Skill of Skills
📄 skillActivePromisingmedium

onlook-dev/onlook

by onlook-dev

The Cursor for Designers • An Open-Source AI-First Design tool • Visually build, style, and edit your React App with AI

Supported Platforms

🤖 Claude Code🧠 Codex

Stars

25.9k

Skill Type

🏗️ Code Scaffolding & Templates

Quality Score

87/200

License

Apache-2.0

Forks

2.0k

Last Updated

Jun 11, 2026

Discovered

Apr 19, 2026

Validation

Passed

github.com/onlook-dev/onlook

Quality Breakdown

87/ 200

Content Signals

○Gotchas/Edge Cases+40
✓Progressive Disclosure+30
○Trigger Description+20
○Verification/Safety+20
○Code Examples+15
○Composability+15

Repo Health

✓Recent Activity+15
✓Scripts/Automation+10
✓Real Usage (Issues)+10
✓Single Responsibility+10
✓Config/Persistence+10
✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • CLAUDE.md and AGENTS.md files present - indicates AI agent configuration/memory files that could contain persistent instructions
  • Docker and containerization setup (.dockerignore, Dockerfile) - allows execution of arbitrary code in isolated environment
  • GitHub workflows (.github/workflows) - CI/CD pipelines with potential external code execution
  • Supabase backend with migrations - database schema changes and potential data access patterns
  • Monorepo structure with multiple apps (admin, backend, web) - complex execution surface
  • SECURITY.md file present - suggests security-sensitive operations or features