all publishers

MiniMax AI

@minimax-ai source repo

254 published skills · page 1 of 3

  1. ▌
    H3 Image Prompt Writing · minimax-ai bundle
    Write prompts for MiniMax-H3-Image text-to-image generation and image editing, and optionally render them through the MiniMax API. Use when the user wants an image such as a poster, infographic, chart, product shot, UI screen, character, scene, storyboard or grid, wants to improve an image prompt, or wants to edit, combine or restyle reference images with MiniMax-H3-Image.
    13.8k repo stars
  2. ▌
    Code Review · minimax-ai
    Review local uncommitted changes, commits, branches, pull requests, files, functions, or other user-specified code scopes for concrete defects. Follow the scope and comparison base named by the user. Do not use for ordinary code explanation, debugging, implementation, or fix requests that do not ask for a review.
    13.8k repo stars
  3. ▌
    Visual Page · minimax-ai
    Proactively create a visual HTML page when plain text cannot effectively convey the information. Use this skill when: the content involves diagrams (flowcharts, architecture, sequence diagrams), data comparisons (tables, charts), timelines, interactive demos, visual layouts, or any scenario where a simple webpage would communicate more clearly than markdown text. Also use when the user explicitly asks for a visual page, a webpage, or says "show me" / "画个图" / "做个页面" / "可视化". This skill should be used proactively by the model — do not wait for the user to ask.
    13.8k repo stars
  4. ▌
    Resume Codex · minimax-ai bundle
    Safely continue the task from a Codex CLI or VS Code session in the current workspace. Use when invoked as /resume-codex with an optional Codex session id, or when the user asks to pick up their latest Codex work.
    13.8k repo stars
  5. ▌
    Deep Research · minimax-ai
    Use this skill for complex, open-ended Deep Research tasks that require external information verification. It is suitable for market/industry analysis, technical research, competitor research, trend judgment, policy/academic/fact verification, and long answers that need source citations.
    13.8k repo stars
  6. ▌
    X Link Reader · minimax-ai
    Read X/Twitter content from x.com or twitter.com URLs. Use when the user shares an X or Twitter link (tweet or profile) and asks about its content. Also use when webfetch fails on x.com with anti-bot errors. Bypasses X's anti-scraping via the FxTwitter API — no API key needed.
    13.8k repo stars
  7. ▌
    Deploy Website · minimax-ai
    Publish the first release of an existing local website project or standalone local `.html` or `.htm` file to a public URL. Use when a user asks to deploy or launch a local website, static site, frontend project, or asks to deploy an absolute HTML file path; use edit-deployed-website to edit an already deployed website.
    13.8k repo stars
  8. ▌
    Mcode Tools Master · minimax-ai
    You must load this skill before running any `mcode-tools` Bash command. The `mcode-tools` CLI is available on PATH and can be invoked directly from Bash. It is the primary entry point for discovering, inspecting, and calling any Connector tool when tool use must be combined with Bash scripts, pipes, local files, loops, or batch automation. It is also the primary entry point for multimodal generation and understanding, including images/photos, video/audio/music, and documents. For an ordinary direct call to a connected plugin or MCP tool already in the model's tool list, call that tool directly and do not load this skill solely for access.
    13.8k repo stars
  9. ▌
    Edit Deployed Website · minimax-ai
    Edit, revise, redesign, fix, or update an already deployed website. Use for requests to change an existing public website; the Desktop Edit entry supplies trusted node_id and workspace source_path before redeployment.
    13.8k repo stars
  10. ▌
    Lark Im · minimax-ai bundle
    飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件(支持大文件分片下载)、管理表情回复。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员时使用。
    13.8k repo stars
  11. ▌
    Lark Vc · minimax-ai bundle
    飞书视频会议:查询会议记录、获取会议纪要产物(总结、待办、章节、逐字稿)。1. 查询已经结束的会议数量或详情时使用本技能(如历史日期| 昨天 | 上周 | 今天已经开过的会议等场景),查询未开始的会议日程使用 lark-calendar 技能。2. 支持通过关键词、时间范围、组织者、参与者、会议室等筛选条件搜索会议记录。3. 获取或整理会议纪要时使用本技能。
    13.8k repo stars
  12. ▌
    Lark Wiki · minimax-ai bundle
    飞书知识库:管理知识空间、空间成员和文档节点。创建和查询知识空间、查看和管理空间成员、管理节点层级结构、在知识库中组织文档和快捷方式。当用户需要在知识库中查找或创建文档、浏览知识空间结构、查看或管理空间成员、移动或复制节点时使用。
    13.8k repo stars
  13. ▌
    Lark Drive · minimax-ai bundle
    飞书云空间:管理云空间中的文件和文件夹。上传和下载文件、创建文件夹、复制/移动/删除文件、查看文件元数据、管理文档评论、管理文档权限、订阅用户评论变更事件、修改文件标题(docx、sheet、bitable、file、folder、wiki);也负责把本地 Word/Markdown/Excel/CSV 导入为飞书在线云文档(docx、sheet、bitable)。当用户需要上传或下载文件、整理云空间目录、查看文件详情、管理评论、管理文档权限、修改文件标题、订阅用户评论变更事件,或要把本地文件导入成新版文档、电子表格、多维表格/Base 时使用。
    13.8k repo stars
  14. ▌
    Lark Sheets · minimax-ai bundle
    飞书电子表格:创建和操作电子表格。创建表格并写入表头和数据、读取和写入单元格、追加行数据、在已知电子表格中查找单元格内容、导出表格文件。当用户需要创建电子表格、批量读写数据、在已知表格中查找内容、导出或下载表格时使用。若用户是想按名称或关键词搜索云空间里的表格文件,请改用 lark-doc 的 docs +search 先定位资源。
    13.8k repo stars
  15. ▌
    Minimax Code Product · minimax-ai bundle
    Use this skill to route questions about the MiniMax Code or Mavis product itself: product identity and ownership; Desktop/Electron, Web/H5, CLI/TUI surfaces; installation, uninstall, upgrade, release, download, version, and platform support; product workflows; Agents, Sessions, Memory, Teams, Skills, Plugins, and MCP; accounts, Token Plan, subscriptions, credits, API keys, BYOK, models, pricing, quotas; and MiniMax Code image, audio, music, or video capabilities. Treat references such as "MiniMax Code", "Mavis", "mcode", "mcode tui", or product features and settings as product-routing signals even when the user asks for a concrete local operation. Use this skill before a general coding, shell, or web skill when the requested operation concerns the product's own installation, configuration, behavior, or documentation. Do not use it for an unrelated coding task merely because the task is performed in this workspace.
    13.8k repo stars
  16. ▌
    Lark Whiteboard · minimax-ai bundle
    飞书画板:查询和编辑飞书云文档中的画板。支持导出画板为预览图片、导出原始节点结构、使用 PlantUML/Mermaid 代码或 OpenAPI 原生格式更新画板内容。 当用户需要查看画板内容、导出画板图片、或编辑画板,或是需要可视化表达架构、流程、组织关系、时间线、因果、对比等结构化信息时使用此 skill,无论是否提及"画板"。
    13.8k repo stars
  17. ▌
    Control In App Browser · minimax-ai
    Control the current chat's session-scoped Browser provider for opening, navigating, inspecting visible or interactive page state, clicking, typing, pasting explicit text, uploading current-turn user attachments or active- workspace files, screenshots, and local web testing. It can have an existing signed-in session when the active provider preserves one. Explicit requests for the in-app, embedded, right-side, current, or FilePanel Browser use this skill; for linked resources without explicit Browser intent, prefer a purpose-built connector, API, or CLI when available.
    13.8k repo stars
  18. ▌
    Lark Workflow Meeting Summary · minimax-ai
    会议纪要整理工作流:汇总指定时间范围内的会议纪要并生成结构化报告。当用户需要整理会议纪要、生成会议周报、回顾一段时间内的会议内容时使用。
    13.8k repo stars
  19. ▌
    PDF · minimax-ai bundle
    Unified PDF skill — generate, reformat, fill, and read PDFs. Covers: text-to-PDF (reports, resumes, proposals, 可视化报告), LaTeX thesis, Markdown→PDF conversion, PDF form filling, and PDF reading/extraction/OCR. Trigger on any task with PDF as primary input or output. Not for DOCX or PPT.
    13.8k repo stars
  20. ▌
    DOCX · minimax-ai bundle
    Unified DOCX skill — create, template-apply, edit/fill, read, repair, and compare Word documents. Use for formal Word deliverables and DOCX diagnosis. Not for PDF/PPT or casual plain-text drafting.
    13.8k repo stars
  21. ▌
    PPTX · minimax-ai bundle
    Read, create, and edit PowerPoint PPTX/PPT presentations. Covers: parsing, summarizing, extracting content, inspecting themes/layouts, creating new decks with PptxGenJS, and editing existing PPTX while preserving formatting.
    13.8k repo stars
  22. ▌
    XLSX · minimax-ai bundle
    Spreadsheet skill — read, edit, create, and convert .xlsx/.xlsm/.csv/.tsv files. Trigger when a spreadsheet file is the primary input or output: editing columns, formulas, formatting, charting, cleaning messy data, or creating new spreadsheets. Not for Word/HTML/PDF deliverables even if tabular data is involved.
    13.8k repo stars
  23. ▌
    Cu Desktop · minimax-ai
    Computer Use desktop operation guide. Auto-injected when CU mode is enabled.
    13.8k repo stars
  24. ▌
    Lark Tools · minimax-ai bundle
    Feishu/Lark full-capability access via the official `lark-cli` (terminal) plus native local-runtime Feishu channel binding/status. Use this skill whenever the user mentions anything related to Feishu or Lark, including but not limited to: checking today's schedule or a specific date's agenda, creating calendar events, querying free/busy status, viewing or creating tasks, searching group chats, reading chat history, sending or replying to messages, looking up contacts or user details, querying or writing Bitable (multi-dimensional table) records, searching documents, or running any lark-cli subcommand. ALSO use this skill to READ or OPEN a Feishu/Lark document, wiki, sheet, or Base from a link — any `feishu.cn`, `larksuite.com`, or `*.feishu.cn` URL (including `/docx/`, `/wiki/`, `/sheets/`, `/base/`, `/w000/`, `/file/` paths), even when the user just pastes the bare URL without saying "Feishu". Route by link type, NOT `webfetch`: a doc/docx/wiki link → `lark-cli docs +fetch` (it resolves both docx and wiki UR
    13.8k repo stars
  25. ▌
    Harness Experiment · minimax-ai
    Run 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.
    13.8k repo stars
  26. ▌
    Independent Review · minimax-ai
    Review 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.
    13.8k repo stars
  27. ▌
    Long Command Check · minimax-ai
    Audit 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.
    13.8k repo stars
  28. ▌
    Long Session Check · minimax-ai
    Check 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.
    13.8k repo stars
  29. ▌
    Example · minimax-ai
    Replace 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.
    13.8k repo stars
  30. ▌
    Subagent Split Check · minimax-ai
    Decide 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.
    13.8k repo stars
  31. ▌
    Engineering Small Prs · minimax-ai
    Use 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.
    13.8k repo stars
  32. ▌
    Evidence First Review · minimax-ai
    Review an agent's finished work by reading the evidence before its summary, naming what each check proves and what it misses, pulling out the decisions it made silently, and trying to falsify the result before accepting it. Use when a MiniMax Code session, subagent or cloud agent reports a task done, before merging its PR or acting on its analysis.
    13.8k repo stars
  33. ▌
    Review Capacity Check · minimax-ai
    Check whether finished agent work is piling up faster than we can stand behind it, and fix that by tightening automatic checks or running fewer parallel sessions instead of starting another one. Also checks that multi-agent chains read original sources, and which skills we are letting go. Use before launching another parallel session or subagent batch, at the end of a day with many agent PRs, or in a weekly review.
    13.8k repo stars
  34. ▌
    Engineering Code Review · minimax-ai
    Use 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.
    13.8k repo stars
  35. ▌
    Engineering Review Comments · minimax-ai
    Use 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.
    13.8k repo stars
  36. ▌
    Engineering Review Feedback · minimax-ai
    Use 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.
    13.8k repo stars
  37. ▌
    Engineering Emergency Changes · minimax-ai
    Use 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.
    13.8k repo stars
  38. ▌
    Engineering Change Descriptions · minimax-ai
    Use 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.
    13.8k repo stars
  39. ▌
    Lifting Loops · minimax-ai bundle
    Finds 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).
    13.8k repo stars
  40. ▌
    Taste To Checks · minimax-ai
    Turn a review correction we keep making on agent output into something that runs on its own, a test, lint rule, hook, CI step or project rule, so the miss does not come back next session. Use when we keep correcting agents on the same mistake (import order, naming, a forbidden API, a missing test), when the same review comment shows up on a second PR, or after a review finds a miss that a check could have caught.
    13.8k repo stars
  41. ▌
    Making Content · minimax-ai bundle
    Content 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.
    13.8k repo stars
  42. ▌
    Pr Description · minimax-ai
    Draft or check a pull request description in a fixed format (background, changes, behavior changes, out of scope, verification, rollback, not done, related) for GitHub or GitLab. Use when opening a PR, when the MCode Review summary reports missing description sections, or when the user asks for a PR description.
    13.8k repo stars
  43. ▌
    Req Prioritize · minimax-ai
    对一个已受理的需求,对照当前在做的工作(WIP)评估成本、影响、风险,给出排期建议和理由;提出人提建议,负责人拍板。Use after req-intake, at backlog grooming or sprint planning, or when someone asks 这个需求优先级多高 / 能不能插队.
    13.8k repo stars
  44. ▌
    Context Tax Audit · minimax-ai
    Inventory 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.
    13.8k repo stars
  45. ▌
    Tool Budget Audit · minimax-ai
    Audit 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.
    13.8k repo stars
  46. ▌
    Trajectory Review · minimax-ai
    Review 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.
    13.8k repo stars
  47. ▌
    Magic Move Deck · minimax-ai bundle
    Build Keynote-style Magic Move slide decks as one offline 1920×1080 HTML file: every slide is an architecture / flow diagram seen through a camera, and the elements two slides share morph and fly instead of cross-fading. Four visual styles (hand-drawn, minimal, dark neon, neo-brutalist): the agent first renders one sample slide in each style, the user picks one, then the whole deck is built in that style. Also exports 4K / 1080p video. Use for 做演示 / 做 slides / 做 PPT / Magic Move / 神奇移动 / 架构图演示 / 技术分享 deck / 动画 slides / animated architecture walkthrough. Not for bullet-point decks or a single static diagram.
    13.8k repo stars
  48. ▌
    Pr Review Tuning · minimax-ai bundle
    The weekly self-tuning loop for the MCode Review bot on GitHub or GitLab. Measures the bot on a repository's recent PRs (threads per PR, which kinds people answer or dismiss, what was unanswered at merge, cost per round, time to merge, follow-up fixes), finds noise and misses, proposes at most three rule changes with their expected effect on each goal, backtests them on past PRs with known outcomes within an agreed token budget, has an independent check recompute the numbers, and changes rules only after a person approves. The first run only measures. Use for requests to run pr-review-tuning or to measure or tune the review bot, for the weekly scheduled run, and for settling a proposal (approve or reject P1).
    13.8k repo stars
  49. ▌
    Pr Quiz · minimax-ai
    Write multiple-choice questions that check whether a PR's author understands their change. Use only when the MCode Review pipeline asks for an author quiz.
    13.8k repo stars
  50. ▌
    Req Ship · minimax-ai
    上线前做就绪检查(回滚方案、可观测性、完成定义 DoD),全部有证据后再推进 Meegle 状态或节点。Use before a requirement is deployed or marked done, when someone says 可以上线了吗 / 准备发布, or before transitioning the work item to a released state.
    13.8k repo stars
  51. ▌
    Pr Review 2 · minimax-ai bundle
    Review a pull request or the current branch with the MCode Review rules (severity, evidence ladder, lens checklists, review principles) and the repository's own .mcode-review.json and .mcode-review.md. Works with GitHub pull requests and GitLab merge requests. Use when the MCode Review CI pipeline starts a review pass, or when a developer asks to review their PR or branch before asking a person to review it.
    13.8k repo stars
  52. ▌
    Req Track · minimax-ai
    按固定节奏跟进进行中的需求,用站会格式记录进展、阻塞和下一步;超过约定时间没有更新的需求要显式标出来,不能悄悄沉下去。Use for daily or weekly requirement check-ins, when asked 这个需求到哪了 / 有没有卡住的, or from a scheduled routine.
    13.8k repo stars
  53. ▌
    Agent Brief · minimax-ai
    Write the brief before handing a non-trivial task to an agent or subagent, covering stakes, your own hypothesis, goal and scope in your words, what "verified" will mean, and whether the agent is thinking with you or for you. Use before starting a MiniMax Code session, spawning a subagent, or delegating a PR, analysis or doc.
    13.8k repo stars
  54. ▌
    Handoff Doc · minimax-ai
    Write 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.
    13.8k repo stars
  55. ▌
    Req Design · minimax-ai
    为已排期的需求做方案:列至少两个选项、写决策记录、评估波及面(blast radius)、定验收检查点,全部落进需求文档。Use when a requirement is scheduled and before implementation, or when someone asks 方案怎么定 / 这个改动会影响哪些地方.
    13.8k repo stars
  56. ▌
    Req Intake · minimax-ai
    在需求刚提出时,先挑战它是否该做,写下一条能验证的预期效果,再用模板建飞书需求文档和飞书项目(Meegle)工作项,两边互相链接。Use when someone raises a product or technical requirement, says 提需求 / 我想要 / 能不能加, or before any requirement work starts without a doc and a work item.
    13.8k repo stars
  57. ▌
    Req Outcome · minimax-ai
    上线后对照 intake 写下的预期效果收集证据,判断是否达成;没达成就写清差距和下一步;只有拿到证据才关闭需求。Use after the observation window of a shipped requirement, when someone asks 这个需求效果怎么样 / 可以关了吗, or before closing a work item.
    13.8k repo stars
  58. ▌
    Pr Review CI · minimax-ai
    Connects a GitHub or GitLab repository to the MCode Review CI and keeps the setup current. Use when someone adds MCode Review to a repository on GitHub Actions or GitLab CI, upgrades or rolls back the pinned plugin commit, changes the repository's rule pack, language, models, shadow or enforce phase, author quiz or Feishu card, checks the security setup, or troubleshoots a review run that failed.
    13.8k repo stars
  59. ▌
    Mcode Island · minimax-ai
    Push the user's terminal out of focus to a Windows desktop Dynamic Island pill so the user can watch your work without switching back to mcode. On mcode 0.2.4+ with the `io.minimax.mcode` Hooks extension enabled (forward-compatible with MiniMax-Code-Plugins PR
    13.8k repo stars
  60. ▌
    Scientific Figure Delivery · minimax-ai bundle
    Create, revise, or audit publication-grade life-science figures with source-data traceability, export QA, and a PNG preview shown directly in the agent conversation. Use for manuscript figures, not dashboards or decorative infographics.
    13.8k repo stars
  61. ▌
    Hello Mcode Hooks V04 · minimax-ai bundle
    Observer example for the mcode 0.4.0+ plugin format. Activates when a Plugin author needs a reference layout for inline Hooks under .claude-plugin/plugin.json.
    13.8k repo stars
  62. ▌
    Jianying Cut · minimax-ai
    Use when: 给视频按调色参数或风格出片 / 给剪映草稿一条命令出成片 / 用复刻的剪映调色链出 10bit 成片 / 按暖色、清爽、电影感、明亮风格调色 / 调色后出带原声的片 / 调完对比成片画面变没变. 触发词: 给这个视频调色出片 / 把这个剪映草稿出成片 / 草稿导出成片 / 按XX风格调色 / 出个10bit的片 / 剪映调色 / 调色后出片 / 出带声音的片 / 剪映出片 / 调完对比画面变没变.
    13.8k repo stars
  63. ▌
    Web Search · minimax-ai bundle
    Use when the user asks to research a topic on the web, gather information from multiple sources, do a literature scan, summarize recent developments on a subject, or look up articles. Triggers on requests like "调研 X", "找几篇关于 Y 的文章", "research Z", "汇总 Q 的资料", "look up the latest on W". Do NOT use for single-URL fetches with no research framing (use the defuddle skill directly), local file operations, code edits, or tasks that do not need web data.
    13.8k repo stars
  64. ▌
    Jianying Review · minimax-ai
    Use when: 审片 / 检查这版剪得对不对 / 返修验收 / 这版片子整体过不过关 / 画质或响度有没有问题 / 交片前检查. 触发词: 审一下这版 / 看看剪得对不对 / 这版片子审得过吗 / 交片前检查 / 画面有没有过曝 / 响度够不够 / 时间线对不对.
    13.8k repo stars
  65. ▌
    Jianying Verify · minimax-ai
    Use when: 需要一套验收判据/口径时 / 设计验收判据 / 判据视野不够要自检 / 被问"这个怎么才算通过" / 审片要给验收口径时. 本 skill 是【库】—— 仅在其它 skill 引用它、或用户明确要验收方法时被使用,不主动触发. 触发词: 怎么算通过 / 验收判据怎么定 / 这个改动该怎么证明 / 判据视野够不够 / 判据自检.
    13.8k repo stars
  66. ▌
    Jianying Pipeline · minimax-ai
    Use when: 用户要的是【一件事做完】而不是单一步骤时 / 调完色还要出成片 / 改完草稿顺便审一遍 / 剪完口播再出成片 / 全流程走一遍 / 把这条片子从头做到尾. 触发词: 一站式做完 / 全流程走一遍 / 把整条流程走完 / 改完直接出片 / 顺便也出个片.
    13.8k repo stars
  67. ▌
    Jianying Talk Cut · minimax-ai
    Use when: 剪口播 / 去掉口播里的废话、停顿、重复、卡壳 / 按转写稿整理口播 / 把长口播剪短 / 剪完落稿并回读时间线确认. 触发词: 把这段口播的废话剪掉 / 去一下口水话 / 把停顿剪了 / 有重复的剪掉 / 口播剪干净点.
    13.8k repo stars
  68. ▌
    Jianying Draft Edit · minimax-ai
    Use when: 改剪映草稿 / 给草稿加素材或音轨 / 移动裁剪片段 / 调某段的音量 / 加文字 / 加轨道 / 撤销重做 / 改完落盘并回读草稿字段确认. 触发词: 给这个草稿加个片段 / 把这条素材剪短 / 把这轨静音 / 加个文字 / 改完存一下 / 撤销刚才那步 / 改完回读草稿字段对不对.
    13.8k repo stars
  69. ▌
    Jianying Grade Chain · minimax-ai
    Use when: 查某个调色节点/参数怎么填时 / 不确定某个调色效果该归到哪个节点时 / 调色链精度口径与可选节点清单时 / 用户给了调色参数要落到链上时. 本 skill 是【库】—— 仅在其它 skill 引用它、或用户明确问调色链细节时被使用,不主动触发. 触发词: 调色链有哪些节点 / 这个参数填哪个节点 / 调色能精确到什么程度 / 曲线的控制点怎么排.
    13.8k repo stars
  70. ▌
    Octopus Meme Maker · minimax-ai bundle
    Use this skill when the user asks for a new pink-octopus office-worker GIF meme, a Smooth Squishmallow-style worker octopus sticker, a 4-character Chinese caption on a 720x720 looping GIF, or wants to add a scene to an existing meme library. Drives a 4-stage pipeline (base pose via image_synthesize -> 6s 24fps video via gen_videos -> transparent Chinese text overlay via Pillow -> 720x720 + 480x480 GIF via ffmpeg) and enforces a strict character-anatomy ban-list. Read this skill before starting any new scene.
    13.8k repo stars
  71. ▌
    Omics Workflow · minimax-ai
    Plan, audit, or interpret public or user-authorized sequencing and omics workflows, including bulk RNA-seq, single-cell, amplicon, metagenomic, variant, and metabolomic analyses. Use only after design and metadata fit are checked.
    13.8k repo stars
  72. ▌
    Evidence Review · minimax-ai bundle
    Independently review a life-science manuscript, analysis, figure package, or repository for claim support, citation validity, numeric traceability, figure-code-data consistency, reproducibility, and privacy. Use as a final gate, not as author self-approval.
    13.8k repo stars
  73. ▌
    Local Bio Toolkit · minimax-ai
    Detect and selectively use local life-science desktop or structural tools, including safe PyMOL rendering and explicit file opening in SnapGene, Cytoscape, or Fiji. Use when a user asks to work with these installed applications; never install tools silently or accept arbitrary commands.
    13.8k repo stars
  74. ▌
    Minimax Code Badge · minimax-ai bundle
    Use whenever creating a GitHub pull request - append the "powered by MiniMax Code" badge to the end of the PR description. Also use when the user asks to add, refresh, or remove the MiniMax Code badge on a PR or Markdown deliverable. GitLab merge requests only when the user explicitly asks. Skip when the user has said not to add the badge.
    13.8k repo stars
  75. ▌
    Manuscript Argument · minimax-ai bundle
    Draft or restructure life-science Introduction and Discussion sections from supplied claims, results, figures, and verified literature. Use for argument construction; do not invent evidence, citations, or causal strength.
    13.8k repo stars
  76. ▌
    Rna Figure Workflow · minimax-ai bundle
    Create and audit common RNA-seq result figures locally, including volcano, PCA, heatmap, expression boxplot, and enrichment dotplot, with PNG/PDF delivery and inline conversation preview. Use for RNA result plotting from user-selected tables; do not use private bundled datasets.
    13.8k repo stars
  77. ▌
    Public Bio Databases · minimax-ai bundle
    Query public biological databases for genes, proteins, domains, structures, literature, networks, motifs, or general Solanaceae metadata through the bundled allowlisted MCP. Use for evidence lookup; never route private or pepper-specific data through it.
    13.8k repo stars
  78. ▌
    Dynamic Workflow · minimax-ai
    Plan and coordinate complex tasks as editable JavaScript workflows with multiple MCode agents. Create a pending-review draft, automatically open its topology in the MCode built-in browser, let the user edit and start it, then track parallel research, code reviews, batch processing, verification, and synthesis with live statuses, logs, results, configurable budgets, pause, cancel, resume, and error-guided repair with reviewed reuse of successful results.
    13.8k repo stars
  79. ▌
    Quantitative Research · minimax-ai
    Design or review statistical, mixed-model, Bayesian, or machine-learning analyses for life-science data. Use when the main risk is estimand, dependence, model choice, diagnostics, leakage, or uncertainty.
    13.8k repo stars
  80. ▌
    Reproducible Analysis · minimax-ai
    Turn a life-science analysis into a cleanly rerunnable workflow with protected raw data, centralized parameters, fixed seeds, environment capture, provenance, and verified outputs. Use for publication or handoff-quality analysis.
    13.8k repo stars
  81. ▌
    Secure Compute Routing · minimax-ai
    Decide whether a life-science computation should run locally, on a controlled HPC over SSH, or on an external cloud GPU based on data sensitivity, scale, cost, and reproducibility. Use before moving data or launching remote work.
    13.8k repo stars
  82. ▌
    Mcode Trajectory Studio · minimax-ai
    Inspect and visualize MiniMax Code session trajectories from the local runtime's read-only SQLite projection. Use when the user asks what happened in a session, why a task was slow or expensive, how many turns or tool calls a run took, which tools failed, how much wall-clock time went to the model versus tools, where context was spent, when compaction ran, which sub-agents were dispatched, or wants an interactive timeline of a session. Trigger phrases include "轨迹", "trajectory", "这个会话花了多久", "为什么这么慢", "调用了哪些工具", "session 时长/轮次", "看看某个 session".
    13.8k repo stars
  83. ▌
    Experimental Design Gate · minimax-ai
    Audit whether biological materials, sampling, controls, replication, and measurements can answer a proposed question before experiments or analysis. Use for study planning and Go/No-Go decisions.
    13.8k repo stars
  84. ▌
    Bio Research Orchestrator · minimax-ai bundle
    Coordinate a life-science research request that spans design, public databases, omics, statistics, writing, figures, reproducibility, or independent review. Use for multi-stage research work; do not use for a single narrow lookup.
    13.8k repo stars
  85. ▌
    Mmx CLI 2 · minimax-ai bundle
    Use mmx to generate text, images, video, and speech, and to transcribe audio, via the MiniMax AI platform. Use when the user wants to create media content, chat with MiniMax models, transcribe audio to text, perform web search, or manage MiniMax API resources from the terminal.
    13.8k repo stars
  86. ▌
    H3 Prompt Writing 2 · minimax-ai bundle
    Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, or defining reference labels for images, videos, and audio.
    13.8k repo stars
  87. ▌
    Customize 2 · minimax-ai
    当用户说"修改画像/改一下我的设置/更新我的信息/换个身份/修改红线/改输出偏好/ 调整 guardrails/改规则/换数据源配置/我刚考了律师证/我换行业了"时使用。这是 修改 docs/guardrails.md 执业画像与 Shared guardrails 的唯一入口:读取现状 → 与使用者 确认修改内容 → 写回 → 提示本次修改影响哪些技能行为。防止直接手改跳过影响评估, 也防止多人协作时画像被无声覆盖。
    13.8k repo stars
  88. ▌
    Task Tracker 2 · minimax-ai bundle
    Use when: 任务追踪与日报周报生成。用于记录老板工作进度、生成日报周报、持续追踪任务完成情况。.
    13.8k repo stars
  89. ▌
    Cold Start Interview 2 · minimax-ai
    当用户首次使用本插件、docs/guardrails.md 执业画像中仍存在 [填空]、用户说"初始化设置/开始访谈/ 设置我的信息/配置画像/重新做一遍设置/检查数据源配置是否生效/检查北大法宝 token"时 使用。通过结构化访谈收集使用者的角色、法域、行业、常做业务、红线条款、升级矩阵、 签署流程、数据源与输出偏好,并以散文形式写回 docs/guardrails.md 执业画像章节。支持 quick (3 分钟 6 问)、full(20 问)、--redo(重谈)、--check-integrations(只检查凭证) 四种模式,支持中断后凭 [PENDING] 标记续谈。
    13.8k repo stars
  90. ▌
    Acp Task Dispatch · minimax-ai
    Dispatch a self-contained task to the OpenClaw-mcode-ACP HTTP server from inside MiniMax Code. Use when a task should be persisted, retried, observed over time, or processed by a worker pool instead of the current MiniMax Code session.
    13.8k repo stars
  91. ▌
    Document Skills PDF · minimax-ai bundle
    Create, extract, transform, or analyze PDF documents. Use this Skill whenever a .pdf file is the input or output - generating reports, one-pagers, posters or structured documents as real selectable-text PDFs; extracting text, tables or images from existing PDFs; merging, splitting, rotating, or watermarking pages; filling forms; checking that a produced PDF has the right page count and extractable text.
    13.8k repo stars
  92. ▌
    Labor Contract Review · minimax-ai
    当用户提供劳动合同、聘用协议、录用通知(offer)或续签/变更协议文本,要求审查 条款合法性、完备性或对本方利弊时使用。覆盖场景:新签劳动合同审查、续签文本 比对、offer 与正式合同一致性核对、入职文件包中的合同文本审查。同义场景词: 劳动合同审查、offer 审查、入职合同审查、续签合同审查。执行链路:画像与 blocks 红线检查、雇主/员工视角确认、必备条款核对、试用期合法性、服务期与 违约金限定、竞业限制三要件审查、按视角三色分桶输出 memo,收尾过引用审计 并提示下一步。
    13.8k repo stars
  93. ▌
    Privacy Policy Review · minimax-ai
    当用户需要审查、修订或上架前核对隐私政策、个人信息保护政策、App 隐私条款 时使用。覆盖场景:隐私政策起草后自检、监管通报或检测问题后的整改复核、 版本更新合规审查、App 上架前隐私合规检查、第三方 SDK 清单与权限调用对应 核查。同义场景词:隐私政策审查、隐私条款审查、隐私声明、privacy policy review。执行全链路:八大检查类别逐项过堂、🟢🟡🔴 三色分桶、输出带 reviewer note 的审查 memo,问题项附整改建议与优先级;需要重写的条款不代拟,一律 建议转法务或律师起草。
    13.8k repo stars
  94. ▌
    Sales Contract Review · minimax-ai
    买卖合同专项审查技能,由 contract-review 路由器按合同类型路由加载,不直接面向用户 调用。覆盖场景:买卖合同、采购合同、购销合同、销售合同、供货协议、 订单+主协议结构的货物交易文本。同义场景词:买卖合同审查、采购合同审查、 购销合同审查、销售合同审查、供货协议审查。执行与 nda-review 同构的全链路: matter 上下文与产物去向检查、买方/卖方立场判定、买卖立场 playbook 加载或 补齐、八类分类检查(标的物与质量、交付与风险转移、价款与支付、验收、违约 责任、所有权保留、解除、管辖与争议解决)、按 playbook 三色分桶、输出统一 triage memo。
    13.8k repo stars
  95. ▌
    Trademark Search Prep · minimax-ai
    当用户准备申请商标、注册品牌标识,需要评估标志可注册性、确定申请类别、 准备申请材料时使用。覆盖场景:新品牌商标申请前评估、显著性初筛、尼斯 分类选择、近似检索策略制定、申请材料清单准备。同义场景词:商标注册、 商标申请准备、商标检索、LOGO 注册、品牌保护。执行链路:显著性与禁用 条款初筛、核心类+防御类类别规划、官方检索指引(人工执行)、主体与 材料清单、时间线与费用构成说明,收尾过引用审计并走后果门。本技能不做 「保证注册成功」的结论。
    13.8k repo stars
  96. ▌
    Verification Loop · minimax-ai
    Enforce a claim-to-proof workflow before declaring work complete. Use this Skill when a task involves implementation, debugging, review, or any other work that could be claimed complete without concrete evidence.
    13.8k repo stars
  97. ▌
    Background Task · minimax-ai
    Background Task
    13.8k repo stars
  98. ▌
    Parallel Fanout · minimax-ai
    Decompose a task into 2+ truly independent sub-tasks and dispatch them concurrently via separate `task()` calls. Pick whether to fan out explicitly, not by accident. USE WHEN: the user task is clearly decomposable into 2+ independent sub-tasks (independent files, independent probes, independent analyses), you would otherwise serialize work that has no real dependency, user said "in parallel" / "并行" / "fan out" / "spawn agents" / "同时跑". TRIGGER PHRASES: "in parallel", "parallel", "fan out", "spawn agents", "并行", "同时", "concurrent", "subagents", "multi-agent", "同时跑几个". SKIP WHEN: sub-tasks have a hard data dependency (output of A is input of B), the user explicitly said "sequential" / "one at a time", there is only one sub-task.
    13.8k repo stars
  99. ▌
    Session Handoff · minimax-ai
    At session end, write a structured handoff file so next session can pick up in 30 seconds. USE WHEN: user says "今天先到这" / "done for today" / "see you tomorrow" / "we'll continue later" / "下次再继续" / "end session" / "收尾", context about to compact, long task in progress, natural pause approaching (end of work day, end of milestone), sub-task in flight that outlives this session. TRIGGER PHRASES: "今天先到这", "done for today", "see you tomorrow", "we'll continue later", "下次再继续", "先到这", "end session", "session 结束", "收尾", "写到 handoff file", "wrap up", "session handoff", "session 接力". SKIP WHEN: session just started (no in-progress work to hand off), work is fully complete and verified (completion-audit passed), user said "throw it all away, start fresh next time" / "全部扔掉".
    13.8k repo stars
  100. ▌
    Document Skills DOCX · minimax-ai bundle
    Create, read, edit, or review Microsoft Word .docx documents. Use this Skill whenever the task involves a .docx file - generating reports, letters, or structured documents from scratch; extracting or reorganizing content; applying consistent formatting (headings, tables, styles, headers/footers, page numbers); editing an existing document while preserving its layout; or checking that a produced document actually opens and renders.
    13.8k repo stars