全部能力

Build production-ready RESTful APIs with Express.js including routing, middleware, validation, and error handling for scalable backend services

Use when designing visual motion systems, creating animation specifications, or when a designer needs guidance on crafting beautiful, meaningful movement.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work…

Linear issue management. Use when the user mentions LOBE-xxx issue IDs (e.g. LOBE-4540), says 'linear' / 'linear issue' / 'link linear', or when creating PRs…

在设计资源生命周期时使用。关键词：RAII、Drop、资源生命周期、连接池、延迟初始化、连接池设计、资源…

Adding or editing keyboard shortcuts in LobeHub. Use when registering a new hotkey, changing a key combo, scoping a shortcut to chat vs global, or wiring a…

When the user wants to plan, implement, or optimize student and education discount programs. Also use when the user mentions "student discount," "education…

Recognize breakthrough moments, blocking resolutions, and design decisions worth preserving. Detect high-value insights that save future time. Suggest…

ai-wrapper-product — 一个可安装的 AI 智能体技能，由 sickn33/antigravity-awesome-skills 发布。

生成专业 SVG 标志与高端展示图。适用于以下场景：(1) 为产品/品牌创建标志或图标，(2) 基于产品信息生成标志设计概念，(3) 创建包含多种背景风格的专业标志展示演示，(4) 以多种格式导出标志（SVG、PNG），或 (5) 以不同视觉风格迭代标志设计。支持几何图案、点阵设计、线性系统和混合构图。使用 Nano Banana（Gemini 图像生成）生成展示图，提供 12 种专业背景风格。

Strict frontend design guardrails for building modern, minimal-visual-noise, airy, non-generic app UIs. Use whenever creating or changing frontend UI, React components, shadcn/ui themes, Tailwind styles, app layouts, or first-version product screens. This skill complements vertical/domain skills like CPQ, CRM, and similar app builders: follow the selected domain skill's workflow and layout requirements, then enforce this skill's shared visual rules for brand-aware theming, generous spacing, typography, contrast, roundedness, shadows, surface hierarchy, cardless defaults, no-sidebar defaults, and anti-pattern avoidance.

EXPERIMENTAL: Three-layer parallel meta-cognition analysis. Triggers on: /meta-parallel, 三层分析, parallel analysis, 并行元认知

Guide building a minimum viable product the minimalist entrepreneur way — manual first, then processized, then productized. Use when someone is ready to build…

Creates PRDs using persistent file-based planning. Use when user explicitly says "PRD", "product requirements document", or "产品需求文档". Combines PRD methodology…

基于文档内容自动生成配图。AI 智能分析文档结构，归纳核心要点， 为每个主题生成符合特定风格的配图。支持封面图生成和自定义图片比例。 使用场景：当用户需要为文档、文章、笔记生成配图时。 关键词：配图、插图、illustration、generate images、document images

Create professional CVs and resumes with perfect typography using RenderCV (v2.8). Users write content in YAML, and RenderCV produces publication-quality PDFs via Typst typesetting. Full control over every visual detail: colors, fonts, margins, spacing, section title styles, entry layouts, and more. 6 built-in themes with unlimited customization. Any language supported (22 built-in, or define your own). Outputs PDF, PNG, HTML, and Markdown. Use when the user wants to create, edit, customize, or render a CV or resume.

将视频转换为多个具有不同质量与大小权衡的 GIF 变体。生成对比图集，以便用户直观地挑选最佳结果。

analytics-events — 一个可安装的 AI 智能体技能，由 metabase/metabase 发布。

分析和改进浏览器游戏视觉表现、氛围及玩家体验的游戏 UI/UX 设计师。当游戏需要视觉……时使用

Analyzes Figma designs and generates implementation-ready PRDs with detailed visual specifications. Use when user provides Figma link or uploads design…