prompt-engineering-ui

prompt-engineering-ui is a skill for Claude Code, Codex from HermeticOrmus/LibreUIUX-Claude-Code. It costs 33 tokens per session (3,439 once invoked), scanned A, original, MIT.

A guide to writing prompts that produce more consistent user interfaces from AI systems. It covers describing design intent, specifying components, giving examples, and refining results with feedback.

In plain words
What is it for?
Use it to specify UI components, express design-system rules, create reusable UI prompt templates, generate interface code, and correct inconsistent results.
Why use it?
It helps reduce visual, behavioural, responsive, and accessibility differences between the requested interface and the generated one.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to specify UI components, express design-system rules, create reusable UI prompt templates, generate interface code, and correct inconsistent results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hermeticormus/libreuiux-claude-code/prompt-engineering-ui
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add HermeticOrmus/LibreUIUX-Claude-Code --skill prompt-engineering-ui
Clone the repo
git clone --depth 1 https://github.com/HermeticOrmus/LibreUIUX-Claude-Code

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prompt-engineering-ui

README.md
[![agentmods](https://agentmods.dev/badge/skills/hermeticormus/libreuiux-claude-code/prompt-engineering-ui/github.svg)](https://agentmods.dev/skills/hermeticormus/libreuiux-claude-code/prompt-engineering-ui)
Your own site
<a href="https://agentmods.dev/skills/hermeticormus/libreuiux-claude-code/prompt-engineering-ui"><img src="https://agentmods.dev/badge/skills/hermeticormus/libreuiux-claude-code/prompt-engineering-ui/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prompt-engineering-ui

Your own site · 80×15
<a href="https://agentmods.dev/skills/hermeticormus/libreuiux-claude-code/prompt-engineering-ui"><img src="https://agentmods.dev/badge/skills/hermeticormus/libreuiux-claude-code/prompt-engineering-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,439 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.03439
Opus 5.5 $0.00013 $0.01376
Sonnet 5.5 $0.00007 $0.00688
Haiku 4.5 $0.00003 $0.00344

Measured 26d ago against content hash c0a44858cf5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prompt-engineering-ui scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 26d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/llm-application-dev/skills/prompt-engineering-ui/SKILL.md · 558 lines

How it starts

The opening of the file, as written. The whole thing — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Engineering for UI Generation

Master the art of communicating design intent to LLMs. This skill covers prompt patterns specifically optimized for generating consistent, high-quality user interfaces.


When to Use This Skill

  • Writing prompts that generate consistent UI components
  • Describing design intent precisely to AI systems
  • Building reusable prompt templates for design systems
  • Iterating on UI generation with structured feedback
  • Creating few-shot examples for UI patterns
  • Debugging inconsistent UI generation outputs

The UI Prompting Challenge

UI generation is uniquely challenging because it requires:

  1. Visual precision - Exact spacing, colors, typography
  2. Behavioral specification - Interactions, states, animations
  3. Contextual coherence - Fitting within a design system
  4. Accessibility compliance - WCAG, ARIA, keyboard navigation
  5. Responsive adaptation - Multiple breakpoints, devices
  6. Code quality - Clean, maintainable output

Standard prompting techniques often fail because UI is simultaneously visual, behavioral, and technical.


Core Prompt Patterns

Pattern 1: The Component Contract

Define components as contracts with explicit input/output specifications.

## Component Contract: DataTable

### Purpose
Display tabular data with sorting, filtering, and pagination.

### Props (Inputs)
| Prop | Type | Required | Default | Description |
|------|------|----------|---------|-------------|
| data | T[] | Yes | - | Array of data objects |
| columns | ColumnDef[] | Yes | - | Column configuration |
| pageSize | number | No | 10 | Rows per page |
| sortable | boolean | No | true | Enable column sorting |
| filterable | boolean | No | false | Show filter inputs |

### Visual Specification
- **Container**: bg-white rounded-lg shadow-sm border border-gray-200
- **Header row**: bg-gray-50 text-gray-600 text-sm font-medium
- **Data rows**: hover:bg-gray-50 border-b border-gray-100
- **Typography**: Font-sans, body text 14px, headers 12px uppercase
- **Spacing**: Cell padding 12px horizontal, 8px vertical

### States
1. **Loading**: Skeleton rows with pulse animation
2. **Empty**: Centered message with icon
3. **Error**: Red border, error message below
4. **Selected**: bg-blue-50, left border accent

### Accessibility Requirements
- role="table" on container
- Sortable columns announce sort direction
- Focus visible on all interactive elements
- Keyboard navigation: Tab through headers, Enter to sort

### Output Format
React TypeScript component using Tailwind CSS.
Include JSDoc comments and prop types.

Read the full file on GitHub · 558 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 26d ago First seen · 558 lines · 33 tokens per session scan A c0a44858cf5a

Subscribe to this mod's changes

prompt-engineering-ui is a skill published in the GitHub repository HermeticOrmus/LibreUIUX-Claude-Code (115 stars, last pushed 11d ago), licensed MIT. It adds 33 tokens to every session and 3,439 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-20.