Communitygithub.com

TerminalSkills/skills

>- Lovable (formerly GPT Engineer) is a browser-based AI app builder that turns a natural-language description into a working full-stack web app with a built-in backend, authentication, database and one-click publishing. Use when the user wants to prototype or ship a web app with Lovable, write effective Lovable prompts, connect Supabase or GitHub, review generated security rules, or move a Lovable project into their own editor.

What is skills?

skills is a Cursor agent skill that >- Lovable (formerly GPT Engineer) is a browser-based AI app builder that turns a natural-language description into a working full-stack web app with a built-in backend, authentication, database and one-click publishing. Use when the user wants to prototype or ship a web app with Lovable, write effective Lovable prompts, connect Supabase or GitHub, review generated security rules, or move a Lovable project into their own editor.

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

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Lovable — AI Full-Stack App Generator

Overview

Lovable (lovable.dev) generates and edits web apps from chat prompts in the browser. Projects use Tailwind CSS and shadcn/ui; apps created since May 2026 use TanStack Start (server-rendered), older ones are React + Vite. For the backend you choose either Lovable Cloud (built-in database, auth, storage, realtime and functions, built on Supabase's open-source stack) or your own Supabase project. Code can be synced two ways with GitHub, and apps are published to a lovable URL or a custom domain. There is nothing to install and no CLI; an agent helps by writing good prompts, reviewing the output and working on the synced repository.

Instructions

1. Plan before the first prompt

Answer four questions: what is it, who uses it, why, and what is the key action. Describe the app section by section with real copy, not placeholders. Lovable's guidance: a full-page prompt gives noise, a section-based prompt gives signal. Name a design direction ("minimal", "premium", "playful") to steer typography and spacing.

2. Choose the backend

  • New projects: Lovable Cloud (default) or Supabase, chosen when the backend is first enabled.
  • Existing Supabase-connected projects keep working. There is no migration from Supabase to Cloud, and no one-click move from Cloud to your own Supabase project, so decide early.

3. Work in modes

Lovable has an Agent mode (builds and changes things) and a Chat mode (discuss, plan, no edits). Plan Mode costs 1 credit per message; normal edits cost roughly 0.5-1.7 credits depending on complexity. Add "Ask me any questions you need before building" to get clarifying questions. Put durable rules (stack, naming, tone) in project or workspace knowledge so they persist between chats.

4. Review security

Generated tables should have Row Level Security. Read each policy, run the built-in security scan, and test with two different users before publishing.

5. Sync and own the code

Connect GitHub from project settings. Sync is two-way for one branch at a time (the default branch unless switched); new branches start from the active one. You can only export Lovable projects to GitHub, not import an existing repo, and files over 10 MB cannot be edited by Lovable. Disconnecting keeps both copies, but reconnecting creates a new repository.

6. Plans

Free, Pro, Business and Enterprise; pricing is by credits, not seats. Free includes 5 daily build credits (up to 30 a month) plus small Cloud credits. Check lovable.dev/pricing for current prices.

Examples

Example 1: Waitlist app with referrals

Request: "Use Lovable to build a SaaS waitlist: signup form with a counter, referral links, a leaderboard, and an admin page."

Prompt to paste:

Build a waitlist site for "Parcelly", a shipping-label tool for Etsy sellers.
Sections: hero ("Print labels in 10 seconds") with an email form and a live
signup counter; a leaderboard of the top 10 referrers; /admin page behind
email login that lists signups and exports CSV.
Every signup gets a unique referral link (?ref=code) that credits the referrer.
Style: minimal, dark mode. Use Lovable Cloud for data and auth.
Ask me any questions you need before building.

Result: Lovable asks about invite emails, then creates pages, a signups table and policies, and a preview URL. A reasonable table and policy set to check against the generated one:

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);
-- reading all rows must be limited to admins, e.g. via a user_roles table

Example 2: Iterating and syncing to GitHub

Request: "Add a signups-over-time chart, then get the code into my repo so I can keep working in Cursor."

Chat prompt: "Add a line chart of signups per day to /admin using the existing data; show an empty state when there are no signups." Then: Project settings, GitHub, Connect, pick the account and create the repository. Afterwards:

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

Pushes to the synced branch appear in Lovable; keep local edits on that branch (or switch the branch in project settings).

Guidelines

  • Put every core feature in the first prompt, then change one thing per follow-up so version history stays useful; bookmark working versions.
  • Do not paste API keys into chat; use the secrets/integration dialogs. Server-side keys belong in backend functions, never in client code.
  • Never trust generated RLS blindly: an insert ... with check (true) policy is fine for a public form, a select one is not.
  • Credits are consumed by building, hosting and AI features, and are not refundable; prefer Chat/Plan mode for questions.
  • Not a good fit for native mobile apps, heavy custom backends or complex existing monorepos: use a coding agent in the repository instead.

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.

Related Skills