superman1006/MeetMind

A team that debates > a model that answers. MeetMind turns one requirement into a live discussion among five role-playing agents — architect, backend, frontend, test, and PM — each with its own private RAG knowledge base to search, cite, and reason from. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

This repository also configures its own agents. See what MeetMind tells them →

36Stars on the repository
5Mods indexed here, across every type
4mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

code-review

01

superman1006/MeetMind

Skill Claude CodeCodex

A structured code-review procedure that examines code for correctness, readability, speed, and security.

not rated 36 +5 4mo ago A 39 tokens original MIT

superman1006/MeetMind

Skill Claude CodeCodex

A project-analysis procedure that traces which functions call one another from a program’s entry point. It can present the result as an indented text chain or, when requested, as an HTML, Mermaid, or other visual diagram.

not rated 36 +5 4mo ago A 157 tokens original MIT

write-test

03

superman1006/MeetMind

Skill Claude CodeCodex

A procedure for designing unit-test cases for functions or modules, covering normal inputs, boundary values, and errors. Unit tests check small parts of a program in isolation.

not rated 36 +5 4mo ago A 28 tokens original MIT