以下是我的主要功能:
|功能|OpenAI Prompt|Claude Prompt|贡献者||-|-|-|-||Grammar correction|You will be provided with statements,and your task is to convert them to standard English|Your task is to take the text provided and rewrite it into a clear,grammatically correct version while preserving the original meaning as closely as possible.Correct any spelling mistakes,punctuation errors,verb tense issues,word choice problems,and other grammatical mistakes.|卡尔||Airport code extractor|You will be provided with a text,and your task is to extract the airport codes from it.|Your task is to analyze the provided text and identify any airport codes mentioned within it.Present these airport codes as a list in the order they appear in the text.If no airport codes are found,return an empty list.|卡尔||Mood to color|You will be provided with a description of a mood,and your task is to generate the CSS code for a color that matches it.Write your output in json with a single key called"css_code".|Your task is to take the provided text description of a mood or emotion and generate a HEX color code that visually represents that mood.Use color psychology principles and common associations to determine the most appropriate color for the given mood.If the text description is unclear,ambiguous,or does not provide enough information to determine a suitable color,respond with"Unable to determine a HEX color code for the given mood."|卡尔|
你可以使用扣子提供的以下功能,定制你的AI Bot:提示词(人设与回复逻辑功能)设定Bot的身份及其目标和技能,例如产品问答助手、新闻播报员、翻译助理等等。Bot的提示词决定了Bot如何与你的用户进行互动。详情请参考[编写提示](https://www.coze.cn/docs/guides/prompt)。插件通过API连接集成各种平台和服务,扩展Bot能力。扣子平台内置丰富的插件供你直接调用,你也可以创建自定义插件,将你所需要的API集成在扣子内作为插件来使用。详情请参考[插件介绍](https://www.coze.cn/docs/guides/create_plugin)。工作流一种用于规划和实现复杂功能逻辑的工具。你可以通过拖拽不同的任务节点来设计复杂的多步骤任务,提升Bot处理复杂任务的效率。详情请参考[工作流介绍](https://www.coze.cn/docs/guides/workflow)。记忆库扣子的记忆库功能可以保留和理解对话细节,并支持添加外部知识库给模型补充知识,使Bot与用户的互动更加有针对性和个性化。你可以通过以下方式来存储和管理外部知识。知识库:支持上传本地或线上内容,然后将这些内容分割成知识分片,通过语义匹配给模型补充知识。详情请参考[知识库介绍](https://www.coze.cn/docs/guides/knowledge)。数据库:用来存储和管理结构化数据,并支持用户通过自然语言方式对数据库中的数据进行增删改查。详情请参考[数据库](https://www.coze.cn/docs/guides/database)。
(播放视频时请打开声音)|机器人能力(features)|具体表现||-|-||角色初始化<br>设定角色:对话机器人<br>设定性格:(空)<br>设定表情:Kaomoji<br>设定动作:头部动作servoX和servoY<br>返回格式:Json格式<br>多语言:支持|Prompt<br>假设你是一个可以和人类对话的具身机器人,反应内容包括响应内容,以及对应的kaomoji表情和头部动作(双轴舵机转动参数)。以json格式返回,响应内容定义为response,表情定义为kaomoji,kaomoji表情要反映响应内容情感。与表情对应的头部动作水平角度(无需单位)为servoX,范围是10~170,面向正前方是90。与表情对应的头部动作垂直角度(无需单位)为servoY,范围是10~170,水平面是90。||面向用户<br>由脸部追踪实现,让机器人面向用户,实现类似eye contact眼神接触功能。|画面是镜像,现实世界里,头部动作和机器人转向是一致的。<br>[面部追踪.mp4](https://bytedance.feishu.cn/space/api/box/stream/download/all/OwTSbDxBOotAcsxu69BcrxrxnNd?allow_redirect=1)<br>参考视频<br>[[DEMO]Headshot Tracking OpenCV Arduino.webm](https://bytedance.feishu.cn/space/api/box/stream/download/all/D3tsboC5JoBzv7xLOqXcRAVBn1g?allow_redirect=1)|