name: goal description: The autonomous goal loop: frame, decompose, then build and verify each slice against real checks, bounded, never auto-ship. disable-model-invocation: true
agents
AGENTS
ANo problem foundPegarose/gstudio
This document defines the production-grade system prompt and a modular design-skill architecture for Open Lovable, the AI platform that turns any URL or idea into a working, premium-quality React/Vite app in seconds. It combines the anti-AI-slop design discipline pioneered by Hallmark, the frontend-quality constraints validated by OpenAI's GPT-5.4 and Nielsen Norman Group research, and Open Lovable's own cloning, brand-extraction, and sandbox pipeline. The goal is consistent output that looks m…
AGENTS got grade A on our automated scan on 2026-10-23.
Details
Source
Public file: https://github.com/Pegarose/gstudio/blob/62356f27e34c6425377ba61712d0ed3986e55eab/AGENTS.md
Last scanned: (Oct 23, 2026, 8:04 p.m. ET)
Category: uncategorized
License: Present
Before you install
- Read any scripts this skill ships.
- Note every URL it fetches.
- Check allowed-tools and hooks.
Embed this grade
Add this badge to your README. It shows the current grade from CheckSkills.
Report this skill if the grade looks wrong, or if something slipped through.
Related
name: seo description: SEO and GEO audit: structured data, canonical, schema, AI-citation optimization.
This directory owns tracked, project-scoped agent instructions. Claude reads the directories directly. Codex uses the ignored .agents/skills projection created by scripts/agents/linkcodexskills.ps1; it is not a second authored copy.
Please refer to the actual skill definition located at ../../.skills/implement/SKILL.md.
Run project onboarding — reads START_HERE.md and executes the protocol there. Auto-detects new project vs. existing codebase, interviews you (new) or reads the code and asks only what it can't answer (existing), fills docs, builds the backlog. Usage: /start