Communitygithub.com

Lovable — AI 全端應用程式生成器

Lovable(原名 GPT Engineer)是一款基於瀏覽器的 AI 應用程式建構工具,能將自然語言描述轉換為可運作的全端網頁應用程式,並內建後端、身份驗證、資料庫及一鍵發佈功能。當使用者想要使用 Lovable 快速打造原型或發佈網頁應用程式、撰寫有效的 Lovable 提示、連接 Supabase 或 GitHub、審查生成的安全規則,或將 Lovable 專案移至自己的編輯器時,可以使用此技能。

Lovable — AI 全端應用程式生成器 是什麼?

Lovable (lovable.dev) 是一款基於瀏覽器的 AI 全端應用程式生成器,可透過聊天提示直接生成並編輯網頁應用程式。專案使用 Tailwind CSS 和 shadcn/ui;2026 年 5 月之後建立的應用程式使用 TanStack Start(伺服器渲染),較舊的則使用 React + Vite。後端方面,您可以選擇 Lovable Cloud(內建資料庫、身份驗證、儲存、即時功能與函式,基於 Supabase 開源堆疊)或自己的 Supabase 專案。程式碼可透過雙向同步與 GitHub 整合,應用程式可發佈至 lovable URL 或自訂網域。無需安裝任何軟體或使用 CLI;AI 代理程式會協助撰寫優質提示、審查輸出結果,並在同步的儲存庫上進行協作。此技能適用於 Claude Code、Coder 等 AI 編碼代理工具,提供逐步指示、安全審查指南、方案選擇建議以及實際範例,確保使用者能有效利用 Lovable 快速迭代、發佈應用程式,並將專案所有權轉移至自己的開發環境。

相容平台~Claude Code~Codex CLI✓Cursor
npx skills add https://github.com/TerminalSkills/skills/tree/HEAD/skills/lovable

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

Lovable — AI 全端應用程式生成器 是做什麼的?

概述

Lovable (lovable.dev) 可透過瀏覽器中的聊天提示生成並編輯網頁應用程式。專案使用 Tailwind CSS 和 shadcn/ui;自 2026 年 5 月起建立的應用程式使用 TanStack Start(伺服器渲染),較舊的則使用 React + Vite。後端方面,您可以選擇 Lovable Cloud(內建資料庫、身份驗證、儲存、即時功能與函式,基於 Supabase 的開源堆疊)或您自己的 Supabase 專案。程式碼可透過兩種方式與 GitHub 同步,應用程式則發佈至 lovable URL 或自訂網域。無需安裝任何軟體,也沒有 CLI;代理程式會協助撰寫優質提示、審查輸出結果,並在已同步的儲存庫上進行協作。

操作說明

1. 在第一次提示前先規劃

回答四個問題:這是什麼、誰會使用它、為什麼使用、以及關鍵動作是什麼。逐區塊描述應用程式,使用真實文案而非佔位符。Lovable 的建議:一整頁的提示會產生雜訊,逐區塊的提示則能提供清晰信號。指定一個設計方向(「簡約」、「高級」、「活潑」)來引導字體排版和間距。

2. 選擇後端

  • 新專案:Lovable Cloud(預設)或 Supabase,在首次啟用後端時選擇。
  • 已連接 Supabase 的現有專案可以繼續運作。目前無法從 Supabase 遷移到 Cloud,也無法一鍵從 Cloud 移至您自己的 Supabase 專案,因此請及早決定。

3. 在模式中工作

Lovable 有「代理模式」(建構和更改內容)和「聊天模式」(討論、規劃,不進行編輯)。規劃模式每則訊息消耗 1 個點數;一般編輯根據複雜度大約消耗 0.5 到 1.7 個點數。在提示中加入「在開始建構之前,請先問我任何你需要的問題」以獲得釐清問題。將持久的規則(如技術堆疊、命名慣例、語氣)放入專案或工作區知識庫,以便在對話之間保持不變。

4. 審查安全性

產生的資料表應啟用資料列層級安全性(Row Level Security)。請閱讀每一條政策,執行內建的安全性掃描,並在發佈前使用兩個不同的使用者帳號進行測試。

5. 同步並擁有程式碼

從專案設定中連接 GitHub。同步是雙向的,一次只針對一個分支(除非切換,否則為預設分支);新分支從活動分支開始。您只能將 Lovable 專案匯出到 GitHub,無法匯入現有儲存庫,且 Lovable 無法編輯超過 10 MB 的檔案。中斷連接會保留兩個副本,但重新連接會建立一個新的儲存庫。

6. 方案

提供免費版、Pro 版、Business 版和 Enterprise 版;定價是基於點數而非座位數。免費版包含每日 5 個建置點數(每月最多 30 個)以及少量的 Cloud 點數。請參考 lovable.dev/pricing 查看最新價格。

範例

範例 1:附有推薦功能的等候名單應用程式

需求:「使用 Lovable 建立一個 SaaS 等候名單:包含計數器的註冊表單、推薦連結、排行榜和一個管理員頁面。」

要貼入的提示:

建立一個名為 "Parcelly" 的等候名單網站,這是一個專為 Etsy 賣家設計的運送標籤工具。
區塊:英雄區塊("10 秒內列印標籤"),包含一個電子郵件表單和即時註冊計數器;
一個顯示前 10 名推薦者的排行榜;一個需要電子郵件登入的 /admin 頁面,
列出所有註冊者並可匯出 CSV。
每位註冊者都會獲得一個唯一的推薦連結 (?ref=code),
推薦人可因此獲得積分。
風格:簡約、深色模式。使用 Lovable Cloud 處理資料和身份驗證。
在開始建構之前,請先問我任何你需要的問題。

結果:Lovable 會詢問有關邀請電子郵件的問題,然後建立頁面、一個 signups 資料表及相關政策,並提供一個預覽 URL。一個可供與生成的政策進行比對的合理資料表與政策集:

create table public.signups (
  id uuid primary key default gen_random_uuid(),
  email text not null unique,
  referral_code text not null unique default encode(gen_random_bytes(6), 'hex'),
  referred_by uuid references public.signups(id),
  created_at timestamptz not null default now()
);
alter table public.signups enable row level security;
create policy "anyone can join" on public.signups for insert to anon with check (true);
-- 讀取所有行必須限制為管理員,例如透過 user_roles 資料表

範例 2:迭代並同步到 GitHub

需求:「新增一個隨時間變化的註冊人數圖表,然後將程式碼放進我的儲存庫,這樣我就可以在 Cursor 中繼續開發。」

聊天提示:「在 /admin 頁面中,使用現有資料新增一個每日註冊人數的折線圖;當沒有註冊資料時顯示空狀態。」然後:專案設定,GitHub,連接,選擇帳戶並建立儲存庫。之後:

git clone [email protected]:parcelly-dev/parcelly-waitlist.git
cd parcelly-waitlist && npm install && npm run dev

推送到已同步分支的內容會出現在 Lovable 中;請將本機編輯保留在該分支上(或在專案設定中切換分支)。

指導原則

  • 將所有核心功能放在第一個提示中,然後每次後續對話只更改一件事,以便版本歷史記錄保持有用;為可運作的版本加上書籤。
  • 不要將 API 金鑰貼入聊天對話;請使用密碼/整合對話方塊。伺服器端金鑰應放在後端函式中,絕不能放在客戶端程式碼中。
  • 絕不要盲目信任生成的 RLS:對於公開表單,insert ... with check (true) 政策是可行的,但 select 政策則不行。
  • 點數用於建置、託管和 AI 功能,且不可退款;對於問題,建議優先使用聊天/規劃模式。
  • 不適合原生行動應用程式、高度自訂的後端或複雜的現有 monorepo:請改為在儲存庫中使用編碼代理程式。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

TerminalSkills/skills

>- Run GitHub Actions locally with act. Use when a user asks to test GitHub Actions workflows locally, debug CI pipelines without pushing, or run workflows offline.

TerminalSkills/skills

>- You are an expert in AG2 (formerly AutoGen), the open-source multi-agent conversation framework. You help developers build systems where multiple AI agents collaborate through structured conversations — with tool use, human-in-the-loop, code execution, group chat orchestration, and nested conversations — for complex tasks like software development, research, and data analysis.

TerminalSkills/skills

>- Generate short-form videos with AI — script writing, text-to-speech narration, stock footage selection, subtitle generation, and video assembly. Use when: creating TikTok/YouTube Shorts/Reels content, automating video production, building content pipelines.

TerminalSkills/skills

>- Animate 3D objects and characters in Blender with Python. Use when the user wants to keyframe properties, create armatures and rigs, set up IK/FK chains, animate shape keys for facial animation, edit F-Curves, use the NLA editor to blend actions, add drivers for expression-based animation, or script any animation workflow in Blender.

TerminalSkills/skills

>- Automate motion capture and tracking workflows in Blender with Python. Use when the user wants to import BVH or FBX mocap data, retarget motion to armatures, track camera or object motion from video, solve camera motion, clean up motion capture data, or script any tracking pipeline in Blender.

TerminalSkills/skills

>- You are an expert in Bolt.new by StackBlitz, the AI-powered full-stack development environment that runs entirely in the browser. You help developers go from idea to deployed app in minutes using natural language prompts — Bolt generates complete applications with frontend, backend, database, and deployment, all running in a WebContainer without local setup.

TerminalSkills/skills

>- Assists with using Bun as an all-in-one JavaScript/TypeScript runtime, package manager, bundler, and test runner. Use when building HTTP servers, managing packages, running tests, or migrating from Node.js. Trigger words: bun, bun serve, bun install, bun test, bun build, javascript runtime, bun runtime.

TerminalSkills/skills

>- Self-host customer support with Chatwoot. Use when a user asks to set up open-source customer support, add live chat without SaaS costs, build a multi-channel inbox, or deploy a free Intercom alternative.

TerminalSkills/skills

>- You are an expert in Chi, the lightweight, idiomatic Go HTTP router built on `net/http`. You help developers build composable HTTP services using Chi's middleware stack, route groups, URL parameters, sub-routers, and context-based request scoping — providing Express-like ergonomics while staying 100% compatible with Go's standard library.

TerminalSkills/skills

When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' or 'copy sweep.' This skill provides a systematic approach to editing marketing copy through multiple focused passes.

TerminalSkills/skills

>- Add live chat and customer support with Crisp. Use when a user asks to add a chat widget, implement live customer support, set up a help desk, create a knowledge base, or add a chatbot to a website.

TerminalSkills/skills

>- Assists with building custom interactive data visualizations using D3.js. Use when creating charts, graphs, maps, force layouts, or hierarchical diagrams that require fine-grained control beyond what charting libraries provide. Trigger words: d3, data visualization, chart, svg, scales, force graph, treemap, choropleth.

TerminalSkills/skills

dbt (data build tool) transforms data in your warehouse using SQL SELECT statements. Learn project setup, models, tests, documentation, incremental materializations, and integration with data warehouses like PostgreSQL, BigQuery, and Snowflake.

TerminalSkills/skills

>- You are an expert in dlt, the open-source Python library for building data pipelines. You help developers load data from any API, file, or database into warehouses and lakes using simple Python decorators — with automatic schema inference, incremental loading, and built-in data contracts. dlt is the "requests library for data pipelines.

TerminalSkills/skills

Data Version Control for ML projects. Track large datasets and models alongside Git, build reproducible ML pipelines, and run experiments with metric comparison. Works with any storage backend including S3, GCS, Azure, and local filesystems.

TerminalSkills/skills

>- You are an expert in E2B, the cloud platform for running AI-generated code in secure sandboxes. You help developers give AI agents the ability to execute code, install packages, read/write files, and run long processes in isolated cloud environments — each sandbox is a lightweight VM that boots in ~150ms with full Linux, filesystem, and networking.

TerminalSkills/skills

>- Transcode, convert, edit, and process audio and video with FFmpeg. Use when a user asks to convert video formats (webm to mp4, mkv to mp4), extract audio from video, compress video files, trim or cut clips, concatenate videos, add subtitles, create thumbnails, apply filters, change resolution or bitrate, re-encode media, create GIFs from video, add watermarks, normalize audio, stream media, or build automated media processing pipelines.

TerminalSkills/skills

>- Create advanced animations with GSAP. Use when building complex timelines, scroll-driven animations, SVG morphing, text animations, or high-performance web animations beyond CSS capabilities.

TerminalSkills/skills

>- Generate deterministic MP4 videos from HTML, CSS, media, and seekable animations using HeyGen's HyperFrames framework. Use when someone asks to "render HTML to video", "make a video with HyperFrames", "create a programmatic video", "turn an animation into MP4", "build a launch/product video from HTML", "render GSAP/Lottie/Three.js to video", or set up an agent-driven video pipeline. Covers init/preview/render/add/lint/inspect commands, data-* timing attributes, animation adapters, and the component catalog.

TerminalSkills/skills

When the user wants to perform load testing, stress testing, or performance testing of APIs and websites using k6. Also use when the user mentions "k6," "load test," "performance test," "stress test," "spike test," "soak test," "thresholds," "virtual users," or "VUs." For browser-based testing, see selenium.

相關技能