Prompt Engineer Toolkit
alirezarezvani/claude-skills
Turns marketing prompts into tested, versioned production assets: A/B prompt evaluation against structured test cases, immutable prompt version history with diffs, ready-to-use marketing prompt…
Prompt patterns for consistent UI generation: stating design intent precisely, component specification formats, few-shot examples, and structured refinement loops.
$ npx skills add HermeticOrmus/LibreUIUX-Claude-Code --skill prompt-engineering-ui -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install HermeticOrmus/LibreUIUX-Claude-Code prompt-engineering-ui --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/HermeticOrmus/LibreUIUX-Claude-Code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/llm-application-dev/skills/prompt-engineering-ui .claude/skills/prompt-engineering-ui && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "prompt-engineering-ui" agent skill from https://github.com/HermeticOrmus/LibreUIUX-Claude-Code/tree/main/plugins/llm-application-dev/skills/prompt-engineering-ui into .claude/skills/prompt-engineering-ui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering-ui", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/HermeticOrmus/LibreUIUX-Claude-Code/tree/main/plugins/llm-application-dev/skills/prompt-engineering-uiType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add HermeticOrmus/LibreUIUX-Claude-Code --skill prompt-engineering-ui -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install HermeticOrmus/LibreUIUX-Claude-Code prompt-engineering-ui --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HermeticOrmus/LibreUIUX-Claude-Code.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/llm-application-dev/skills/prompt-engineering-ui .agents/skills/prompt-engineering-ui && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "prompt-engineering-ui" agent skill from https://github.com/HermeticOrmus/LibreUIUX-Claude-Code/tree/main/plugins/llm-application-dev/skills/prompt-engineering-ui into .agents/skills/prompt-engineering-ui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering-ui", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add HermeticOrmus/LibreUIUX-Claude-Code --skill prompt-engineering-ui -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install HermeticOrmus/LibreUIUX-Claude-Code prompt-engineering-ui --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HermeticOrmus/LibreUIUX-Claude-Code.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/llm-application-dev/skills/prompt-engineering-ui .cursor/skills/prompt-engineering-ui && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "prompt-engineering-ui" agent skill from https://github.com/HermeticOrmus/LibreUIUX-Claude-Code/tree/main/plugins/llm-application-dev/skills/prompt-engineering-ui into .cursor/skills/prompt-engineering-ui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering-ui", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/HermeticOrmus/LibreUIUX-Claude-Code.git --path plugins/llm-application-dev/skills/prompt-engineering-ui--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add HermeticOrmus/LibreUIUX-Claude-Code --skill prompt-engineering-ui -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install HermeticOrmus/LibreUIUX-Claude-Code prompt-engineering-ui --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HermeticOrmus/LibreUIUX-Claude-Code.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/llm-application-dev/skills/prompt-engineering-ui .gemini/skills/prompt-engineering-ui && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "prompt-engineering-ui" agent skill from https://github.com/HermeticOrmus/LibreUIUX-Claude-Code/tree/main/plugins/llm-application-dev/skills/prompt-engineering-ui into .gemini/skills/prompt-engineering-ui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering-ui", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install HermeticOrmus/LibreUIUX-Claude-Code prompt-engineering-uiInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add HermeticOrmus/LibreUIUX-Claude-Code --skill prompt-engineering-ui -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/HermeticOrmus/LibreUIUX-Claude-Code.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/llm-application-dev/skills/prompt-engineering-ui .github/skills/prompt-engineering-ui && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "prompt-engineering-ui" agent skill from https://github.com/HermeticOrmus/LibreUIUX-Claude-Code/tree/main/plugins/llm-application-dev/skills/prompt-engineering-ui into .github/skills/prompt-engineering-ui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering-ui", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add HermeticOrmus/LibreUIUX-Claude-Code --skill prompt-engineering-ui -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install HermeticOrmus/LibreUIUX-Claude-Code prompt-engineering-ui --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HermeticOrmus/LibreUIUX-Claude-Code.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/llm-application-dev/skills/prompt-engineering-ui .opencode/skills/prompt-engineering-ui && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "prompt-engineering-ui" agent skill from https://github.com/HermeticOrmus/LibreUIUX-Claude-Code/tree/main/plugins/llm-application-dev/skills/prompt-engineering-ui into .opencode/skills/prompt-engineering-ui/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "prompt-engineering-ui", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
prompt-engineering-uiPrompt patterns for consistent UI generation: stating design intent precisely, component specification formats, few-shot examples, and structured refinement loops.
Prompt Engineering UI is an agent skill from HermeticOrmus/LibreUIUX-Claude-Code. Prompt patterns for consistent UI generation: stating design intent precisely, component specification formats, few-shot examples, and structured refinement loops. Use when UI output from an LLM is inconsistent or generic, or when building reusable prompt templates for a design system.
Its SKILL.md is about 3.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Prompt engineering. The repository describes itself as: UI/UX system for Claude Code: 71 plugins, 93 agents, 74 skills. Design mastery, archetypal design, accessibility, and frontend workflows in one validated plugin marketplace. The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 41a968c. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and typescript).
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Prompt Engineering UI loads about 3.6k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 598 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from HermeticOrmus/LibreUIUX-Claude-Code at commit 41a968c, republished under its MIT licence (© HermeticOrmus). 598 words, ~3,582 tokens.
.claude/skills/prompt-engineering-ui/SKILL.md (or your agent's skills folder).Master the art of communicating design intent to LLMs. This skill covers prompt patterns specifically optimized for generating consistent, high-quality user interfaces.
UI generation is uniquely challenging because it requires:
Standard prompting techniques often fail because UI is simultaneously visual, behavioral, and technical.
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.Why This Works:
Embed design tokens directly in prompts for consistency.
Generate a Card component following these design tokens:
## Tokens
```json
{
"spacing": {
"xs": "4px",
"sm": "8px",
"md": "16px",
"lg": "24px",
"xl": "32px"
},
"colors": {
"surface": {
"primary": "#FFFFFF",
"secondary": "#F9FAFB",
"elevated": "#FFFFFF"
},
"border": {
"subtle": "#E5E7EB",
"default": "#D1D5DB"
},
"shadow": {
"sm": "0 1px 2px rgba(0,0,0,0.05)",
"md": "0 4px 6px rgba(0,0,0,0.1)"
}
},
"radius": {
"sm": "4px",
"md": "8px",
"lg": "12px"
}
}surface.elevated backgroundborder.subtlespacing.lgradius.lgshadow.mdMap these tokens to Tailwind classes where possible.
**Token Mapping Strategy**:
```typescript
// Prompt can include this mapping guide
const tokenToTailwind = {
"spacing.xs": "p-1",
"spacing.sm": "p-2",
"spacing.md": "p-4",
"spacing.lg": "p-6",
"spacing.xl": "p-8",
"colors.surface.primary": "bg-white",
"colors.surface.secondary": "bg-gray-50",
"colors.border.subtle": "border-gray-200",
"radius.lg": "rounded-xl",
"shadow.md": "shadow-md",
};Chain visual descriptions from abstract to concrete.
## Component: Hero Section
### Mood (Abstract)
Confident, minimal, focused. The user should feel capable and unintimidated.
### Aesthetic (Semi-Abstract)
- Clean sans-serif typography
- Generous whitespace (40% of viewport)
- Single accent color for CTAs
- Photography: abstract, not literal
### Visual Details (Concrete)
- **Layout**: Centered, max-width 1200px, py-24
- **Headline**: text-5xl font-bold tracking-tight text-gray-900
- **Subheadline**: text-xl text-gray-600 max-w-2xl mx-auto mt-6
- **CTA Group**: mt-10 flex gap-4 justify-center
- **Primary CTA**: bg-indigo-600 hover:bg-indigo-700 text-white px-8 py-4 rounded-lg
- **Secondary CTA**: border border-gray-300 text-gray-700 px-8 py-4 rounded-lg
### Content
- Headline: "Build interfaces that inspire"
- Subheadline: "The design system that empowers creators to ship beautiful products faster."
- Primary CTA: "Get Started"
- Secondary CTA: "Learn More"The Chain:
Mood → Aesthetic → Visual Details → Content
↓ ↓ ↓ ↓
Emotion Style CSS Values TextThis pattern works because it builds from intention to implementation.
Define component states as a state machine.
## Button Component States
### State Machineidle → hover → pressed → idle ↓ ↓ ↓ focus focus focus ↓ ↓ ↓ disabled (terminal) loading (blocks all transitions)
### State Definitions
| State | Visual Treatment | Tailwind Classes |
|-------|------------------|------------------|
| idle | Default appearance | bg-blue-600 text-white |
| hover | Slightly darker | hover:bg-blue-700 |
| focus | Ring indicator | focus:ring-2 focus:ring-blue-500 focus:ring-offset-2 |
| pressed | Darker, slight scale | active:bg-blue-800 active:scale-[0.98] |
| disabled | Muted, no pointer | disabled:bg-gray-300 disabled:cursor-not-allowed |
| loading | Spinner, no text | Spinner SVG, opacity-50, pointer-events-none |
### Transitions
- All transitions: `transition-all duration-150 ease-in-out`
- Scale transitions: spring-like (use framer-motion if available)
### Implementation Notes
- Use `<button>` element, never `<div>`
- disabled state must be set via HTML attribute
- loading should set aria-busy="true"Lead with constraints to narrow the solution space.
## Constraints (Non-Negotiable)
### Technical Constraints
- React 18+ with TypeScript strict mode
- Tailwind CSS only (no CSS-in-JS)
- No external component libraries
- Bundle size: component must be < 5KB gzipped
### Design Constraints
- Must pass WCAG 2.1 AA
- Must work without JavaScript (progressive enhancement)
- Must support RTL layouts
- Color contrast ratio >= 4.5:1
### Browser Support
- Chrome 90+, Firefox 88+, Safari 14+, Edge 90+
- No IE11 support required
### Performance Constraints
- First paint < 100ms
- No layout shift on load
- Images must be lazy-loaded
---
## Now, generate a Modal component that satisfies all constraints above.Why Constraints First:
Structure feedback for effective iteration:
## Iteration 1 Feedback
### What Works
- Component structure is correct
- Props interface is well-typed
- Basic styling matches tokens
### What Needs Fixing
#### Critical (Must Fix)
1. **Missing keyboard navigation**
- Current: Only mouse interaction works
- Required: Arrow keys to navigate, Enter to select
- Reference: WAI-ARIA Listbox pattern
2. **Color contrast failure**
- Current: text-gray-400 on bg-white (ratio 2.5:1)
- Required: Minimum 4.5:1 for body text
- Fix: Use text-gray-600 (ratio 5.7:1)
#### Important (Should Fix)
3. **Animation too fast**
- Current: duration-75
- Recommended: duration-150 for better perception
#### Nice to Have
4. Consider adding subtle shadow on hover
### Revised Requirements
Regenerate the component addressing Critical and Important items.Request specific changes rather than full regeneration:
## Current Component
```tsx
<button className="bg-blue-500 text-white px-4 py-2 rounded">
Click me
</button>Show only the modified code with inline comments explaining each change.
---
### The A/B Variant Request
Request multiple options for comparison:
```markdown
Generate 3 variants of a Card component:
## Variant A: Minimal
- No shadow
- Hairline border only
- Maximum whitespace
## Variant B: Elevated
- Pronounced shadow
- No visible border
- Subtle hover lift effect
## Variant C: Outlined
- Thick left accent border
- Light background fill
- Category color coding
## Common Requirements (All Variants)
- Same prop interface
- Same content structure
- Same responsive behavior
- Same accessibility
## Output
Provide all three variants as separate components.
Include a brief rationale for when to use each.## Few-Shot Examples: Button Component
### Example 1: Primary Button
Input: Primary action button with "Submit" text
Output:
```tsx
<button className="bg-indigo-600 hover:bg-indigo-700 text-white font-medium py-2.5 px-5 rounded-lg transition-colors focus:ring-2 focus:ring-indigo-500 focus:ring-offset-2">
Submit
</button>Input: Secondary action button with "Cancel" text Output:
<button className="bg-white hover:bg-gray-50 text-gray-700 font-medium py-2.5 px-5 rounded-lg border border-gray-300 transition-colors focus:ring-2 focus:ring-gray-500 focus:ring-offset-2">
Cancel
</button>Input: Destructive action button with "Delete" text Output:
<button className="bg-red-600 hover:bg-red-700 text-white font-medium py-2.5 px-5 rounded-lg transition-colors focus:ring-2 focus:ring-red-500 focus:ring-offset-2">
Delete
</button>Now generate: Ghost button with "Learn More" text
**Pattern Recognition**:
- Consistent class structure across examples
- Clear input-output mapping
- Similar complexity level
- Demonstrates the pattern, not just the answer
---
## Prompt Templates
### Template: Component Generation
```markdown
# Generate: {ComponentName}
## Context
Project: {ProjectDescription}
Design System: {DesignSystemName}
Framework: React + TypeScript + Tailwind
## Design Tokens
{DesignTokensJSON}
## Component Specification
Purpose: {ComponentPurpose}
Props: {PropsTable}
States: {StatesList}
Variants: {VariantsList}
## Visual Requirements
Layout: {LayoutDescription}
Typography: {TypographySpecs}
Colors: {ColorSpecs}
Spacing: {SpacingSpecs}
## Behavior
Interactions: {InteractionList}
Animations: {AnimationSpecs}
Accessibility: {A11yRequirements}
## Constraints
{ConstraintsList}
## Output
Provide production-ready React TypeScript component.
Include prop types, JSDoc comments, and usage example.# Review: {ComponentCode}
## Review Criteria
### Design Fidelity
- Does it match the design tokens?
- Is spacing consistent?
- Are colors correct?
### Accessibility
- Keyboard navigable?
- Screen reader friendly?
- Color contrast sufficient?
### Code Quality
- Types correct?
- Props well-named?
- Logic clear?
### Performance
- Unnecessary re-renders?
- Bundle size reasonable?
- Animations performant?
## Output Format
For each criterion, provide:
- Score (1-5)
- Issues found
- Specific fixes neededBad: "Make it look modern and clean" Good: "Use Inter font, 16px base, 1.5 line-height, 24px vertical rhythm"
Bad: "Create a button" Good: "Create a button with idle, hover, focus, active, disabled, and loading states"
Bad: "Use a nice blue" Good: "Use the primary color from the design tokens: #4F46E5"
Bad: "Make it accessible" Good: "Include ARIA labels, keyboard navigation per WAI-ARIA Listbox pattern, focus indicators"
Bad: Expecting perfect output on first try Good: Plan for 2-3 refinement iterations with structured feedback
| Situation | Pattern to Use |
|---|---|
| New component | Component Contract |
| Ensure consistency | Design Token Injection |
| Explain visual intent | Visual Reference Chain |
| Complex interactions | State Machine Specification |
| Avoid rework | Constraint-First Prompting |
| Improving output | Feedback Loop Protocol |
| Minor adjustments | Diff-Based Refinement |
| Exploring options | A/B Variant Request |
This skill pairs well with:
agent-orchestration/ui-agent-patterns - Prompt patterns for agent delegationcontext-management/design-system-context - Loading tokens into promptsllm-application-dev/prompt-engineering-patterns - General prompting foundationsdesign-mastery/design-principles - Visual vocabulary for descriptions"A precise prompt is a precise thought. The UI emerges from the clarity of intention."
© HermeticOrmus, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in plugins/llm-application-dev/skills/prompt-engineering-ui of HermeticOrmus/LibreUIUX-Claude-Code.
Open the folder on GitHubat commit 41a968c
Prompt Engineering UI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Prompt Engineering UI this skillHermeticOrmus/LibreUIUX-Claude-Code | 112 | — | ~3.6k | Automated safety check: Pass | MIT | |
| Prompt Engineer Toolkitalirezarezvani/claude-skills | 28k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Prompt Improverseverity1/claude-code-prompt-improver | 1.9k | 1 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Prompt Engineering Patternsynulihao/AgentSkillOS | 618 | 14 repos | ~1.7k | Automated safety check: Pass | None | |
| Patch CreationPiebald-AI/tweakcc | 2.5k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Senior Prompt Engineermaslennikov-ig/claude-code-orchestrator-kit | 260 | 3 repos | ~1.4k | Automated safety check: Pass | Custom licence |
alirezarezvani/claude-skills
Turns marketing prompts into tested, versioned production assets: A/B prompt evaluation against structured test cases, immutable prompt version history with diffs, ready-to-use marketing prompt…
severity1/claude-code-prompt-improver
This skill enriches vague prompts with targeted research and clarification before execution.
ynulihao/AgentSkillOS
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production.
Piebald-AI/tweakcc
Create and register new patches for tweakcc. An agent skill from Piebald-AI/tweakcc.
maslennikov-ig/claude-code-orchestrator-kit
Provides reference guides and Python scripts for prompt optimization, RAG evaluation, and agent orchestration when building or tuning LLM systems.
baskduf/FableCodex
Apply a Claude Fable 5 inspired operating style inside Codex.
HermeticOrmus/LibreUIUX-Claude-Code
Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration.
HermeticOrmus/LibreUIUX-Claude-Code
Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, and GCP.
HermeticOrmus/LibreUIUX-Claude-Code
Rules and worked examples for combining an archetype (structure and behavior) with a Major Arcana card (color and mood) into one coherent design system.
HermeticOrmus/LibreUIUX-Claude-Code
Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns.
HermeticOrmus/LibreUIUX-Claude-Code
Brand identity building blocks: positioning, personality, archetypes, logo systems, color palettes, type pairing, voice, and guidelines documentation.
HermeticOrmus/LibreUIUX-Claude-Code
Core visual design principles (visual hierarchy, Gestalt grouping, composition, balance, contrast, white space, color, typography) with UI fixes, a checklist, and deep-dive references.
Categories
Prompt patterns for consistent UI generation: stating design intent precisely, component specification formats, few-shot examples, and structured refinement loops. Prompt Engineering UI is an agent skill from HermeticOrmus/LibreUIUX-Claude-Code. Prompt patterns for consistent UI generation: stating design intent precisely, component specification formats, few-shot examples, and structured refinement loops.
Prompt Engineering UI fits situations like: UI output from an LLM is inconsistent; building reusable prompt templates for a design system.
Run `npx skills add HermeticOrmus/LibreUIUX-Claude-Code --skill prompt-engineering-ui -a claude-code`. Or copy the skill folder (plugins/llm-application-dev/skills/prompt-engineering-ui in HermeticOrmus/LibreUIUX-Claude-Code) into .claude/skills/prompt-engineering-ui in your project. Claude Code loads it when a task matches its description.
Run `npx skills add HermeticOrmus/LibreUIUX-Claude-Code --skill prompt-engineering-ui -a codex`. Or copy the skill folder (plugins/llm-application-dev/skills/prompt-engineering-ui in HermeticOrmus/LibreUIUX-Claude-Code) into .agents/skills/prompt-engineering-ui in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HermeticOrmus/LibreUIUX-Claude-Code --skill prompt-engineering-ui -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prompt-engineering-ui, .gemini/skills/prompt-engineering-ui, .github/skills/prompt-engineering-ui and .opencode/skills/prompt-engineering-ui in your project.
SKILL.md names no scripts, command-line tools or credentials: Prompt Engineering UI is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Prompt Engineering UI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.6k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Prompt Engineering UI: Prompt Engineer Toolkit (alirezarezvani/claude-skills, 28k stars), Prompt Improver (severity1/claude-code-prompt-improver, 1.9k stars), Prompt Engineering Patterns (ynulihao/AgentSkillOS, 618 stars) and Patch Creation (Piebald-AI/tweakcc, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
HermeticOrmus (a GitHub user) maintains it in HermeticOrmus/LibreUIUX-Claude-Code, which has 112 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 4, 2026.
Source: HermeticOrmus/LibreUIUX-Claude-Code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.