diff --git a/.gitignore b/.gitignore
index 7d631e219..070a03685 100644
--- a/.gitignore
+++ b/.gitignore
@@ -415,3 +415,8 @@ tags
 
 # Camel
 logs/
+
+# Data
+datasets_test/
+evaluation_data/
+camel_data/
diff --git a/camel/agents/role_playing.py b/camel/agents/role_playing.py
index 579fa752d..95b0c719a 100644
--- a/camel/agents/role_playing.py
+++ b/camel/agents/role_playing.py
@@ -185,7 +185,7 @@ def __init__(
             self.critic = None
 
     def init_chat(self) -> Tuple[AssistantChatMessage, List[ChatMessage]]:
-        r"""Initializes the chat by resetting both the assistant and user
+        r"""Initializes the chat by resetting both of the assistant and user
         agents, and sending the system messages again to the agents using
         chat messages. Returns the assistant's introductory message and the
         user's response messages.
@@ -218,13 +218,13 @@ def process_messages(
         self,
         messages: Sequence[ChatMessage],
     ) -> ChatMessage:
-        r"""Processes a list of chat messages, returning the processed message.
-        If multiple messages are provided and `with_critic_in_the_loop`
-        is `False`, raises a `ValueError`. If no messages are provided, also
-        raises a `ValueError`.
+        r"""Processes a sequence of chat messages, returning the processed
+        message. If multiple messages are provided and
+        `with_critic_in_the_loop` is `False`, raises a `ValueError`.
+        If no messages are provided, a `ValueError` will be raised.
 
         Args:
-            msgs: A list of `ChatMessage`s to process.
+            messages: A sequence of `ChatMessage` objects to process.
 
         Returns:
             A single `ChatMessage` representing the processed message.
@@ -248,11 +248,10 @@ def step(
         r"""Advances the conversation by taking a message from the assistant,
         processing it using the user agent, and then processing the resulting
         message using the assistant agent. Returns a tuple containing the
-        resulting assistant message, whether or not the assistant agent
-        terminated the conversation, and any additional assistant information,
-        as well as a tuple containing the resulting user message, whether or
-        not the user agent terminated the conversation, and any additional user
-        information.
+        resulting assistant message, whether the assistant agent terminated
+        the conversation, and any additional assistant information, as well as
+        a tuple containing the resulting user message, whether the user agent
+        terminated the conversation, and any additional user information.
 
         Args:
             assistant_msg: A `ChatMessage` representing the message from the
@@ -260,11 +259,11 @@ def step(
 
         Returns:
             A tuple containing two ChatAgentResponse: the first struct contains
-            the resulting assistant message, whether or not the assistant agent
+            the resulting assistant message, whether the assistant agent
             terminated the conversation, and any additional assistant
             information; the second struct contains the resulting user message,
-            whether or not the user agent terminated the conversation, and
-            any additional user information.
+            whether the user agent terminated the conversation, and any
+            additional user information.
         """
         user_response = self.user_agent.step(assistant_msg)
         if user_response.terminated or user_response.msgs is None:
diff --git a/camel/agents/task_agent.py b/camel/agents/task_agent.py
index 20320cfa9..0d1e81cac 100644
--- a/camel/agents/task_agent.py
+++ b/camel/agents/task_agent.py
@@ -21,7 +21,7 @@
 
 
 class TaskSpecifyAgent(ChatAgent):
-    r"""An agent that Specifies a given task prompt by prompting the user to
+    r"""An agent that specifies a given task prompt by prompting the user to
     provide more details.
 
     Attributes:
@@ -160,12 +160,12 @@ def step(
         task_msg = UserChatMessage(role_name="Task Planner",
                                    content=self.task_planner_prompt)
         # sub_tasks_msgs, terminated, _
-        task_tesponse = super().step(task_msg)
+        task_response = super().step(task_msg)
 
-        if task_tesponse.msgs is None:
+        if task_response.msgs is None:
             raise RuntimeError("Got None Subtasks messages.")
-        if task_tesponse.terminated:
+        if task_response.terminated:
             raise RuntimeError("Task planning failed.")
 
-        sub_tasks_msg = task_tesponse.msgs[0]
+        sub_tasks_msg = task_response.msgs[0]
         return TextPrompt(sub_tasks_msg.content)
diff --git a/camel/agents/tool_agents/base.py b/camel/agents/tool_agents/base.py
index a06c72e42..a3d30c6a8 100644
--- a/camel/agents/tool_agents/base.py
+++ b/camel/agents/tool_agents/base.py
@@ -28,5 +28,13 @@ def __init__(self, name: str, description: str) -> None:
         self.name = name
         self.description = description
 
+    def reset(self) -> None:
+        r"""Resets the agent to its initial state."""
+        pass
+
+    def step(self) -> None:
+        r"""Performs a single step of the agent."""
+        pass
+
     def __str__(self) -> str:
         return f"{self.name}: {self.description}"
diff --git a/camel/agents/tool_agents/hugging_face_tool_agent.py b/camel/agents/tool_agents/hugging_face_tool_agent.py
index 0bf4b7b71..2106167ff 100644
--- a/camel/agents/tool_agents/hugging_face_tool_agent.py
+++ b/camel/agents/tool_agents/hugging_face_tool_agent.py
@@ -50,9 +50,7 @@ def __init__(
                 "pip install huggingface_hub==0.14.1 transformers==4.29.0 diffusers accelerate datasets torch soundfile sentencepiece opencv-python"
             )
         self.agent = OpenAiAgent(*args, **kwargs)
-        self.name = name
-        self.remote = remote
-        self.description = f"""The `{self.name}` is a tool agent that can perform a variety of tasks including:
+        description = f"""The `{name}` is a tool agent that can perform a variety of tasks including:
 - Document question answering: given a document (such as a PDF) in image format, answer a question on this document
 - Text question answering: given a long text and a question, answer the question in the text
 - Unconditional image captioning: Caption the image!
@@ -73,26 +71,26 @@ def __init__(
 Single execution (step) mode, the single execution method is when using the step() method of the agent:
 ```
 # Text to image
-rivers_and_lakes_image = {self.name}.step("Draw me a picture of rivers and lakes.")
+rivers_and_lakes_image = {name}.step("Draw me a picture of rivers and lakes.")
 rivers_and_lakes_image.save("./rivers_and_lakes_image.png")
 
 # Text to image -> Image transformation
-sea_add_island_image = {self.name}.step("Draw me a picture of the sea then transform the picture to add an island")
+sea_add_island_image = {name}.step("Draw me a picture of the sea then transform the picture to add an island")
 sea_add_island_image.save("./sea_add_island_image.png")
 
 # If you'd like to keep a state across executions or to pass non-text objects to the agent, 
 # you can do so by specifying variables that you would like the agent to use. For example,
 # you could generate the first image of rivers and lakes, and ask the model to update that picture to add an island by doing the following:
-picture = {self.name}.step("Generate a picture of rivers and lakes.")
+picture = {name}.step("Generate a picture of rivers and lakes.")
 picture.save("./picture.png")
-updated_picture = {self.name}.step("Transform the image in `picture` to add an island to it.", picture=picture)
+updated_picture = {name}.step("Transform the image in `picture` to add an island to it.", picture=picture)
 updated_picture.save("./updated_picture.png")
 
-capybara_sea_image = {self.name}.step("Draw me a picture of the `prompt`", prompt="a capybara swimming in the sea")
+capybara_sea_image = {name}.step("Draw me a picture of the `prompt`", prompt="a capybara swimming in the sea")
 capybara_sea_image.save("./capybara_sea_image.png")
 
 # Document question answering
-answer = {self.name}.step(
+answer = {name}.step(
     "In the following `document`, where will the TRRF Scientific Advisory Council Meeting take place?",
     document=document,
 )
@@ -100,46 +98,48 @@ def __init__(
 
 
 # Text to image
-boat_image = {self.name}.step("Generate an image of a boat in the water")
+boat_image = {name}.step("Generate an image of a boat in the water")
 boat_image.save("./boat_image.png")
 
 # Unconditional image captioning
-boat_image_caption = {self.name}.step("Can you caption the `boat_image`?", boat_image=boat_image)
+boat_image_caption = {name}.step("Can you caption the `boat_image`?", boat_image=boat_image)
 print(boat_image_caption)
 
 # Text to image -> Unconditional image captioning -> Text to speech
-boat_audio = {self.name}.step("Can you generate an image of a boat? Please read out loud the contents of the image afterwards")
+boat_audio = {name}.step("Can you generate an image of a boat? Please read out loud the contents of the image afterwards")
 
 # Text downloading
-document = {self.name}.step("Download the text from http://hf.co")
+document = {name}.step("Download the text from http://hf.co")
 print(document)
 
 # Text summarization
-summary = {self.name}.step("Summarize the following text: `document`", document=document)
+summary = {name}.step("Summarize the following text: `document`", document=document)
 print(summary)
 
 # Text downloading -> Text summarization -> Text to speech
-audio = {self.name}.step("Read out loud the summary of http://hf.co")
+audio = {name}.step("Read out loud the summary of http://hf.co")
 ```
 
 Chat-based execution (chat), the agent also has a chat-based approach, using the chat() method:
 ```
 # Clean the chat history
-{self.name}.reset()
+{name}.reset()
 
 # Text to image
-capybara_image = {self.name}.chat("Show me an an image of a capybara")
+capybara_image = {name}.chat("Show me an an image of a capybara")
 capybara_image.save("./capybara_image.png")
 
 # Image transformation
-transformed_capybara_image = {self.name}.chat("Transform the image so that it snows")
+transformed_capybara_image = {name}.chat("Transform the image so that it snows")
 transformed_capybara_image.save("./transformed_capybara_image.png")
 
 # Image segmentation
-segmented_transformed_capybara_image = {self.name}.chat("Show me a mask of the snowy capybaras")
+segmented_transformed_capybara_image = {name}.chat("Show me a mask of the snowy capybaras")
 segmented_transformed_capybara_image.save("./segmented_transformed_capybara_image.png")
 ```
 """
+        super(HuggingFaceToolAgent, self).__init__(name, description)
+        self.remote = remote
 
     def reset(self) -> None:
         r"""Resets the chat history of the agent."""
diff --git a/camel/prompts/code.py b/camel/prompts/code.py
index 35c1563af..463b46031 100644
--- a/camel/prompts/code.py
+++ b/camel/prompts/code.py
@@ -56,7 +56,7 @@ class CodePromptTemplateDict(TextPromptDict):
     )
 
     ASSISTANT_PROMPT = TextPrompt(
-        """Never forget you are a Computer Programmer and I am a person working in {domain}. Never flip roles!  Never instruct me!
+        """Never forget you are a Computer Programmer and I am a person working in {domain}. Never flip roles! Never instruct me!
 We share a common interest in collaborating to successfully complete a task.
 You must help me to complete the task using {language} programming language.
 Here is the task: {task}. Never forget our task!
diff --git a/requirements.txt b/requirements.txt
index fb22ba519..ff4f98fb8 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -17,7 +17,7 @@ pytest-cov
 
 # Packages for huggingface tools
 bs4
-transformers["agent"]
+transformers[agent]
 diffusers==0.16.1
 accelerate==0.19.0
 datasets==2.12.0