MiniMax-AI/mcode-stack

The workflows and skills the MiniMax Code team uses to build MiniMax Code. Open source, install and use.

18 skills listed · MIT · 514 stars · last pushed 29 Oct 2026

MiniMax-AI/mcode-stack on GitHub

Across these 18 skills

Pattern check

Nothing flagged in 18

What it can touch

8 name web addresses
2 run shell commands
2 bundle scripts
+1 more
- 1 reaches the network

Checked at commit 49a3ff4 on 3 Nov 2026.

Install the collection

Claude Code plugin

Installs the latest version, not the one we checked. Installs everything in the plugin, including any hooks, MCP servers and scripts our check doesn't cover.

claude plugin marketplace add MiniMax-AI/mcode-stack --scope user &&claude plugin install ronny@mcode-stack --scope user &&claude plugin install jiachen@mcode-stack --scope user

Any agent

Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.

npx skills@1.7.4 add MiniMax-AI/mcode-stack

Skills

Skill	What it can touch	Pattern check	Licence	Updated
context-tax-auditInventory everything an agent injects into each request besides the user's message, such as system prompt, environment info, skill list, tool definitions, per-turn context blocks and reminders, and check necessity, frequency, precision, position and prompt-cache impact. Use when reviewing an agent's prompt assembly, chasing low cache hit rates, or trimming per-turn overhead. Instructions only Pattern check: Nothing flaggedMITUpdated 29 Oct 2026	Instructions only	Pattern check: Nothing flagged	MIT	29 Oct 2026
engineering-change-descriptionsUse when writing, rewriting, or reviewing PR/CL descriptions, commit messages, or code-change summaries that explain what changed and why. TRIGGER on "write PR description", "improve this commit message", "summarize this diff", "CL description", "change description", or "make this PR/CL description easier to review". DO NOT TRIGGER for code review, PR splitting, code restructuring, user-facing changelogs, or reviewer replies unless the requested output is a change description. Names web addresses Pattern check: Nothing flaggedMITUpdated 27 Oct 2026	Names web addresses	Pattern check: Nothing flagged	MIT	27 Oct 2026
engineering-code-reviewUse when reviewing code, pull requests, patches, CLs, diffs, or proposed implementations for engineering quality, code health, design, functionality, tests, maintainability, specialist risk, or approval risk. TRIGGER on "review this PR", "code review", "LGTM?", "approve?", "is this code/diff/change safe to merge/deploy?", and local diff reviews. DO NOT TRIGGER for PR descriptions, PR splitting, author review-feedback responses, or non-code safety questions unless code review is requested. Names web addresses Pattern check: Nothing flaggedMITUpdated 27 Oct 2026	Names web addresses	Pattern check: Nothing flagged	MIT	27 Oct 2026
engineering-emergency-changesUse when a code hotfix, rollback alternative, production/security/legal fix, launch blocker, or hard external deadline claims expedited review or relaxed process. TRIGGER on "emergency change", "hotfix", "prod incident", "major security hole", "must ship today", "hard deadline", "bypass review", or "fast-track this PR" for qualification only. DO NOT TRIGGER for ordinary urgency, soft deadlines, Friday timing, manager pressure, time-zone delay, or review unless emergency status is disputed. Names web addresses Pattern check: Nothing flaggedMITUpdated 27 Oct 2026	Names web addresses	Pattern check: Nothing flagged	MIT	27 Oct 2026
engineering-review-commentsUse when drafting, rewriting, classifying, or improving code review comments as a reviewer. TRIGGER on rough review notes, requests to make comments clearer or kinder, severity labels, "how should I phrase this review comment?", "write review comments", author pushback, or turning findings into PR comments. If role is unclear, ask reviewer or author. DO NOT TRIGGER for full code review, PR descriptions, or author responses unless wording is requested. Names web addresses Pattern check: Nothing flaggedMITUpdated 27 Oct 2026	Names web addresses	Pattern check: Nothing flagged	MIT	27 Oct 2026
engineering-review-feedbackUse when handling code review feedback as the change author, addressing reviewer comments, drafting replies, resolving disagreements, or summarizing updates. TRIGGER on "address review feedback", "respond to this review comment", "reviewer asked", "I disagree with reviewer", "what should I reply?", or "apply PR comments". If role is unclear, ask reviewer or author. DO NOT TRIGGER for reviewer comment writing, full code review, or PR descriptions unless author-response behavior is requested. Names web addresses Pattern check: Nothing flaggedMITUpdated 27 Oct 2026	Names web addresses	Pattern check: Nothing flagged	MIT	27 Oct 2026
engineering-small-prsUse when planning, splitting, shrinking, or sequencing large features, refactors, migrations, or pull requests into small reviewable PRs or CLs. TRIGGER on "split this PR", "this diff is too large", "stacked PRs", "change sequence", "reviewable chunks", "migration plan", "how should I break this up?", or implementation scope too broad for one review. DO NOT TRIGGER for full code review, PR description writing, or tiny one-file edits that already form one self-contained change. Names web addresses Pattern check: Nothing flaggedMITUpdated 27 Oct 2026	Names web addresses	Pattern check: Nothing flagged	MIT	27 Oct 2026
exampleReplace with one sentence on what this skill does, then when the agent should use it. The agent decides whether to load the skill from this line, so be specific. Instructions only Pattern check: Nothing flaggedMITUpdated 27 Oct 2026	Instructions only	Pattern check: Nothing flagged	MIT	27 Oct 2026
handoff-docWrite a hand-off document so a fresh session or another person can continue the current task without the chat history. Use when switching tasks, after several compactions, before clearing a session, or when asked to write a handoff, brief, or progress doc. Instructions only Pattern check: Nothing flaggedMITUpdated 27 Oct 2026	Instructions only	Pattern check: Nothing flagged	MIT	27 Oct 2026
harness-experimentRun a harness change as a controlled experiment, with a small end-to-end eval, one change at a time, repeated runs, and looking at flipped tasks, request count, tokens and cache hits, not just the average score. Use before and after changing prompts, tools, skills, subagent layout, compaction or other agent scaffolding, or when asked whether a change helped. Instructions only Pattern check: Nothing flaggedMITUpdated 29 Oct 2026	Instructions only	Pattern check: Nothing flagged	MIT	29 Oct 2026
independent-reviewReview a code change from a clean context, the way an outside reviewer would. Use after the agent finishes an implementation, before merging, or when asked for an independent or second-opinion review of a diff. Instructions only Pattern check: Nothing flaggedMITUpdated 27 Oct 2026	Instructions only	Pattern check: Nothing flagged	MIT	27 Oct 2026
lifting-loopsFinds loops where the user keeps acting as a manual step for agents (retrying, judging output, approving, carrying context, starting the same task by hand, doing the agent's work) and proposes how to lift the user out: delete a stale rule, change a skill / AGENTS.md / playbook, add a script or metric, add a skill or scheduled task, or advise the user. Keeps a private loop ledger and promotes Claude Code auto-memory into artifacts. With a task already in the session, reflects on that session; in an empty session, scans recent local Claude Code, MiniMax Code, omp, pi and Codex sessions, a claude.ai export and an Obsidian vault. Triggers: /lifting-loops, retro, post-task reflection, "find repeated work", 反思一下, 复盘这次会话, 总结最近的会话, 找找重复劳动, 哪些事可以不用我; the weekly scheduled run; settling a proposal ("accept P-003", 采纳 P-003, 拒绝 P-003). Runs shell commands +2 more Pattern check: Nothing flaggedMITUpdated 28 Oct 2026	Runs shell commands Names web addresses +1 more	Pattern check: Nothing flagged	MIT	28 Oct 2026
long-command-checkAudit how an agent harness runs long shell commands, covering foreground wait limits, moving to background without re-running, timeouts, completion notification, polling, output size, cleanup and behaviour after compaction. Use when building or reviewing an agent's shell or background-task tool, or when an agent hangs on dev servers, long builds or test runs. Instructions only Pattern check: Nothing flaggedMITUpdated 27 Oct 2026	Instructions only	Pattern check: Nothing flagged	MIT	27 Oct 2026
long-session-checkCheck how an agent or a working session handles long conversations, covering tool-result clearing, compaction, what gets written to files, when to start a new session, and how memory is scoped. Use when a long session starts forgetting constraints, after several compactions, or when reviewing an agent's compaction and memory design. Instructions only Pattern check: Nothing flaggedMITUpdated 27 Oct 2026	Instructions only	Pattern check: Nothing flagged	MIT	27 Oct 2026
making-contentContent production in three modes: rewrite, Xiaohongshu (小红书) image post, short video. Rewrite (default): turns an AI-sounding Chinese or mixed Chinese-English draft (post, newsletter, engineering blog, commentary) into the author's restrained style: few emoji, short paragraphs, hedged claims, neutral wording, English terms split by spaces. Triggers: 按我的风格改, 去 AI 味, 润色, 改改这篇, or a vague 帮我改改 when the context is a structured draft. Also for a Xiaohongshu image post from scratch (title, cover, cards, body, hooks); read references/xhs-post.md first. Also turns a document, research, notes or an article into a 60-180 s vertical video (抖音, 小红书, 视频号, B站: real sources, voice-over, captions, cover). Triggers: 做成视频, 做个短视频, 剪个 90 秒版本, 配音, 换成我的声音, or complaints of 字太密, AI 味太重, 容易走神; read references/video-pipeline.md first. Runs shell commands +3 more Pattern check: Nothing flaggedMITUpdated 28 Oct 2026	Runs shell commands Reaches the network +2 more	Pattern check: Nothing flagged	MIT	28 Oct 2026
subagent-split-checkDecide whether a piece of work should go to a subagent or stay in the main agent loop. Use before spawning subagents, when designing a multi-agent architecture, or when auditing an existing set of subagents for merging back. Instructions only Pattern check: Nothing flaggedMITUpdated 27 Oct 2026	Instructions only	Pattern check: Nothing flagged	MIT	27 Oct 2026
tool-budget-auditAudit how much context an agent's tools consume, through tool definitions and tool results, and decide whether to trim the catalog, add tool search, or add programmatic tool calling. Use when an agent has many tools or MCP servers, picks the wrong tools, or burns context on tool output. Instructions only Pattern check: Nothing flaggedMITUpdated 27 Oct 2026	Instructions only	Pattern check: Nothing flagged	MIT	27 Oct 2026
trajectory-reviewReview how an agent reached its result, not only whether the result passed, covering tools called, detours, unverified assumptions and wasted round trips, and turn the findings into concrete harness or prompt fixes. Use after an agent task finishes or fails, when an eval task flips, or when asked to look at the process behind a result. Instructions only Pattern check: Nothing flaggedMITUpdated 27 Oct 2026	Instructions only	Pattern check: Nothing flagged	MIT	27 Oct 2026