UX Review Nt — Design skill for Claude Code
Cold-first-timer UX review — wipe state, walk the app as a new user, rank where onboarding / nav / time-to-first-value fail; plus a Lighthouse pass.
How to install UX Review Nt
Installs to ~/.claude/skills/naklitechie-ntkit-ux-review-nt/SKILL.md
mkdir -p ~/.claude/skills/naklitechie-ntkit-ux-review-nt && curl -fsSL https://raw.githubusercontent.com/NakliTechie/ntkit/HEAD/commands/ux-review-nt.md -o ~/.claude/skills/naklitechie-ntkit-ux-review-nt/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What UX Review Nt does
description: "Cold-first-timer UX review — wipe state, walk the app as a new user, rank where onboarding / nav / time-to-first-value fail; plus a Lighthouse pass. Read-only report." argument-hint: "[area to focus, e.g. first-run | settings | nav]" allowed-tools: ["Bash", "Glob", "Grep", "Read", "Write", "Task"] entry: "app boots; state wipeable to cold-start" exit: "first-run + IA report written (read-only run)" writes: "plan/ux-review-.md"
Review the app **as a cold first-time us
Alternatives in Design
- Value Proposition — Design value propositions using 6-part JTBD template 7.8k ★
- Grade — Generate a shareable HTML "Design Report Card" — letter grade, 8 dimensions, evidence (palette, type, rhythm) 3.6k ★
- Deepen — Spare-budget design pass 1.1k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Pricing Strategy
Walk value-based pricing logic and tier design, then produce a specific tier structure with real numbers. Writ
Cs Work
Cold-start work session -- read state, execute, write state, exit. Stateless by design.
Craft Skill
Frontend design skill for Claude Code & OpenCode: interfaces that look designed, not generated. Anti-cliché ca
Claude Skill Debug Walk
Claude Code skill: walk one code behavior like a debugger, with a Markdown report and a Step Functions-style e
Screenshot Iterate
Visual loop — implement against a mock, screenshot the running app with a browser tool, compare, and iterate u
Full System Diagnostic Agent
Chains token, naming, component, drift and docs-coverage audits (plus theme and Figma variable audits where th
Related Agents
Langertha ADR Auditor
Audit Langertha for architecturally-significant decisions that lack an ADR, and (in write mode) record them in
Re Analyst
A game reverse-engineering analyst for software the user owns and the Pointer Lab tutorial. Use it to run a mu
Ferrox A11y Auditor
Post-change WCAG 2.1 AA audit of implemented frontend surfaces. Static rules with file:line evidence plus an o