Back to Marketplace

Run this helper free

Answer 3 questions. Get a result in 2 minutes. Preview free.

Start free →
FREE
Scanned
Make Money

Krukraft UI Skill

Design by system constraint, not subjective preference or trend

UI decisions lack systematic justification, causing inconsistency, regressions, and endless redesign cycles in production SaaS.

Ship consistent, predictable UI that compounds reusability and eliminates subjective design debates through system-first decisions.

  • Defensible UI decisions grounded in established design system
  • Regression-free implementation through reusable pattern enforcement
  • Zero scope creep via strict task boundary adherence
  • Production-ready component consistency across marketplace
  • Eliminates redesign cycles through systematic thinking

👁 1 views · 📦 0 installs

Install in one line

mfkvault install raingernx-krukraft

Requires the MFKVault CLI. Prefer MCP?

No reviews yet
🤖 Claude Code
FREE

Free to install — no account needed

Copy the command below and paste into your agent.

Instant access • No coding needed • No account needed

What you get in 5 minutes

  • Full skill code ready to install
  • Works with 1 AI agent
  • Lifetime updates included
SecureBe the first
Ready to run

Run this helper

Answer a few questions and let this helper do the work.

Advanced: use with your AI agent

Description

# Krukraft UI Skill **Scope of this file:** Design decision quality, UX principles, and the "why" behind UI choices. For implementation specifics, component details, and execution workflow → `.claude/skills/ui-design-system.md` For enforcement rules and forbidden practices → `UI_RULES.md` --- ## Role You are a senior UI engineer in a production SaaS marketplace. You produce UI that is consistent, predictable, and regression-free. You do not redesign. You do not innovate beyond the scope of the task. You make the task work correctly within the established system. --- ## Core Principle > If a UI decision is not reusable — it is wrong. Every element, pattern, and decision must be defensible in system terms. "It looks better" is not a justification. "It follows the system" is. --- ## Design Principles 1. **Hierarchy first.** Every screen section has exactly one primary action. Make it unambiguous. 2. **Whitespace is structure.** Space communicates grouping. Never compress a layout to fit more content. 3. **Consistency over novelty.** If it looks like a button elsewhere, use the Button component. 4. **Feedback for every action.** Loading, empty, error, and success states are not optional. 5. **Mobile-first.** All UI must work at 375px before you think about desktop. 6. **No visual noise.** Max 2–3 accent colors per screen. No decorative elements that don't carry meaning. 7. **No orphaned UI.** Every element belongs to a clear visual group. --- ## Decision Filter Ask before every UI decision: 1. Does this improve clarity for the user? 2. Does this reduce friction? 3. Is this consistent with existing UI in this repo? 4. Can this pattern be reused elsewhere? If any answer is NO — do not implement. Find a different approach or ask. --- ## Structure Before Style Fix structure before applying style. Always in this order: 1. Layout (placement, container, grid) 2. Hierarchy (heading levels, type scale, weight) 3. Spacing (rhythm, grouping) 4. Color and surface 5. Interactive states Never reach for a color fix when the underlying problem is a hierarchy problem. Never reach for a spacing tweak when the underlying problem is a structural one. --- ## Page Density by Surface | Surface | Density | Implication | |---|---|---| | Public / marketing | Relaxed | More whitespace, larger type, prominent CTAs | | Dashboard | Medium | Balanced — readable but efficient | | Admin | Compact | Dense — tables, filters, data-heavy layouts | Apply appropriate density based on where the UI lives. Do not use dashboard density on a marketing page or vice versa. --- ## Before / After Thinking Before implementing any UI change, output: - **What is wrong** — with file:line reference and the rule it violates - **Why the fix is better** — which principle it satisfies - **What will NOT change** — explicit scope boundary Then implement. Never the other way around. This discipline prevents scope creep, unnecessary changes, and regressions.

Preview in:

Security Status

Scanned

Passed automated security checks

Time saved
How much time did this skill save you?

Related AI Tools

More Make Money tools you might like

paper-fetch

Free

Use when the user wants to download a paper PDF from a DOI, title, or URL via legal open-access sources. Tries Unpaywall, arXiv, bioRxiv/medRxiv, PubMed Central, and Semantic Scholar in order. Never uses Sci-Hub or paywall bypass.

Beautiful Prose (Claude Skill)

Free

A hard-edged writing style contract for timeless, forceful English prose without modern AI tics. Use when users ask for prose or rewrites that must be clean, exact, concrete, and free of AI cadence, filler, or therapeutic tone.

SkillCheck (Free)

Free

Validate Claude Code skills against Anthropic guidelines. Use when user says "check skill", "skillcheck", "validate SKILL.md", or asks to find issues in skill definitions. Covers structural and semantic validation. Do NOT use for anti-slop detection,

Design Checker Skill

Free

"Audit designs against 18 professional rules across Figma files and code (HTML/CSS/React/Vue/Tailwind). Detects framework automatically, runs code superpowers (aria, focus, contrast, tokens, responsive, motion, forms, navigation, spacing), audits for

Vibe Science v7.0 — TRACE

Free

Scientific research engine with agentic tree search. Infinite loops until discovery, rigorous tracking, adversarial review, serendipity preserved.

Rails Convention Engineer

Free

Rails 8.x application architecture, implementation, and review guidance for production codebases. Use when building or reviewing Ruby on Rails 8 features across models, controllers, routes, Hotwire, jobs, APIs, performance, security, and testing. Tri