How do I install the Lovable Project skill?

Run npx skillmds@latest add 10k-digital/lovable-project-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Lovable Project safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Lovable Project?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Lovable Project free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Lovable Project?

10k-digital (@10k-digital) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Lovable Project by 10k-digital — Agent Skill

Name: Lovable Project
Author: 10k-digital

Lovable Project

Provider-neutral project context for Lovable.dev repositories. Use when initializing, inspecting, or modifying a Lovable project, detecting Vite SPA versus TanStack Start, reading `.lovable-agent` configuration, or generating agent instruction shims for Codex, Claude Code, and other agents.

10k-digital Updated Sep 22, 2026

File contents

Lovable Project Context

Use this skill as the first step for work in a Lovable repository.

For initialization or reinitialization, call the init skill at ../init/SKILL.md. Before Lovable submissions, read ../lovable/references/prompt-authorization.md.

Read .lovable-agent/config.json and .lovable-agent/context.md when present. Treat them as the canonical source of project settings; read AGENTS.md as the neutral instruction shim.
Preserve provider-specific files as adapters: CLAUDE.md, .claude/, and Claude commands remain supported, but new state belongs in .lovable-agent/.
Detect architecture before making assumptions:
- Run python3 plugins/lovable/scripts/detect-architecture.py . when the helper is available; it reports JSON without reading secret values.
- app.config.ts → TanStack Start (SSR, file-based routes, *.server.ts auto-deploys).
- vite.config.ts → Vite SPA (CSR, src/, backend changes need Lovable deployment prompts).
- If both or neither are present, report the ambiguity and inspect the package scripts.
Keep context secret-safe. Record secret names and status only; never record values, preview tokens, OAuth credentials, or API keys in config, instructions, logs, or generated reports.
For the detailed neutral schema and migration rules, read ../lovable/references/agent-config.md.

The legacy plugins/lovable/skills/lovable/SKILL.md remains the Claude-compatible deep reference.

Frequently asked questions