diff --git a/metagpt/actions/skill_action.py b/metagpt/actions/skill_action.py
index 301cebaab..5af2b3fc4 100644
--- a/metagpt/actions/skill_action.py
+++ b/metagpt/actions/skill_action.py
@@ -29,9 +29,7 @@ class ArgumentsParingAction(Action):
 
     @property
     def prompt(self):
-        prompt = "You are a function parser. You can convert spoken words into function parameters.\n"
-        prompt += "\n---\n"
-        prompt += f"{self.skill.name} function parameters description:\n"
+        prompt = f"{self.skill.name} function parameters description:\n"
         for k, v in self.skill.arguments.items():
             prompt += f"parameter `{k}`: {v}\n"
         prompt += "\n---\n"
@@ -49,7 +47,10 @@ class ArgumentsParingAction(Action):
 
     async def run(self, with_message=None, **kwargs) -> Message:
         prompt = self.prompt
-        rsp = await self.llm.aask(msg=prompt, system_msgs=[])
+        rsp = await self.llm.aask(
+            msg=prompt,
+            system_msgs=["You are a function parser. You can convert spoken words into function parameters."],
+        )
         logger.debug(f"SKILL:{prompt}\n, RESULT:{rsp}")
         self.args = ArgumentsParingAction.parse_arguments(skill_name=self.skill.name, txt=rsp)
         self.rsp = Message(content=rsp, role="assistant", instruct_content=self.args, cause_by=self)
diff --git a/metagpt/memory/brain_memory.py b/metagpt/memory/brain_memory.py
index ff29eaddb..384c4d3a9 100644
--- a/metagpt/memory/brain_memory.py
+++ b/metagpt/memory/brain_memory.py
@@ -201,11 +201,14 @@ class BrainMemory(BaseModel):
 
     @staticmethod
     async def _openai_is_related(text1, text2, llm, **kwargs):
-        command = (
-            f"{text2}\n\nIs there any sentence above related to the following sentence: {text1}.\nIf is there "
-            "any relevance, return [TRUE] brief and clear. Otherwise, return [FALSE] brief and clear."
+        context = f"## Paragraph 1\n{text2}\n---\n## Paragraph 2\n{text1}\n"
+        rsp = await llm.aask(
+            msg=context,
+            system_msgs=[
+                "You are a tool capable of determining whether two paragraphs are semantically related."
+                'Return "TRUE" if "Paragraph 1" is semantically relevant to "Paragraph 2", otherwise return "FALSE".'
+            ],
         )
-        rsp = await llm.aask(msg=command, system_msgs=[])
         result = True if "TRUE" in rsp else False
         p2 = text2.replace("\n", "")
         p1 = text1.replace("\n", "")
@@ -223,12 +226,16 @@ class BrainMemory(BaseModel):
 
     @staticmethod
     async def _openai_rewrite(sentence: str, context: str, llm):
-        command = (
-            f"{context}\n\nExtract relevant information from every preceding sentence and use it to succinctly "
-            f"supplement or rewrite the following text in brief and clear:\n{sentence}"
+        prompt = f"## Context\n{context}\n---\n## Sentence\n{sentence}\n"
+        rsp = await llm.aask(
+            msg=prompt,
+            system_msgs=[
+                'You are a tool augmenting the "Sentence" with information from the "Context".',
+                "Do not supplement the context with information that is not present, especially regarding the subject and object.",
+                "Return the augmented sentence.",
+            ],
         )
-        rsp = await llm.aask(msg=command, system_msgs=[])
-        logger.info(f"REWRITE:\nCommand: {command}\nRESULT: {rsp}\n")
+        logger.info(f"REWRITE:\nCommand: {prompt}\nRESULT: {rsp}\n")
         return rsp
 
     @staticmethod
@@ -293,14 +300,14 @@ class BrainMemory(BaseModel):
         """Generate text summary"""
         if len(text) < max_words:
             return text
+        system_msgs = [
+            "You are a tool for summarizing and abstracting text.",
+            "Return the summarized text to less than 200 words.",
+        ]
         if keep_language:
-            command = f".Translate the above content into a summary of less than {max_words} words in language of the content strictly."
-        else:
-            command = f"Translate the above content into a summary of less than {max_words} words."
-        msg = text + "\n\n" + command
-        logger.debug(f"summary ask:{msg}")
-        response = await self.llm.aask(msg=msg, system_msgs=[])
-        logger.debug(f"summary rsp: {response}")
+            system_msgs.append("The generated summary should be in the same language as the original text.")
+        response = await self.llm.aask(msg=text, system_msgs=system_msgs)
+        logger.debug(f"{text}\nsummary rsp: {response}")
         return response
 
     @staticmethod
diff --git a/setup.py b/setup.py
index 2b16e2cd1..235c18f53 100644
--- a/setup.py
+++ b/setup.py
@@ -57,7 +57,7 @@ extras_require["dev"] = (["pylint~=3.0.3", "black~=23.3.0", "isort~=5.12.0", "pr
 
 setup(
     name="metagpt",
-    version="0.6.7",
+    version="0.6.8",
     description="The Multi-Agent Framework",
     long_description=long_description,
     long_description_content_type="text/markdown",