zai-org
- 167 skills
- 0 followers
- 477 repo stars
- 6 days ago last updated
- ▌ Setup · zai-orgLocate or install the official native Godot editor and verify its built-in CLI before creating, opening or editing a game project.
- ▌ CLI · zai-orgCreate and edit Godot game projects using the official CLI and project files, open the original desktop editor to show iterations, and run games with visible feedback. Use for Godot scenes, GDScript, game development, debugging and exports.
- ▌ Ruic Card · zai-org bundleGenerate interactive 3D holographic collectible-card websites from a user description or reference image, using layered artwork, Blender and Three.js. Includes project-local Blender installation, reusable parallax materials and browser verification. Use when the user asks for 全息闪卡, 镭射卡, 3D 卡牌网页, a holographic collectible card site, or an editable card.blend.
- ▌ Photo Card · zai-org bundleTurn a photo the user already has into a 3D holographic card — cut the subject into the four card layers with rembg, optionally erase a watermark from the original, build the card with the ruic-card pipeline, render a 10-second animation and encode MP4 / WeChat-sized GIF deliverables. Use when the user brings a photo, screenshot or scan and asks for 全息闪卡, 照片转闪卡, 把照片做成卡, 去水印, 卡片动图, a holographic card from my photo, or an animated card video. Use the ruic-card skill instead when the artwork has to be generated from a text description.
- ▌
- ▌ Jupyter Notebook · zai-orgWork with Jupyter notebooks (.ipynb) in the Jupyter Notebook side panel — create, read, edit and run cells on a Jupyter Server, together with the user. Use when the user wants a notebook, asks to analyse data or prototype in Jupyter, mentions a .ipynb file or a running JupyterLab / Jupyter Server, or when the panel sends a message about a notebook cell.
- ▌
- ▌ Jev Judgment · zai-orgConventions for the Jev judgment tools (jev_verify, jev_screen, jev_noul, jev_find, jev_rerank, jev_classify, jev_decide, jev_compare, jev_extract, jev_review, jev_gate). Use when screening fetched or pasted content before it enters context, verifying claims against cited evidence, ranking or classifying items by meaning, extracting fields with a recognizable shape, reviewing a patch, gating task completion, or judging how likely a proposition is — and when choosing between a judgment tool, ripgrep, or plain reading. Requires the bundled jev MCP server (enabled together with the plugin) and a TypeSafe API key.
- ▌ Developing MCP Apps · zai-org bundleDevelop, migrate, build, and test MCP Apps for ZCode using the official MCP Apps SDK. Covers ZCode plugin manifests, persistent panel entries, host capabilities, and standalone distribution.
- ▌
- ▌ Tripo 3d · zai-org bundleGenerate a 3D model from a text prompt, a reference image, or an existing mesh, and deliver it as GLB, FBX, OBJ, STL, USDZ or 3MF. Use when the user asks for a 3D asset, model, mesh, prop, character or texture for a game, renderer, viewer, AR scene or 3D print — including requests like "make me a low-poly X", "turn this image into 3D", "rig this character", "convert this model to FBX", or "generate placeholder assets". 中文触发词:生成3D模型、建模、3D素材、把图片变成3D、图生3D、文生3D、骨骼绑定、绑骨、角色动画、贴图、纹理、低模、低多边形、减面、3D打印、手办、格式转换(FBX/GLB/OBJ/STL/USDZ/3MF)。Also use to re-run, convert or inspect a previous Tripo generation.
- ▌ Unity Setup · zai-org bundleInstall Unity CLI and the matching Unity Editor, check the local environment, and resolve first-run setup or licensing blockers in ZCode. Use before Unity CLI workflows to check version compatibility, or when installation, licensing, or Editor reconnection needs troubleshooting.
- ▌ Anet · zai-orgWork with other AI agents through AgentNetwork (anet): find an agent, send it a task over A2A, wait for the result, pay for a priced skill within the operator's limits, and answer tasks other agents sent to this node. Use when the user mentions anet, AgentNetwork, an agent's AID, or wants to hand work to another agent.
- ▌ Libtv CLI · zai-org bundleLibTV 官方 CLI(libtv):在命令行里完整操作 / 运行 LibTV 画布。 凡是和 LibTV 画布 / 项目 / 节点 / 模型 / 素材相关的操作,一律通过 libtv CLI 完成, 不要自己捏造 HTTP 请求或绕到网页端步骤。本 skill 内即包含完整的 CLI 命令操作手册; 常见场景见 examples/,安装/更新见 scripts/install.md。
- ▌ JSON Canvas · zai-org bundleCreate and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian. Also generates complete canvases from raw text content (articles, outlines, brainstorms) using MindMap radial or freeform layouts.
- ▌ Typst · zai-orgWrite and fix Typst documents (.typ) with a live preview in the Typst side panel — compile with the user's own Typst, read errors with file:line and hints, look at rendered pages as images, point at places in the preview, and export PDFs. Use when the user works on a Typst document (papers, theses, reports, letters, CVs, slides with touying/polylux), mentions Typst or a .typ file, asks to typeset or lay out something in Typst, or when the panel sends a selection, a source location or Typst problems.
- ▌ Anet Setup · zai-orgCheck, install or update the anet command line, start the local anet node, join a hub and verify the setup, so that the anet MCP tools of this plugin can start. Use when the anet tools are missing, when the user asks to install, set up, update or repair anet or AgentNetwork, or when anet reports daemon_not_running.
- ▌ Unreal MCP · zai-org bundleUse this skill to perform actions inside an Unreal Engine project via a live-editor MCP connection. Trigger when the user wants to change, query, or run something in their Unreal Engine project, not for conceptual or docs questions. Concrete triggers: spawn/move/duplicate/transform actors in a level, open a `.uproject`, add things around a PlayerStart, create or edit a Blueprint/Widget/Material/Niagara/Control Rig/Sequencer/Behavior Tree/GAS ability, read or write properties on actors (e.g. `bIsLocked` on `BP_DoorActor`), Live Coding recompile after editing C++ (`AActor`, `UMyComponent::Method`, `UPROPERTY`), or modify Static/Skeletal Mesh assets. Treat as Unreal context even without the word "Unreal": asset prefixes `BP_`, `WBP_`, `M_`, `MI_`, `NS_`, `CR_`, `SK_`, `SM_`, `ABP_`; UE C++ types/macros; `.uproject`; Content Browser; Outliner; PlayerStart; "in my game" plus UE signals. Skip for: pure conceptual/docs questions, Unity, Godot, or unrelated uses of "blueprint"/"sequencer"/"widget".
- ▌ Tripo Game Asset · zai-orgRecipes for producing game-ready 3D assets with Tripo and wiring them into a game project - low-poly props on a face budget, PBR hero assets, LOD chains, and rigged characters with locomotion clips for Unity, Unreal, Godot or Three.js. Use when the user is building a game or real-time 3D scene and needs props, characters, placeholder art, LODs, or an animated rig, rather than a single one-off model. 中文触发词:游戏资产、游戏素材、游戏模型、低模道具、面数预算、LOD、角色绑骨、走跑跳动画、Unity/Unreal/Godot 模型导入。
- ▌ Kicad Board · zai-orgDesign a 2-layer PCB with the KiCad plugin — circuit spec, real KiCad library lookups, auto-route, DRC, 3D render, Gerber/BOM/CPL export — show it in the KiCad side panel, and hand it to the real KiCad GUI when the user wants to keep editing. Use when the user wants a circuit board designed, checked, edited or exported.
- ▌ Design · zai-org用 OpenPencil 设计稿工具打开、修改、导出工作区里的 Figma .fig 设计稿,并根据设计稿写代码。当用户提到设计稿、Figma、.fig、.pen、画布、选中的元素、按稿写码时使用。
- ▌ Hyper3d Rodin · zai-orgGenerate Hyper3D Rodin Gen-2.5 models from text or images, split completed models with BANG, track progress, and retrieve result pages or requested model files.
- ▌ Excalidraw Diagram · zai-org bundleGenerate Excalidraw diagrams from text content. Supports three output modes - Obsidian (.md), Standard (.excalidraw), and Animated (.excalidraw with animation order). Triggers on "Excalidraw", "画图", "流程图", "思维导图", "可视化", "diagram", "标准Excalidraw", "standard excalidraw", "Excalidraw动画", "动画图", "animate".
- ▌ Knap · zai-orgRender Markdown from templates and structured data using Knap CLI. Use when the user asks to apply a Knap template, turn JSON or CSV data into notes, batch-generate Markdown files, or format Defuddle output into a note.
- ▌ Zotero · zai-orgWork with the user's Zotero library in the Zotero side panel — search papers, read their PDFs page by page and the user's own highlights, point at evidence with highlights in the PDF, cite (BibTeX / CSL styles) and keep a .bib file in the workspace, and add or organise items (arXiv / DOI import, notes, tags, collections). Use when the user mentions Zotero, their library, papers or references they have collected, citations or a .bib file, literature questions ("what do my papers say about…", "what did I highlight…"), or when the panel sends Zotero items or a quoted passage.
- ▌ Unity CLI · zai-org bundleControls the Unity Editor and projects from the command line, driving a running Editor to edit scenes and assets or run C#. Use when asked to install or manage Editors, licenses, or projects, set up version control, build, test, configure the Unity MCP server, or run any unity command.
- ▌ Defuddle · zai-orgExtract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.
- ▌ Glmocr 3 · zai-orgTrigger when: (1) User wants to extract text, tables, formulas, or structured data from images/PDFs/scanned documents, (2) User mentions "OCR", "文字识别", "文档解析", (3) User has a document (screenshot, scanned page, invoice, paper, whiteboard photo) and needs its content in structured form, (4) User asks to parse, digitize, or extract content from a visual document. Invokes the GLM-OCR SDK (pip install glmocr) to parse documents via Zhipu's cloud API. No GPU required. Returns structured JSON (regions with labels + bounding boxes) and Markdown. Agent can operate entirely via CLI — no YAML files needed. NOT for: real-time camera feeds, audio transcription, or non-document images (photos, illustrations).
- ▌ Glm Master Skill 2 · zai-orgDocumentation-only master skill for GLM ecosystem discovery and installation. This skill does not execute scripts or subprocess commands. It provides a curated list of official GLM skills, install methods, and source links.
- ▌ Glmv Caption 2 · zai-org bundleGenerate captions (descriptions) for images, videos, and documents using ZhiPu GLM-V multimodal model series. Use this skill whenever the user wants to describe, caption, summarize, or interpret the content of images, videos, or files. Supports single/multiple inputs, URLs, local paths, and base64 (images only).
- ▌ Glmv Grounding 2 · zai-org bundleA skill that uses GLM-V native grounding capabilities for coordinate conversion, bounding-box visualization, and more. GLM-V native grounding can locate any target specified by the prompt in an image and output relative coordinates normalized to 0-1000 based on image size. Coordinate formats include 2D bounding box (default), 2D points, and 3D bounding box. GLM-V also supports spatiotemporal localization and tracking of multiple prompt-specified targets in videos, outputting 2D bounding boxes per second.
- ▌ Glmv PDF To Ppt 2 · zai-org bundleConvert a PDF (research paper, report, or any document) into a polished multi-slide HTML presentation with a structured outline JSON and summary markdown. Trigger this skill when the user mentions making slides or a PPT from a PDF — in Chinese or English.
- ▌ Glmv PDF To Web 2 · zai-org bundleConvert a PDF (research paper, technical report, or project document) into a beautiful single-page academic/project website with a structured outline JSON. Trigger this skill when the user wants to make a paper page, project homepage, or academic website from a PDF — in Chinese or English.
- ▌ Glmv Prompt Gen 2 · zai-org bundleAnalyze images/videos and generate professional prompts for text-to-image and text-to-video AI tools (Midjourney, Stable Diffusion, DALL-E, Sora, Runway, Kling, Pika). Use when the user wants to generate prompts from reference images/videos, create AI art prompts, or get prompt engineering suggestions from visual content.
- ▌ Glmv Resume Screen 2 · zai-org bundleScreen and evaluate resumes against criteria using ZhiPu GLM-V multimodal model. Reads multiple resume files (PDF/DOCX/TXT), compares against user-defined screening criteria, and outputs a Markdown table with pass/fail analysis. Use when the user wants to filter resumes, compare candidates, or batch-evaluate job applications.
- ▌ Glmv Stock Analyst 2 · zai-org bundle股票分析与涨跌预测分析。 在用户表达分析、判断或预测意图时触发,如“分析一下腾讯”、“0700最近走势如何”、“XX能不能买”、“预测一下后续走势”、“生成一份分析报告”等; 支持港股、A股、美股,整合多源数据(包括新闻、基本面、技术面、资金流及宏观信息)进行多维综合分析,输出图文结合、包含可视化图表的结构化分析报告。 对于简单查询类需求(如“腾讯当前价格是多少”、“茅台代码是什么”)不触发本skill, 直接通过web_search 能力搜索并总结。 ⚠️ 需要多模态主模型支持(如 glm-5v-turbo),主模型需能读取图片。
- ▌ Glmv Doc Based Writing 2 · zai-org bundleWrite a textual content based on given document(s) and requirements, using ZhiPu GLM-V multimodal model. Read and comprehend one or multiple documents (PDF/DOCX), write a content in Markdown format according to the specified requirements. Use when the user wants to draft a paper/article/essay/report/review/post/brief/proposal/plan, etc.
- ▌ Impeccable 5 · zai-org bundleUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
- ▌ Impeccable 6 · zai-org bundleUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
- ▌
- ▌ Audit Xls 2 · zai-orgAudit a spreadsheet for formula accuracy, errors, and common mistakes. Scopes to a selected range, a single sheet, or the entire model (including financial-model integrity checks like BS balance, cash tie-out, and logic sanity). Triggers on "audit this sheet", "check my formulas", "find formula errors", "QA this spreadsheet", "sanity check this", "debug model", "model check", "model won't balance", "something's off in my model", "model review".
- ▌ XLSX Author 2 · zai-org bundleProduce a professional .xlsx workbook on disk with openpyxl — formula construction rules, colour conventions, and the mandatory recalc/error-check step before delivery. Use for any tabular deliverable that belongs in a file — valuation models, comps spreads, screen shortlists, batch risk tables, holdings breakdowns.
- ▌ Report Render 2 · zai-org bundleBuild paginated research deliverables (PDF, or DOCX where the reader edits the file) with correct CJK rendering, density-sized charts, clickable [n] citations, and a mandatory render-and-inspect gate. Use when a report, industry primer, earnings update, diligence report, working paper, memo, or any multi-page analyst deliverable must be produced as a file rather than chat text. Triggers on "出一份PDF", "导出报告", "生成研报", "报告存成文件", "导出Word", "存成docx", "给个可编辑版本", "export as PDF", "as a Word document", "build the report", "把报告存到".
- ▌ Glm Image Generation · zai-org bundleOfficial skill for generating high-quality images from text prompts using ZhiPu GLM-Image API. Excellent at scientific illustrations, high-quality portraits, social media graphics, and commercial posters. Supports multiple aspect ratios, HD quality, and watermark control. Use this skill when the user wants to generate images, create AI art, text-to-image, or convert text descriptions into visual content.
- ▌ Glmocr 2 · zai-org bundleExtract text from images using GLM-OCR API. Supports images and PDFs with high accuracy OCR, table recognition, formula extraction, and handwriting recognition. Use this skill whenever the user wants to extract text from images, perform OCR on pictures, scan documents, convert images to text, or process any image files to get their textual content.
- ▌ Impeccable 2 · zai-org bundleUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
- ▌ Impeccable 3 · zai-org bundleUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
- ▌ Impeccable 4 · zai-org bundleUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
- ▌ Glmocr Sdk · zai-orgTrigger when: (1) User wants to extract text, tables, formulas, or structured data from images/PDFs/scanned documents, (2) User mentions "OCR", "文字识别", "文档解析", (3) User has a document (screenshot, scanned page, invoice, paper, whiteboard photo) and needs its content in structured form, (4) User asks to parse, digitize, or extract content from a visual document. Invokes the GLM-OCR SDK (pip install glmocr) to parse documents via Zhipu's cloud API. No GPU required. Returns structured JSON (regions with labels + bounding boxes) and Markdown. Agent can operate entirely via CLI — no YAML files needed. NOT for: real-time camera feeds, audio transcription, or non-document images (photos, illustrations).
- ▌ Glm Image Gen · zai-org bundleOfficial skill for generating high-quality images from text prompts using ZhiPu GLM-Image API. Excellent at scientific illustrations, high-quality portraits, social media graphics, and commercial posters. Supports multiple aspect ratios, HD quality, and watermark control. Use this skill when the user wants to generate images, create AI art, text-to-image, or convert text descriptions into visual content.
- ▌
- ▌ Setup 3 · zai-orgCheck or install the latest Lark CLI, reuse existing profiles or guide first-time app and OAuth setup, and verify identity, scopes, and a minimal read-only call.
- ▌ CLI 2 · zai-orgUse the Alibaba Cloud CLI (aliyun) for cloud resource queries and operations after setup; choose product plugins from live help, preserve profile and region context, and gate remote writes.
- ▌ Setup 4 · zai-orgCheck or install the latest Alibaba Cloud CLI, reuse or configure a local profile, and verify caller identity before cloud operations.
- ▌ CLI 3 · zai-orgUse Tencent Meeting CLI (tmeet) to query or manage meetings, recordings, and attendee reports. Discover task-specific commands from live help after checking authentication.
- ▌ Setup 5 · zai-orgSet up Tencent Meeting CLI (tmeet) when installation, OAuth2 login, or authentication checks are needed. Resolve missing executables and verify readiness without exposing credentials.
- ▌ HTTP API Cloudbase · zai-org bundleCloudBase official HTTP API client guide. This skill should be used when backends, scripts, or non-SDK clients must call CloudBase platform APIs over raw HTTP instead of using a platform SDK or MCP management tool.
- ▌ Auth Tool Cloudbase · zai-org bundleCloudBase auth provider configuration and login-readiness guide. This skill should be used when users need to inspect, enable, disable, or configure auth providers, publishable-key prerequisites, login methods, SMS/email sender setup, or other provider-side readiness before implementing a client or backend auth flow.
- ▌ Cloudbase CLI · zai-org bundleCloudBase CLI (tcb, 云开发CLI, Tencent CloudBase命令行) resource management skill. This skill should be used when users need to deploy cloud functions, manage CloudRun apps, upload files to storage, query NoSQL/MySQL databases, deploy static hosting, set access permissions, or configure CORS/domains/routing via tcb commands. Also use for CI/CD pipeline scripting, batch operations, terminal-based CloudBase management, or when the user prefers CLI over SDK/MCP.
- ▌ Cloudbase Document Database Web Sdk · zai-org bundleUse CloudBase document database Web SDK only for confirmed NoSQL collection work. Query, create, update, and delete document data; if the task mentions PostgreSQL / CloudBase PG / app.rdb(), route to postgresql-development instead.
- ▌ Cloudbase Agent · zai-org bundleBuild and deploy AI agents with CloudBase Agent SDK (TypeScript & Python). Implements the AG-UI protocol for streaming agent-UI communication. Use when deploying agent servers, using LangGraph/LangChain/CrewAI adapters, building custom adapters, understanding AG-UI protocol events, or building web/mini-program UI clients. Supports both TypeScript (@cloudbase/agent-server) and Python (cloudbase-agent-server via FastAPI).
- ▌ Cloudbase Document Database In Wechat Miniprogram · zai-org bundleUse CloudBase document database WeChat MiniProgram SDK to query, create, update, and delete data. Supports complex queries, pagination, aggregation, and geolocation queries.
- ▌ Cloudbase Code Review · zai-org bundleCode review and validation for CloudBase projects. After writing code for Web / miniprogram / CloudRun / cloud-function projects, call this skill to check for known pitfalls — auth guard misuse, missing database tables, RLS misconfiguration, storage domain setup, and SDK API misuse. Supports automated lint scripts (regex-based) + LLM semantic review.
- ▌ Cloudbase Wechat Integration · zai-org bundleCloudBase WeChat integration guide for Mini Program WeChat Pay, Official Account JSAPI Pay, Native QR-code Pay, Official Account OAuth, openid handling, payment callbacks, and CloudBase Integration Center generated functions. This skill should be used when users ask to add, debug, or extend WeChat payment or official-account flows on CloudBase.
- ▌ Impeccable · zai-org bundleUse when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
- ▌ Seedance Prompt En · zai-orgWrite effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.
- ▌ SEO Site Audit Content Writer Competitor Analysis · zai-org bundleSEO specialist agent with site audits, content writing, keyword research, technical fixes, link building, and ranking strategies.
- ▌
- ▌ Git Essentials · zai-org bundleEssential Git commands and workflows for version control, branching, and collaboration.
- ▌
- ▌ Glmocr · zai-org bundleExtract text from images using GLM-OCR API. Supports images and PDFs with high accuracy OCR, table recognition, formula extraction, and handwriting recognition. Use this skill whenever the user wants to extract text from images, perform OCR on pictures, scan documents, convert images to text, or process any image files to get their textual content.
- ▌ Glmocr Table · zai-org bundleOfficial skill for recognizing and extracting tables from images and PDFs into Markdown format using ZhiPu GLM-OCR API. Supports complex tables, merged cells, and multi-page documents. Use this skill when the user wants to extract tables, recognize spreadsheets, or convert table images to editable format.
- ▌ Glmocr Formula · zai-org bundleOfficial skill for recognizing and extracting mathematical formulas from images and PDFs into LaTeX format using ZhiPu GLM-OCR API. Supports complex equations, inline formulas, and formula blocks. Use this skill when the user wants to extract formulas, convert formula images to LaTeX, or OCR mathematical expressions.
- ▌ Glm Master Skill · zai-orgDocumentation-only master skill for GLM ecosystem discovery and installation. This skill does not execute scripts or subprocess commands. It provides a curated list of official GLM skills, install methods, and source links.
- ▌ Glmocr Handwriting · zai-org bundleOfficial skill for recognizing handwritten text from images using ZhiPu GLM-OCR API. Supports various handwriting styles, languages, and mixed handwritten/printed content. Use this skill when the user wants to read handwritten notes, convert handwriting to text, or OCR handwritten documents.
- ▌ Pr · zai-orgCreate, list, check out, review, or merge GitHub pull requests using GitHub CLI. Use when the user wants any pull-request workflow, not when they want to manage issues, releases, or local-only commits.
- ▌ Gist · zai-orgCreate, view, edit, or delete GitHub gists for code and text sharing. Use when the user specifically asks to work with a gist, including public or secret gist visibility, not for files stored in a repository.
- ▌ Repo · zai-orgClone or fork a GitHub repository with optional local setup, or open repository resources such as files, branches, issues, and settings in the browser. Use when the user wants a new local checkout or the web UI, not a Codespace or an existing pull-request checkout.
- ▌ Glab · zai-orgGitLab CLI (glab) for working with GitLab from the command line. Read this skill before running any `glab` or GitLab API command — it applies to every GitLab operation, whether reading or writing (for example merge requests, issues, work items, discussions and threaded replies, comments, CI/CD pipelines, releases, packages, members, and project settings). Whenever a task touches GitLab in any way, consult this skill first so you use the correct, safe command on the first try. Prefer glab over raw API calls for all GitLab operations.
- ▌ Issue · zai-orgCreate, view, list, or close GitHub issues and manage the labels and milestones that organize issues and pull requests. Use when the user wants to track or organize repository work, not when they are referring to a pull request itself.
- ▌ Commit · zai-orgCreate a local Git commit from staged changes using a conventional commit message. Use when the user wants to record already prepared changes locally, not when they want to create, review, or merge a pull request.
- ▌ Secret · zai-orgList, set, delete, or synchronize GitHub Actions repository secrets without exposing secret values. Use when the user explicitly wants to manage GitHub secret storage, not ordinary environment files or repository variables.
- ▌ Release · zai-orgCreate a GitHub release and prepare changelog notes for a version tag. Use when the user wants to publish or draft a repository release, not merely create a Git commit, tag, or pull request.
- ▌ Codespace · zai-orgCreate, list, connect to, stop, or delete GitHub Codespaces. Use when the user explicitly wants to manage a remote Codespaces development environment, not for cloning a repository locally.
- ▌ Glab Stack · zai-orgManage stacked diffs and merge requests with the GitLab CLI. Use when the user wants to create, save, amend, sync, navigate, or reorder a stack of dependent merge requests. Triggers on tasks involving stacked diffs, stacked MRs, dependent merge requests, or incremental code review workflows using `glab stack`.
- ▌ Workflow Run · zai-orgList, inspect, trigger, watch, or rerun GitHub Actions workflows and runs. Use when the user wants to operate or inspect CI workflows, not when they only want to merge a PR or browse the Actions page.
- ▌ XLSX Author · zai-org bundleProduce a professional .xlsx workbook on disk with openpyxl — formula construction rules, colour conventions, and the mandatory recalc/error-check step before delivery. Use for any tabular deliverable that belongs in a file — valuation models, comps spreads, screen shortlists, batch risk tables, holdings breakdowns.
- ▌ Env Setup · zai-org bundleCheck and provision the video2code plugin environment: Python/MCP/video packages, ffmpeg/ffprobe, Node/npm, registry, and webapp cache. Browser interaction and recording use ZCode's built-in Browser Use WebView, so Playwright and external Chromium are intentionally not installed.
- ▌ Url2video · zai-orgRecord a live website with ZCode's built-in Browser Use WebView (native WebM), then transcode it to MP4 with ffmpeg. Use when a task starts from a URL and asks to record, capture, replicate, clone, 录制, 录屏, 复刻, 复现, or 还原 the site. Produces a recordings/name.mp4 deliverable (intermediate .webm kept) without Playwright or a separate Chromium.
- ▌ Fund Watch · zai-orgOngoing monitoring of held or shortlisted funds over a window — manager changes, size and flow shocks, 仓位 shifts, style drift, and performance/rank deviation — graded by what a holder must act on. Triggers on "基金跟踪", "持仓基金有没有问题", "基金预警", "盯一下这几只基金", "经理换人了吗", "fund watch", "规模异动".
- ▌ Cash Forecast · zai-orgA 13-week rolling direct cash forecast — opening cash, AR-ageing-driven receipts, disbursements (payroll, AP, tax, debt service, capex), closing cash, and headroom against a covenant or minimum balance, with an explicit collection curve and DSO assumption and a downside case. Triggers on "13周现金流", "滚动资金预测", "资金计划", "现金流预测", "未来三个月资金够不够", "回款预测", "cash forecast", "13-week cash flow", "liquidity runway".
- ▌ Report Render · zai-org bundleBuild paginated research deliverables (PDF, or DOCX where the reader edits the file) with correct CJK rendering, density-sized charts, clickable [n] citations, and a mandatory render-and-inspect gate. Use when a report, industry primer, earnings update, diligence report, working paper, memo, or any multi-page analyst deliverable must be produced as a file rather than chat text. Triggers on "出一份PDF", "导出报告", "生成研报", "报告存成文件", "导出Word", "存成docx", "给个可编辑版本", "export as PDF", "as a Word document", "build the report", "把报告存到".
- ▌ Video2code · zai-org bundleReplicating a webpage shown in a screen-recording video — layout, visual style, interactions, and animations. Use whenever the task provides a recording (mp4, webm, mov, etc.) of a website and asks to recreate / reproduce / replicate / clone / build the page shown in it (复刻 / 复现 / 还原). Load this skill AND `web-replicate` together — two Skill calls in one turn — before implementing. If Phase-1 observation shows the page is a WebGL/3D scene (true 3D depth, particle fields, volumetric light/glow, camera flythrough, shader backgrounds), additionally load `video2code-3d`.
- ▌ Deal Comps · zai-org bundleAssemble a precedent-transaction set by hand for a specific deal — identify candidate transactions from stock events and announcement search, extract the announced terms from the announcements themselves, and compute transaction multiples (EV/EBITDA, EV/Revenue, P/E) and 控制权溢价 against a stated pre-announcement reference date. Delivers either a Markdown snapshot or an Excel workbook. Use when a banker or corp-dev team asks what comparable deals paid, what the precedent multiples are, or what premium the market has accepted for control.
- ▌ Fund Screen · zai-org bundleMulti-criteria fund screening across mutual funds, ETFs, and LOFs — by type, performance, risk, size, fees, holdings, manager. Triggers on "筛选基金", "找基金", "fund screen", "哪些基金满足", "近一年收益前10%的股票基金", "重仓XX的基金".
- ▌ Peer Benchmark · zai-orgThe company's own metrics against listed comparables — peer set built with search_stocks and confirmed with get_stock_info, metrics from get_stock_financials, aggregated to a median or weighted average with get_stock_financials, and every 口径 adjustment between management accounts and statutory accounts stated. Triggers on "同业对标", "跟同行比", "对标分析", "行业中位数", "我们的毛利率在行业什么水平", "peer benchmark", "industry median", "competitive benchmarking".
- ▌ Fund Profile · zai-orgDeep-dive profile of a single fund — performance vs benchmark and peers, risk, drawdowns, size and flows, fees, holdings snapshot, manager tenure. Triggers on "基金画像", "分析这只基金", "XX基金怎么样", "fund profile", "<基金代码> 深度分析".
- ▌ Budget Variance · zai-orgActual against budget with attribution rather than description — price / volume / mix / FX on revenue, rate / usage on cost, every material variance classified 时间性 or 永久性, and graded by decision impact. Triggers on "预算执行", "预实差异", "预算对比分析", "为什么没达预算", "量价差分析", "budget variance", "actual vs budget", "variance bridge", "PVM analysis".
- ▌ Dd Report · zai-orgAssemble a full company due-diligence report — entity resolution, registry profile, ownership and related parties, business and industry-chain position, risk records, adverse media, and (for issuers) financial red flags. Triggers on "尽调", "尽职调查", "due diligence", "DD报告", "排查这家公司", "供应商准入", "交易对手调查".
- ▌ Risk Scan · zai-orgFast risk-record screen for one company or a batch — 失信被执行, 终本案件, 限制高消费, 司法涉诉, 行政处罚, 股权质押与冻结, 对外担保, 破产重整与司法拍卖, plus adverse media — with severity ranking. Triggers on "风险排查", "有没有失信", "涉诉情况", "被限高了吗", "有没有破产重整", "黑名单筛查", "risk screen", "批量排查供应商".