Before developing your first skill, please read the skill guide.


Follow the Preliminaries and Installation sections from the AEA quick start.

Step 1: Setup

We will first create an agent and add a scaffold skill, which we call my_search.

aea create my_agent && cd my_agent
aea scaffold skill my_search

In the following steps, we replace each one of the scaffolded Behaviour, Handler and Task in my_agent/skills/my_search with our implementation. We will build a simple skill which lets the agent send a search query to the OEF and process the resulting response.

Step 2: Develop a Behaviour

A Behaviour class contains the business logic specific to initial actions initiated by the agent rather than reactions to other events.

In this example, we implement a simple search behaviour. Each time, act() gets called by the main agent loop, we will send a search request to the OEF.

import logging

from import Query, Constraint, ConstraintType
from aea.skills.behaviours import TickerBehaviour
from packages.protocols.oef.message import OEFMessage
from packages.protocols.oef.serialization import DEFAULT_OEF, OEFSerializer

logger = logging.getLogger("aea.my_search_skill")

class MySearchBehaviour(TickerBehaviour):
    """This class provides a simple search behaviour."""

    def __init__(self, **kwargs):
        """Initialize the search behaviour."""
        self.sent_search_count = 0

    def setup(self) -> None:
        Implement the setup.

        :return: None
        """"[{}]: setting up MySearchBehaviour".format(self.context.agent_name))

    def act(self) -> None:
        Implement the act.

        :return: None
        self.sent_search_count += 1
        search_constraints = [Constraint("country",
                              ConstraintType("==", "UK"))]
        search_query_w_empty_model = Query(search_constraints, model=None)
        search_request = OEFMessage(type=OEFMessage.Type.SEARCH_SERVICES,
                                    query=search_query_w_empty_model)"[{}]: sending search request to OEF, search_count={}".format(self.context.agent_name, self.sent_search_count))

    def teardown(self) -> None:
        Implement the task teardown.

        :return: None
        """"[{}]: tearing down MySearchBehaviour".format(self.context.agent_name))

Searches are proactive and, as such, well placed in a Behaviour. Specifically, we subclass the TickerBehaviour as it allows us to repeatedly search at a defined tick interval.

We place this code in my_agent/skills/my_search/

Step 3: Develop a Handler

So far, we have tasked the agent with sending search requests to the OEF. However, we have no way of handling the responses sent to the agent by the OEF at the moment. The agent would simply respond to the OEF via the default error skill which sends all unrecognised envelopes back to the sender.

Let us now implement a handler to deal with the incoming search responses.

import logging

from aea.skills.base import Handler
from packages.protocols.oef.message import OEFMessage
from packages.protocols.oef.serialization import OEFSerializer

logger = logging.getLogger("aea.my_search_skill")

class MySearchHandler(Handler):
    """This class provides a simple search handler."""

    SUPPORTED_PROTOCOL = OEFMessage.protocol_id

    def __init__(self, **kwargs):
        """Initialize the handler."""
        self.received_search_count = 0

    def setup(self) -> None:
        """Set up the handler.""""[{}]: setting up MySearchHandler".format(self.context.agent_name))

    def handle(self, message: OEFMessage) -> None:
        Handle the message.

        :param message: the message.
        :return: None
        msg_type = OEFMessage.Type(message.get("type"))

        if msg_type is OEFMessage.Type.SEARCH_RESULT:
            self.received_search_count += 1
            nb_agents_found = len(message.get("agents"))
  "[{}]: found number of agents={}, received search count={}".format(self.context.agent_name, nb_agents_found, self.received_search_count))

    def teardown(self) -> None:
        Teardown the handler.

        :return: None
        """"[{}]: tearing down MySearchHandler".format(self.context.agent_name))

We create a handler which is registered for the oef protocol. Whenever it receives a search result, we log the number of agents returned in the search - the agents matching the search query - and update the counter of received searches.

Note, how the handler simply reacts to incoming events (i.e. messages). It could initiate further actions, however, they are still reactions to the upstream search event.

We place this code in my_agent/skills/my_search/

Step 4: Develop a Task

We have implemented a behaviour and a handler. We conclude by implementing a task. Here we can implement background logic. We will implement a trivial check on the difference between the amount of search requests sent and responses received.

import logging
import time

from aea.skills.base import Task

logger = logging.getLogger("aea.my_search_skill")

class MySearchTask(Task):
    """This class scaffolds a task."""

    def setup(self) -> None:
        Implement the setup.

        :return: None
        """"[{}]: setting up MySearchTask".format(self.context.agent_name))

    def execute(self) -> None:
        Implement the task execution.

        :return: None
        time.sleep(1)  # to slow down the agent"[{}]: number of search requests sent={} vs. number of search responses received={}".format(self.context.agent_name,

    def teardown(self) -> None:
        Implement the task teardown.

        :return: None
        """"[{}]: tearing down MySearchTask".format(self.context.agent_name))

Note, how we have access to other objects in the skill via self.context.

We place this code in my_agent/skills/my_search/

Step 5: Create the config file

Based on our skill components above, we create the following config file.

name: my_search
author: fetchai
version: 0.1.0
license: Apache 2.0
description: 'A simple search skill utilising the OEF.'
    class_name: MySearchBehaviour
      tick_interval: 5
    class_name: MySearchHandler
    args: {}
    class_name: MySearchTask
    args: {}
shared_classes: {}
protocols: ['fetchai/oef:0.1.0']
dependencies: {}

Importantly, the keys my_search_behaviour and my_search_handler are used in the above task to access these skill components at runtime. We also set the tick_interval of the TickerBehaviour to 5 seconds.

We place this code in my_agent/skills/my_search/skill.yaml.

Step 6: Add the oef protocol and connection

Our agent does not have the oef protocol yet so let's add it.

aea add protocol fetchai/oef:0.1.0

This adds the protocol to our agent and makes it available on the path packages.protocols....

We also need to add the oef connection:

aea add connection fetchai/oef:0.1.0

Step 7: Run the agent

We first start an oef node (see the connection section for more details) in a separate terminal window.

python scripts/oef/ -c ./scripts/oef/launch_config.json

We can then launch our agent.

aea run --connections oef

We can see that the agent sends search requests to the OEF and receives search responses from the OEF. Since our agent is only searching on the OEF - and not registered on the OEF - the search response returns an empty list of agents.

We stop the agent with CTRL + C.

Now it's your turn

We hope this step by step introduction has helped you develop your own skill. We are excited to see what you will build.