Skip to content

minimax-ai/jiachen

v0.1.1

Find the loops where you keep acting as a manual step for your agents (retrying, judging, approving, carrying context) and lift yourself out of them, plus a content pipeline that rewrites AI-sounding Chinese drafts and turns material into Xiaohongshu image posts and short vertical videos.

jiachen

The stack of Jiachen, an engineer on MiniMax Code: one skill that keeps taking the user out of the agent loop, and one that turns notes into posts and short videos.

Install

In Claude Code, one command installs this stack. In a shell:

claude plugin install jiachen --marketplace MiniMax-AI/mcode-stack

Inside a session:

/plugin install jiachen --marketplace MiniMax-AI/mcode-stack

Older Claude Code can add the marketplace first, then install:

/plugin marketplace add MiniMax-AI/mcode-stack
/plugin install jiachen@mcode-stack

In Codex, add the marketplace, then install from the Plugins Directory or the CLI:

codex plugin marketplace add MiniMax-AI/mcode-stack
codex plugin add jiachen@mcode-stack

In MiniMax Code, copy this whole directory into the local plugin directory shown by mcode plugin marketplace list, or copy single skills into ~/.agents/skills/. See the repository README.

SkillWhat it does
lifting-loopsFind the loops where you keep acting as a manual step for your agents (retrying, judging output, approving, carrying context, starting the same task by hand) and turn each one into a concrete fix: delete a stale rule, change a skill or AGENTS.md, add a script, a skill or a scheduled task. Reads local MiniMax Code, Claude Code and Codex sessions; keeps its ledger in a gitignored private/ folder.
making-contentRewrite an AI-sounding Chinese draft in a restrained voice, make a Xiaohongshu (小红书) image post from scratch, or turn material into a 60–180 s vertical video with real sources, voice-over and captions.

Requirements

  • lifting-loops: Python 3, standard library only.
  • making-content: text rewriting needs nothing. Video needs Python 3 with pip install -r skills/making-content/requirements.txt, Playwright's Chromium, ffmpeg and a CJK font; see video-pipeline.md. A cloned voice is optional and needs the user's own Volcengine key.

Personal samples stay local: making-content reads before/after samples from a gitignored test-cases/ folder, and lifting-loops writes everything it learns about you to a gitignored private/ folder.

How these fit into a working day: WORKFLOW.md.

Origin

Both skills are maintained in yujiachen-y/dotfiles, where changes land first; this stack carries a copy with personal examples replaced by neutral ones, released under MIT. The dotfiles repository has a few more skills (for example making-flashcards for Anki and review-skill for auditing skills) and its own marketplace for Claude Code and Codex:

/plugin marketplace add yujiachen-y/dotfiles      # Claude Code
npx skills add yujiachen-y/dotfiles --skill <name>