should also use this skill.

Should Use

  • You need another agent's expertise, judgment, or second opinion
  • You need to request a plan, review, or recommendation from an agent
  • The user explicitly asks a specific agent to participate, assist, or answer
  • You need to continue an existing agent session while preserving context

Should Not Use

  • You can complete the task yourself and the user has not explicitly asked to involve another agent
  • It is a simple Q&A that does not require a specialized agent
  • The target agent is unclear — you should ask for clarification or list available agents first
  • You just received a message from an agent and are about to immediately call back the same agent, which may cause a loop

Decision Rules

  1. If the user explicitly requests a specific agent, follow that request — but still look up the agent first; do not guess the ID
  2. If you can complete the task yourself, do not call another agent
  3. When continuing a conversation, you must pass session_id
  4. By default, prefer using list_agents() and chat_with_agent(...) for foreground conversations — do not resort to other methods
  5. If the task should run in the background, use submit_to_agent(...) to submit it, then check_agent_task(...) to check the status

Usage Flow

Follow this flow strictly when using this skill:

  1. Ensure your tool list includes both list_agents() and chat_with_agent(...) built-in tools
  • These two tools are the foundation for communicating with other agents — do not remove or disable them
  • 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
  1. Use list_agents() to view the currently available agents, and select one by extracting its ID
  • Choose the most appropriate agent based on the user's needs and each agent's description
  • If no suitable agent is found and you are not the Default Agent, use the Default Agent
  • 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
  1. Call chat_with_agent(...) to initiate a foreground conversation. Key parameters include:
  • to_agent: the target agent's ID (note: this is the ID, not the name)
  • text: what you want to say to the target agent
  • 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
  • timeout: (optional) estimated time needed for the foreground wait, to avoid premature timeouts
  1. If the task is better suited for background execution, use the background tool path:
  • submit_to_agent(...): submit a background task — requires to_agent, text, and optionally session_id / task_timeout
    • Default execution budget is 3600 seconds (1 hour) when task_timeout is omitted
    • For work that may exceed 1 hour, pass an explicit positive task_timeout in seconds
    • Numeric strings such as "7200" are accepted
  • check_agent_task(...): check task status by task_id; returns the final result when complete
    • On timeout the task finishes as failed with an error like Task timed out after Ns (and code=timeout in the API payload)

Minimal Call Examples

New Conversation

text
list_agents()

chat_with_agent(
  to_agent="<target_agent_id>",
  text="[Agent <your_agent_id> requesting] I need your help determining the approach for this issue.",
)

Continuing an Existing Conversation

text
chat_with_agent(
  to_agent="<target_agent_id>",
  text="[Agent <your_agent_id> requesting] Please continue expanding on point 2 based on the previous conclusion.",
  session_id="<previous_session_id>",
)

Background Submission and Status Check

text
submit_to_agent(
  to_agent="<target_agent_id>",
  text="[Agent <your_agent_id> requesting] Please complete this longer task in the background.",
  task_timeout=7200,
)

check_agent_task(
  task_id="<task_id>",
)

Important Notes

  • Add a conversation identifier: it is recommended to start your message with:
text
[Agent <your_agent_id> requesting]

This helps the other agent clearly identify who is speaking, improving communication efficiency and accuracy.

  • 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:

    text
    [SESSION: xxx]

    where xxx is the session_id value. This value is typically system-generated and has a long, unique format. Save this session_id and continue using it in subsequent conversations with the same agent.

Frequently asked questions

What does the Chat With Agent AI skill do?

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

Why use Chat With Agent on TypingMind?

Because you install it once and use it with any model. Chat With Agent 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 Chat With Agent in TypingMind?

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

Which AI models can use Chat With Agent?

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 Chat With Agent?

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

Is the Chat With Agent 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 👇