UI Pass — AI skill for Claude Code
Phase 7 - build or fix the UI so it doesn't look AI-made, loop until ui-critic passes.
How to install UI Pass
Installs to ~/.claude/skills/ctesorierog-claude-setup-ui-pass/SKILL.md
mkdir -p ~/.claude/skills/ctesorierog-claude-setup-ui-pass && curl -fsSL https://raw.githubusercontent.com/ctesorierog/claude-setup/HEAD/commands/ui-pass.md -o ~/.claude/skills/ctesorierog-claude-setup-ui-pass/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What UI Pass does
description: Phase 7 - build or fix the UI so it doesn't look AI-made, loop until ui-critic passes argument-hint: [page or component, and the design reference if any]
Use the playbook skill. We are in Phase 7 (UI). Target: $ARGUMENTS
- Find one design reference: a DESIGN.md in the project, or ask Carlos for a site he likes. Only one; two references pull in different directions.
- Use the
impeccableskill to build or critique the target (product mode for apps and dashboards, brand mo
Alternatives in AI
- Omniget — Udemy & Hotmart course downloader, YouTube downloader (yt-dlp GUI, 1,800+ sites) + desktop app for AI agents 13.9k ★
- Ralph For Claude Code — by Frank Bria - An autonomous AI development framework that enables Claude Code to work iteratively on project 8k ★
- LaTeX Document Skill — Universal LaTeX document skill for Claude Code: 27 templates, 27 scripts, 26 reference guides 725 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Skillgate
Deterministic finish-line gates for AI coding agents. A model-independent evaluator that blocks commit/publish
Portfolio Skill
An agent skill that turns a resume, a few repos and some links into a personal portfolio site that doesn't loo
Motionmaxxing
Looksmaxxing for motion graphics. An agent skill that turns AI slop videos into films that look made by a moti
Iterate Skill
Turn any AI coding assistant into a self-checking senior engineer: multi-round, multi-dimension code review →
Headsign
A tiny phase gate for coding agents: your shell checks decide pass/fail (never the LLM), your workflow routes
Sloppy
Static analysis for the debt AI agents leave in PHP: 25 rules, Claude Code hooks, git-diff review, a Rector an
Related Agents
Plan Coordinator
Iteratively polish a plan by launching plan-polisher in a loop until critique passes or max iterations reached
Content Director
Orchestrates the content-shorts pipeline 리서치팀 → 제작팀 ⇄ 법률팀 → 출시팀 for a single short (info/news/idol). Delegates
Sweep Controller
Controls autonomous fix-and-revalidate loops until all journeys pass or max attempts exhausted