←Story detail

Trending story

AYi releases the system prompt for an emotional intelligence plug-in tool

1 reports1 story updatesUpdated Oct 30 22:16

Understand this story

AI overview

On October 30, 2026, AYi publicly released the core system prompt of the "Emotional Intelligence Plug-in" message rewriting tool. The tool is based on the four elements of Marshall Rosenberg's "Nonviolent Communication"—observation, feeling, need, and request—and is used to rewrite messages on WeChat, Feishu, and DingTalk. AYi said the code was generated by Cursor and uploaded to GitHub; during development, the requirements were to use only the Python standard library, have zero third-party dependencies, not send sensitive API Keys back to the frontend, and be compatible with standard OpenAI-format interfaces. The prompt specifically constrains the model not to apply fixed sentence patterns, not to fabricate facts beyond the original words, and to use 【】 as a placeholder for missing information. There is currently no further progress.

AI-generated from public reports

Latest development · Report

Ayi shares the core system prompt and development constraints of the "Emotional Intelligence Plugin"

Developments

1 confirmed developments

  1. AYi releases the system prompt for the EQ booster tool

    Source:Ayi AI Notes

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Oct 30

  1. Ayi AI Notes

    Ayi shares the core system prompt and development constraints of the "Emotional Intelligence Plugin"

    Ayi has publicly released the core system prompt of the "Emotional Intelligence Plugin" message rewriting tool, which rewrites WeChat, Feishu, and DingTalk messages based on the four elements of Marshall Rosenberg's Nonviolent Communication: observation, feeling, need, and request. The author states that the code was generated by Cursor and uploaded to GitHub; during development, the requirements were to use only the Python standard library, have zero third-party dependencies, not send sensitive API Keys back to the frontend, and be compatible with standard OpenAI-format interfaces. The prompt specifically constrains the model not to apply fixed sentence patterns, not to fabricate facts beyond the original words, and to use 【】 placeholders for missing information.

Related stories

  1. Related storiesheise online launches a hands-on workshop on AI coding assistants
  2. Related storiesUncle Bob open-sources Agent discipline Skills "ub-mode"
  3. Related storiesiX-Workshop launches Agentic Engineering course
  4. Related storiesEnglish translation is being prepared.