with one click
critique
The feature or area to critique (optional)
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
The feature or area to critique (optional)
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | critique |
| description | The feature or area to critique (optional) |
Conduct a holistic design critique, evaluating whether the interface actually works—not just technically, but as a designed experience. Think like a design director giving feedback.
First: Use the frontend-design skill for design principles and anti-patterns.
Evaluate the interface across these dimensions:
This is the most important check. Does this look like every other AI-generated interface from 2024-2025?
Review the design against ALL the DON'T guidelines in the frontend-design skill—they are the fingerprints of AI-generated work. Check for the AI color palette, gradient text, dark mode with glowing accents, glassmorphism, hero metric layouts, identical card grids, generic fonts, and all other tells.
The test: If you showed this to someone and said "AI made this," would they believe you immediately? If yes, that's the problem.
Structure your feedback as a design director would:
Start here. Pass/fail: Does this look AI-generated? List specific tells from the skill's Anti-Patterns section. Be brutally honest.
A brief gut reaction—what works, what doesn't, and the single biggest opportunity.
Highlight 2-3 things done well. Be specific about why they work.
The 3-5 most impactful design problems, ordered by importance:
For each issue:
Quick notes on smaller issues worth addressing.
Provocative questions that might unlock better solutions:
Remember:
Review unsupported Claude skill fields manually: args, required, user-invokable.
Download and inspect a single turn of a real Lorcana game from production using the `tcg-replay` CLI. Use whenever you need to understand what actually happened in a player-reported bug — gives you the cards involved (with file paths), the pre-turn match state, and a step-by-step trace of moves, engine logs, and JSON patches for that turn.
What to adapt for (mobile, tablet, desktop, print, email, etc.)
The feature or component to animate (optional)
The feature or area to audit (optional)
Configure Better Auth server and client, set up database adapters, manage sessions, add plugins, and handle environment variables. Use when users mention Better Auth, betterauth, auth.ts, or need to set up TypeScript authentication with email/password, OAuth, or plugin configuration.
Configure rate limiting, manage auth secrets, set up CSRF protection, define trusted origins, secure sessions and cookies, encrypt OAuth tokens, track IP addresses, and implement audit logging for Better Auth. Use when users need to secure their auth setup, prevent brute force attacks, or harden a Better Auth deployment.