diff --git a/metagpt/actions/__init__.py b/metagpt/actions/__init__.py
index 79ff94b3e..c34c72ed2 100644
--- a/metagpt/actions/__init__.py
+++ b/metagpt/actions/__init__.py
@@ -13,7 +13,6 @@ from metagpt.actions.add_requirement import UserRequirement
 from metagpt.actions.debug_error import DebugError
 from metagpt.actions.design_api import WriteDesign
 from metagpt.actions.design_api_review import DesignReview
-from metagpt.actions.design_filenames import DesignFilenames
 from metagpt.actions.project_management import AssignTasks, WriteTasks
 from metagpt.actions.research import CollectLinks, WebBrowseAndSummarize, ConductResearch
 from metagpt.actions.run_code import RunCode
@@ -33,7 +32,6 @@ class ActionType(Enum):
     WRITE_PRD_REVIEW = WritePRDReview
     WRITE_DESIGN = WriteDesign
     DESIGN_REVIEW = DesignReview
-    DESIGN_FILENAMES = DesignFilenames
     WRTIE_CODE = WriteCode
     WRITE_CODE_REVIEW = WriteCodeReview
     WRITE_TEST = WriteTest
diff --git a/metagpt/actions/action.py b/metagpt/actions/action.py
index 1fcc8fc80..e18983d7d 100644
--- a/metagpt/actions/action.py
+++ b/metagpt/actions/action.py
@@ -14,6 +14,7 @@ from pydantic import BaseModel, Field
 from metagpt.actions.action_node import ActionNode
 from metagpt.llm import LLM
 from metagpt.provider.base_gpt_api import BaseGPTAPI
+from metagpt.schema import CodingContext, CodeSummarizeContext, TestingContext, RunCodeContext
 
 
 action_subclass_registry = {}
@@ -22,7 +23,7 @@ action_subclass_registry = {}
 class Action(BaseModel):
     name: str = ""
     llm: BaseGPTAPI = Field(default_factory=LLM, exclude=True)
-    context = ""
+    context: dict | CodingContext | CodeSummarizeContext | TestingContext | RunCodeContext | str | None = ""
     prefix = ""  # aask*时会加上prefix，作为system_message
     desc = ""  # for skill manager
     node: ActionNode = Field(default_factory=ActionNode, exclude=True)
diff --git a/metagpt/actions/analyze_dep_libs.py b/metagpt/actions/analyze_dep_libs.py
deleted file mode 100644
index 53d40200a..000000000
--- a/metagpt/actions/analyze_dep_libs.py
+++ /dev/null
@@ -1,37 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-"""
-@Time    : 2023/5/19 12:01
-@Author  : alexanderwu
-@File    : analyze_dep_libs.py
-"""
-
-from metagpt.actions import Action
-
-PROMPT = """You are an AI developer, trying to write a program that generates code for users based on their intentions.
-
-For the user's prompt:
-
----
-The API is: {prompt}
----
-
-We decide the generated files are: {filepaths_string}
-
-Now that we have a file list, we need to understand the shared dependencies they have.
-Please list and briefly describe the shared contents between the files we are generating, including exported variables, 
-data patterns, id names of all DOM elements that javascript functions will use, message names and function names.
-Focus only on the names of shared dependencies, do not add any other explanations.
-"""
-
-
-class AnalyzeDepLibs(Action):
-    def __init__(self, name, context=None, llm=None):
-        super().__init__(name, context, llm)
-        self.desc = "Analyze the runtime dependencies of the program based on the context"
-
-    async def run(self, requirement, filepaths_string):
-        # prompt = f"Below is the product requirement document (PRD):\n\n{prd}\n\n{PROMPT}"
-        prompt = PROMPT.format(prompt=requirement, filepaths_string=filepaths_string)
-        design_filenames = await self._aask(prompt)
-        return design_filenames
diff --git a/metagpt/actions/design_filenames.py b/metagpt/actions/design_filenames.py
deleted file mode 100644
index ffa171d7b..000000000
--- a/metagpt/actions/design_filenames.py
+++ /dev/null
@@ -1,30 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-"""
-@Time    : 2023/5/19 11:50
-@Author  : alexanderwu
-@File    : design_filenames.py
-"""
-from metagpt.actions import Action
-from metagpt.logs import logger
-
-PROMPT = """You are an AI developer, trying to write a program that generates code for users based on their intentions.
-When given their intentions, provide a complete and exhaustive list of file paths needed to write the program for the user.
-Only list the file paths you will write and return them as a Python string list.
-Do not add any other explanations, just return a Python string list."""
-
-
-class DesignFilenames(Action):
-    def __init__(self, name, context=None, llm=None):
-        super().__init__(name, context, llm)
-        self.desc = (
-            "Based on the PRD, consider system design, and carry out the basic design of the corresponding "
-            "APIs, data structures, and database tables. Please give your design, feedback clearly and in detail."
-        )
-
-    async def run(self, prd):
-        prompt = f"The following is the Product Requirement Document (PRD):\n\n{prd}\n\n{PROMPT}"
-        design_filenames = await self._aask(prompt)
-        logger.debug(prompt)
-        logger.debug(design_filenames)
-        return design_filenames
diff --git a/metagpt/actions/detail_mining.py b/metagpt/actions/generate_questions.py
similarity index 69%
rename from metagpt/actions/detail_mining.py
rename to metagpt/actions/generate_questions.py
index 0314d30dd..c38c463bc 100644
--- a/metagpt/actions/detail_mining.py
+++ b/metagpt/actions/generate_questions.py
@@ -3,19 +3,11 @@
 """
 @Time    : 2023/9/12 17:45
 @Author  : fisherdeng
-@File    : detail_mining.py
+@File    : generate_questions.py
 """
 from metagpt.actions import Action
 from metagpt.actions.action_node import ActionNode
 
-CONTEXT_TEMPLATE = """
-## TOPIC
-{topic}
-
-## RECORD
-{record}
-"""
-
 QUESTIONS = ActionNode(
     key="Questions",
     expected_type=list[str],
@@ -25,11 +17,9 @@ QUESTIONS = ActionNode(
 )
 
 
-class DetailMining(Action):
+class GenerateQuestions(Action):
     """This class allows LLM to further mine noteworthy details based on specific "##TOPIC"(discussion topic) and
     "##RECORD" (discussion records), thereby deepening the discussion."""
 
-    async def run(self, topic, record):
-        context = CONTEXT_TEMPLATE.format(topic=topic, record=record)
-        rsp = await QUESTIONS.fill(context=context, llm=self.llm)
-        return rsp
+    async def run(self, context):
+        return await QUESTIONS.fill(context=context, llm=self.llm)
diff --git a/metagpt/schema.py b/metagpt/schema.py
index 59203c404..327bfd2d1 100644
--- a/metagpt/schema.py
+++ b/metagpt/schema.py
@@ -19,6 +19,7 @@ import asyncio
 import json
 import os.path
 import uuid
+from abc import ABC
 from asyncio import Queue, QueueEmpty, wait_for
 from json import JSONDecodeError
 from pathlib import Path
@@ -281,7 +282,7 @@ class MessageQueue(BaseModel):
 T = TypeVar("T", bound="BaseModel")
 
 
-class BaseContext(BaseModel):
+class BaseContext(BaseModel, ABC):
     @classmethod
     @handle_exception
     def loads(cls: Type[T], val: str) -> Optional[T]:
diff --git a/metagpt/actions/azure_tts.py b/metagpt/tools/azure_tts.py
similarity index 65%
rename from metagpt/actions/azure_tts.py
rename to metagpt/tools/azure_tts.py
index daa3f6892..e59d98016 100644
--- a/metagpt/actions/azure_tts.py
+++ b/metagpt/tools/azure_tts.py
@@ -7,19 +7,16 @@
 """
 from azure.cognitiveservices.speech import AudioConfig, SpeechConfig, SpeechSynthesizer
 
-from metagpt.actions.action import Action
-from metagpt.config import Config
+from metagpt.config import CONFIG
 
 
-class AzureTTS(Action):
-    def __init__(self, name, context=None, llm=None):
-        super().__init__(name, context, llm)
-        self.config = Config()
+class AzureTTS:
+    """https://learn.microsoft.com/zh-cn/azure/cognitive-services/speech-service/language-support?tabs=tts#voice-styles-and-roles"""
 
-    # Parameters reference: https://learn.microsoft.com/zh-cn/azure/cognitive-services/speech-service/language-support?tabs=tts#voice-styles-and-roles
-    def synthesize_speech(self, lang, voice, role, text, output_file):
-        subscription_key = self.config.get("AZURE_TTS_SUBSCRIPTION_KEY")
-        region = self.config.get("AZURE_TTS_REGION")
+    @classmethod
+    def synthesize_speech(cls, lang, voice, role, text, output_file):
+        subscription_key = CONFIG.get("AZURE_TTS_SUBSCRIPTION_KEY")
+        region = CONFIG.get("AZURE_TTS_REGION")
         speech_config = SpeechConfig(subscription=subscription_key, region=region)
 
         speech_config.speech_synthesis_voice_name = voice
@@ -41,5 +38,5 @@ class AzureTTS(Action):
 
 
 if __name__ == "__main__":
-    azure_tts = AzureTTS("azure_tts")
+    azure_tts = AzureTTS()
     azure_tts.synthesize_speech("zh-CN", "zh-CN-YunxiNeural", "Boy", "Hello, I am Kaka", "output.wav")
diff --git a/metagpt/utils/serialize.py b/metagpt/utils/serialize.py
index d4db5985b..8ad46a120 100644
--- a/metagpt/utils/serialize.py
+++ b/metagpt/utils/serialize.py
@@ -5,12 +5,10 @@
 import copy
 import pickle
 
-<<<<<<< HEAD
+
 from metagpt.utils.common import import_class
-=======
 from metagpt.actions.action_node import ActionNode
 from metagpt.schema import Message
->>>>>>> 09e2f05 (refactor action_output and action_node)
 
 
 def actionoutout_schema_to_mapping(schema: dict) -> dict:
diff --git a/tests/metagpt/actions/test_azure_tts.py b/tests/metagpt/actions/test_azure_tts.py
index bcafe10f5..9995e9691 100644
--- a/tests/metagpt/actions/test_azure_tts.py
+++ b/tests/metagpt/actions/test_azure_tts.py
@@ -5,11 +5,11 @@
 @Author  : alexanderwu
 @File    : test_azure_tts.py
 """
-from metagpt.actions.azure_tts import AzureTTS
+from metagpt.tools.azure_tts import AzureTTS
 
 
 def test_azure_tts():
-    azure_tts = AzureTTS("azure_tts")
+    azure_tts = AzureTTS()
     azure_tts.synthesize_speech("zh-CN", "zh-CN-YunxiNeural", "Boy", "你好，我是卡卡", "output.wav")
 
     # 运行需要先配置 SUBSCRIPTION_KEY
diff --git a/tests/metagpt/actions/test_detail_mining.py b/tests/metagpt/actions/test_detail_mining.py
index 30bcf9dfb..a178ec840 100644
--- a/tests/metagpt/actions/test_detail_mining.py
+++ b/tests/metagpt/actions/test_detail_mining.py
@@ -3,20 +3,26 @@
 """
 @Time    : 2023/9/13 00:26
 @Author  : fisherdeng
-@File    : test_detail_mining.py
+@File    : test_generate_questions.py
 """
 import pytest
 
-from metagpt.actions.detail_mining import DetailMining
+from metagpt.actions.generate_questions import GenerateQuestions
 from metagpt.logs import logger
 
+context = """
+## topic
+如何做一个生日蛋糕
+
+## record
+我认为应该先准备好材料，然后再开始做蛋糕。
+"""
+
 
 @pytest.mark.asyncio
-async def test_detail_mining():
-    topic = "如何做一个生日蛋糕"
-    record = "我认为应该先准备好材料，然后再开始做蛋糕。"
-    detail_mining = DetailMining("detail_mining")
-    rsp = await detail_mining.run(topic=topic, record=record)
+async def test_generate_questions():
+    detail_mining = GenerateQuestions()
+    rsp = await detail_mining.run(context)
     logger.info(f"{rsp.content=}")
 
     assert "Questions" in rsp.content