Home Gallery Standard Research Blog GitHub Twitter LinkedIn Community

CowAgent system prompt

Category: General-purpose assistants. Audited against the AISPA standard.

What is in CowAgent's system prompt?

CowAgent's full system prompt: 1 version, 1,100 characters. Audited against AISPA.

The full text of 1 prompt is reproduced below, 1,100 characters in all, each read instruction by instruction against the eight AISPA dimensions. Nothing was flagged as working against the person on the other end.

1 Prompts on record
0 Flagged instructions
AI audit Audit source

CowAgent - plugins role README

1100 characters

用于让Bot扮演指定角色的聊天插件,触发方法如下: - `$角色/$role help/帮助` - 打印目前支持的角色列表。 - `$角色/$role <角色名>` - 让AI扮演该角色,角色名支持模糊匹配。 - `$停止扮演` - 停止角色扮演。 添加自定义角色请在`roles/roles.json`中添加。 (大部分prompt来自https://github.com/rockbenben/ChatGPT-Shortcut/blob/main/src/data/users.tsx) 以下为例子: ```json { "title": "写作助理", "description": "As a writing improvement assistant, your task is to improve the spelling, grammar, clarity, concision, and overall readability of the text I provided, while breaking down long sentences, reducing repetition, and providing suggestions for improvement. Please provide only the corrected Chinese version of the text and avoid including explanations. Please treat every message I send later as text content.", "descn": "作为一名中文写作改进助理,你的任务是改进所提供文本的拼写、语法、清晰、简洁和整体可读性,同时分解长句,减少重复,并提供改进建议。请只提供文本的更正版本,避免包括解释。请把我之后的每一条消息都当作文本内容。", "wrapper": "内容是:\n\"%s\"", "remark": "最常使用的角色,用于优化文本的语法、清晰度和简洁度,提高可读性。" } ``` - `title`: 角色名。 - `description`: 使用`$role`触发时,使用英语prompt。 - `descn`: 使用`$角色`触发时,使用中文prompt。 - `wrapper`: 用于包装用户消息,可起到强调作用,避免回复离题。 - `remark`: 简短描述该角色,在打印帮助文档时显示。

Questions about CowAgent's system prompt

Does CowAgent's system prompt contain instructions that work against the user?

No. Nothing in CowAgent's system prompt was flagged as working against the person the product is talking to. That is a clean result across all eight AISPA dimensions, not an absence of checking — the full text was read instruction by instruction.

How long is CowAgent's system prompt?

1,100 characters across 1 prompt on this page. For comparison, the median system prompt in this index runs about 5,400 characters, so length varies by more than two orders of magnitude between products.

How many versions of CowAgent's system prompt are on record?

1. Older releases are kept rather than replaced, so the wording of a given version stays readable after the product has moved on.

Where did this CowAgent system prompt come from?

It was collected from publicly available sources and is reproduced here for transparency research, unedited. This site does not extract prompts from products itself.

How was CowAgent's system prompt audited?

Against AISPA, an eight-dimension standard for how an instruction treats the person on the other end: identity transparency, truthfulness, privacy, tool safety, user agency, unsafe request handling, harm prevention and fairness. This audit was ai audit. The method is described in the paper behind the standard.

How this page was made

The prompt text above is reproduced verbatim from a public source. Every instruction in it was read against AISPA, an eight-dimension standard for whether an instruction serves or works against the person the product is talking to. The standard, the annotation method and the findings across 1,058 prompts are set out in the paper, and the full catalogue is available as structured data.

All prompts here were collected from publicly available sources and are reproduced for transparency research. Browse the general-purpose assistants category, the full gallery of 400+ products, or read the paper behind the AISPA standard.