lovable-project

Detects Lovable project architecture and reads provider-neutral agent configuration.

20|5|Updated Jan 1, 2026
One-click install
npx skills add https://github.com/10K-Digital/lovable-agent-skills --skill lovable-project-10k-digital
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lovable-project
Source: https://github.com/10K-Digital/lovable-agent-skills/tree/main/plugins/lovable/skills/lovable-project
Command: npx skills add https://github.com/10K-Digital/lovable-agent-skills --skill lovable-project-10k-digital

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Working on Lovable.dev repositories with coding agents requires knowing the project architecture (Vite SPA vs TanStack Start), where configuration lives, and how to keep secrets out of generated instructions. This Skill provides the shared project context and rules so agents like Codex and Claude Code operate on a Lovable repo correctly from the first step. ## Core Features & Use Cases - Architecture Detection: Distinguishes Vite SPA (CSR) from TanStack Start (SSR) projects using app.config.ts, vite.config.ts, and the detect-architecture.py helper script. - Provider-Neutral Configuration: Reads .lovable-agent/config.json and context.md as the source of truth while preserving CLAUDE.md and .claude/ as compatible adapters. - Secret-Safe Context Handling: Records secret names and status only, never values, preview tokens, or API keys in config, logs, or generated reports. - Use Case: An agent opens a Lovable repository, reads .lovable-agent/config.json, detects a TanStack Start architecture, and generates correct instruction shims without leaking credentials. ## Quick Start Use the lovable-project skill to inspect this Lovable repository, detect whether it is a Vite SPA or TanStack Start app, and summarize its agent configuration.

Frequently Asked Questions about lovable-project

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I detect whether a Lovable project uses Vite SPA or TanStack Start?

Check for app.config.ts, which indicates TanStack Start with SSR and file-based routes, or vite.config.ts, which indicates a Vite SPA with client-side rendering. You can also run the detect-architecture.py helper script, which reports the result as JSON without reading secret values.

What is the .lovable-agent directory used for?

The .lovable-agent directory is the shared source of truth for Lovable projects, containing config.json for project and deploy settings, context.md for provider-neutral project facts, and test plans. It replaces provider-specific state while CLAUDE.md and .claude/ remain supported adapters.

Does this skill work with both Codex and Claude Code?

Yes, the skill is provider-neutral and supports Codex, Claude Code, and other Agent Skills runtimes. AGENTS.md serves as the canonical instruction file, while CLAUDE.md and Claude commands remain compatible aliases.

How are secrets handled when generating agent instructions?

Only secret names and status are recorded, never values, preview tokens, OAuth credentials, or API keys. This rule applies to config files, instructions, logs, and generated reports to prevent credential leakage.

What happens if both app.config.ts and vite.config.ts are present?

The skill reports the ambiguity rather than guessing, then inspects the package scripts to determine the actual architecture. This avoids incorrect assumptions about routing and deployment behavior.