Optimize AI coding with open-source workflows and skill stacks from MiniMax-AI

The MiniMax Code team open-sourced the actual workflows and skill stacks they use to build products daily. By installing skill stacks like ronny or jiachen, developers can standardize high standards for AI-generated code, subtask decomposition, long session management, and code review processes.

GitHubMiniMax-AI466

MiniMax CodeClaude CodeCodexGit

Added 2026-10-31 · originally published 2026-10-29

Steps

1Clone the repository in your shell or terminal: git clone https://github.com/MiniMax-AI/mcode-stack.git ~/mcode-stack
2Create the agent skills directory: mkdir -p ~/.agents/skills
3Copy the required individual skill folder (such as long-command-check) to your skills directory: cp -R ~/mcode-stack/stacks/ronny/skills/long-command-check ~/.agents/skills/
4Alternatively, install the entire stack as a plugin by opening Plugins in the MiniMax Code desktop app, selecting Add marketplace, and entering MiniMax-AI/mcode-stack
5Start a new session in MiniMax Code, type /skills to view and run the corresponding skill (such as /long-command-check)

Ideas for Chinese platforms

This skill stack includes the making-content skill, which can be directly used to convert notes and materials into Xiaohongshu image posts and short vertical videos.

Copy-ready prompt

Act as my AI programming assistant. Refer to the guidelines in [MiniMax-AI/mcode-stack] to help me evaluate whether the current [task requirement] should be delegated to a subagent, and provide a detailed subtask breakdown plan and implementation steps.

View original post

#AI Agent#Workflow#Open Source#Code Review

Replicating Stripe's internal AI agent workflow

Handle repetitive tasks using the same AI agent setup used internally by Stripe, reducing task completion time from 20 days to 4 days compared to standard Claude Code. This system is built using over 100 saved prompts (one per step) with multiple agents collaborating to handle the build work.

Build an AI agent system from a blank terminal in 10 minutes

Build an AI agent system from a blank terminal in under 10 minutes using Claude Code, scaling from a single agent to automatic execution, checking, iteration, and multi-agent collaboration. Reportedly, 95% of engineers inside Anthropic use a similar workflow.

Practical AI video editing workflows

Explores several AI video editing and production tech stacks combining Claude Code, Whisper, FFmpeg, and Remotion to automate editing, subtitle generation, motion graphics, and effects processing.

Found this useful? Get daily updates on Telegram or X.

Join on Telegram Follow @CaiXiang23766

Summarized by AI from the original source - refer to the original post for details. Copyright belongs to the original author.

Steps

Ideas for Chinese platforms

Related use cases