Agent Native

enable-lovable-cloud-database

This skill provisions and manages a Lovable Cloud Postgres database, letting the agent run SQL queries to read data, inspect schemas, and apply targeted fixes.

by LovableOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (lovablelabs)

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
License
MIT (permissive)
Pin
c85eecfpinned Oct 9, 2026
Context cost
about 370 tokenswhen the skill loads
GitHub stars
6on lovablelabs/lovable-cursor-plugin
Scripts
None found

What it does

“Provision and inspect a Lovable Cloud Postgres database, and run SQL safely. Use when a project needs data, or when you need to read or fix rows directly.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill provisions and manages a Lovable Cloud Postgres database, letting the agent run SQL queries to read data, inspect schemas, and apply targeted fixes. It handles database setup through provisioning calls and enables safe data inspection and modification with confirmation steps.

When to use it

  • A project needs persistent storage for data or user authentication
  • You must inspect current database schema or row contents directly
  • One-off data fixes or corrections are required in production
  • Reporting requires querying live data from the Postgres database

When not to

  • Routine app features should be built through generated code, not direct SQL modifications
  • Database schema changes the UI depends on should go through the Lovable code agent instead
  • Speculative or experimental writes without clear purpose or confirmation

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add lovablelabs/lovable-cursor-plugin --skill enable-lovable-cloud-database

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install lovablelabs/lovable-cursor-plugin enable-lovable-cloud-database@c85eecf665adcef48dd701d479a9afa2abc86438

Installs the commit we checked (c85eecf).

Copy by hand

Download the folder at c85eecf and put it in .claude/skills/enable-lovable-cloud-database for Claude Code and in .agents/skills/enable-lovable-cloud-database for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at c85eecf

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "enable-lovable-cloud-database" by Lovable.

Source, pinned to commit c85eecf665adcef48dd701d479a9afa2abc86438:
https://github.com/lovablelabs/lovable-cursor-plugin/tree/c85eecf665adcef48dd701d479a9afa2abc86438/plugins/lovable/skills/cloud-database

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/enable-lovable-cloud-database/ for Claude Code and .agents/skills/enable-lovable-cloud-database/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/lovable/enable-lovable-cloud-database

SKILL.md at the pin

---
name: enable-lovable-cloud-database
description: Provision and inspect a Lovable Cloud Postgres database, and run SQL safely. Use when a project needs data, or when you need to read or fix rows directly.
---

# Lovable Cloud database

## When to use

- A project needs to store data, sign users in, or hold files.
- You need to read the current data, check a schema, or apply a one-off fix.

## What this touches

Lovable Cloud provisions a Postgres database with auth, storage, and edge functions. `query_database` runs with full permissions against the real database, so handle it like production.

## Provisioning

1. Call `get_database_status` to see whether a database already exists.
2. If none exists, call `enable_database`. It takes about 30 to 60 seconds. Wait, then re-check `get_database_status` instead of querying right away.

## Reading data

- Use `query_database` for inspection. Select only the columns you need and add a LIMIT while you explore.
- Summarize what you find back to the person, including row counts, so the state is clear.

## Changing data or schema

- For changes the app relies on (new tables, columns the UI reads), describe them to the Lovable agent with `send_message` so the generated code and the database move together. Editing schema underneath the app by hand leads to drift.
- Use `query_database` writes for genuine one-off fixes and reporting.
- Before any write or destructive statement, show the exact SQL and confirm it is wanted. Do not run DROP, DELETE, TRUNCATE, or ALTER speculatively.

## After changes

Report what ran and what it affected. If the schema changed, point the Lovable agent at it so the app keeps up.

From lovablelabs/lovable-cursor-plugin at c85eecf, shown as plain text under its license: MIT (permissive). The license text is in plugins/lovable/LICENSE.

View SKILL.md on GitHub at c85eecf

Files

1 file, 1.7 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at c85eecf
All 4 skills from Lovable

More from Lovable

  • deploy-lovable-project

    This skill enables the agent to publish a Lovable project to a live environment, verify the deployment succeeded, and monitor visitor traffic afterward.

    Claude Code, Codex, Cursor +4 · about 230 tokens · pinned 6 days ago

  • iterate-with-lovable-agent

    This skill lets an agent iterate on existing Lovable projects by sending messages describing changes to the cloud sandbox and reviewing the resulting diffs.

    Agents not labelled yet · about 460 tokens · pinned 6 days ago

  • scaffold-lovable-project

    This skill scaffolds a new Lovable project from a plain-language description, using TypeScript, Tailwind, and shadcn/ui with a cloud sandbox.

    Claude Code, Codex, Cursor +4 · about 390 tokens · pinned 6 days ago

All Data and databases skills

Related in Data and databases

  • prisma-8

    This skill helps agents work with Prisma 8, a contract-first data layer for TypeScript projects.

    by PrismaOfficial publisher

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 3.5K tokens · pinned 6 days ago

  • supabase-postgres-best-practices

    This skill provides a comprehensive guide to Postgres optimization and best practices maintained by Supabase.

    by SupabaseOfficial publisher

    Claude Code, Codex, Cursor +4 · about 440 tokens · pinned 6 days ago

  • dsql

    This skill enables agents to build and manage Aurora DSQL, a serverless PostgreSQL-compatible distributed SQL database.

    by Amazon (AWS)Official publisher

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 6.5K tokens · pinned 6 days ago

  • neki

    This skill guides agents on Neki, PlanetScale's distributed sharded Postgres system.

    by PlanetScaleOfficial publisher

    Claude Code, Codex, Cursor +4 · about 2K tokens · pinned 6 days ago

  • postgres

    This skill provides PostgreSQL best practices, optimization guidance, and operational knowledge across schema design, indexing, query patterns, and…

    by PlanetScaleOfficial publisher

    Claude Code, Codex, Cursor +4 · about 1.7K tokens · pinned 6 days ago

  • chdb-datastore

    This skill enables working with tabular data using a pandas-compatible API backed by ClickHouse for faster execution.

    by ClickHouseOfficial publisher

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 1.2K tokens · pinned 6 days ago

Open roles at Lovable

5 of 15 open roles on the jobs board

See all 15 roles at Lovable on the jobs board

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use