Agent skill

UI Agent Patterns

by HermeticOrmus in HermeticOrmus/LibreUIUX-Claude-Code

Patterns for delegating UI work to agents: one synthesis agent versus specialized agents, multi-agent pipelines for research, design, implementation, and review, and clean handoffs between them.

MITAuto-check passedFrontend & Design

Install UI Agent Patterns

skills CLI
$ npx skills add HermeticOrmus/LibreUIUX-Claude-Code --skill ui-agent-patterns -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HermeticOrmus/LibreUIUX-Claude-Code ui-agent-patterns --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HermeticOrmus/LibreUIUX-Claude-Code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/agent-orchestration/skills/ui-agent-patterns .claude/skills/ui-agent-patterns && rm -rf skills-src

Use ~/.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/

Facts

Skill name
ui-agent-patterns
GitHub stars
112
Token cost
~4.6k tokens
SKILL.md length
565 words
Files
1
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

Patterns for delegating UI work to agents: one synthesis agent versus specialized agents, multi-agent pipelines for research, design, implementation, and review, and clean handoffs between them.

  • Works in 5 steps: Monolithic Mega-Prompt → Context Overflow → No Feedback Loop → …
  • A UI task is too large for one pass
  • SKILL.md covers When to Use This Skill, Core Concepts, Agent Architecture Patterns and Multi-Agent Workflow Patterns, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

UI Agent Patterns is an agent skill from HermeticOrmus/LibreUIUX-Claude-Code. Patterns for delegating UI work to agents: one synthesis agent versus specialized agents, multi-agent pipelines for research, design, implementation, and review, and clean handoffs between them. Use when a UI task is too large for one pass or you are designing an agent workflow for components or design systems.

Its SKILL.md is about 4.6k 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 Frontend & Design, covering Design systems, Multi-agent orchestration and Software architecture. 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.

When your agent uses it

  • A UI task is too large for one pass
  • You are designing an agent workflow for components

Example prompts

  • “Use the ui-agent-patterns skill to pattern for delegating UI work to agents: one synthesis agent versus specialized agents, multi-agent pipelines…”
  • “/ui-agent-patterns”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Monolithic Mega-Prompt
  2. Context Overflow
  3. No Feedback Loop
  4. Hardcoded Workflows
  5. Agent Anarchy

What it can do on your machine

Read from SKILL.md and the folder at commit 41a968c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

UI Agent Patterns loads about 4.6k tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 565 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~4.6k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from HermeticOrmus/LibreUIUX-Claude-Code at commit 41a968c, republished under its MIT licence (© HermeticOrmus). 565 words, ~4,590 tokens.

Download SKILL.mdSave it as .claude/skills/ui-agent-patterns/SKILL.md (or your agent's skills folder).
name
ui-agent-patterns
description
Patterns for delegating UI work to agents: one synthesis agent versus specialized agents, multi-agent pipelines for research, design, implementation, and review, and clean handoffs between them. Use when a UI task is too large for one pass or you are designing an agent workflow for components or design systems.

UI Agent Patterns

Patterns for orchestrating AI agents to generate, refine, and maintain user interfaces. This skill bridges Karpathy's "new programming vocabulary" with practical UI/UX development workflows.


When to Use This Skill

  • Delegating complex UI generation to specialized agents
  • Deciding between synthesis-master vs specialized agent architectures
  • Orchestrating multi-agent workflows for design systems
  • Managing handoffs between research, design, and implementation agents
  • Building agent pipelines for iterative UI refinement
  • Scaling UI generation beyond single-agent capabilities

Core Concepts

The New Programming Vocabulary

Karpathy's insight: LLMs introduce new programming primitives that extend beyond functions and objects:

PrimitiveDescriptionUI Application
AgentsAutonomous LLM-powered workersUI generators, reviewers, refiners
SubagentsDelegated specialistsComponent builders, accessibility checkers
PromptsInstructions as codeDesign specifications, component contracts
ContextsShared state and knowledgeDesign tokens, brand guidelines
MemoryPersistent learningStyle preferences, past decisions
ModesBehavioral configurationsDraft mode, production mode, audit mode
PermissionsCapability boundariesRead-only review vs code modification
ToolsExternal capabilitiesFigma API, browser DevTools, screenshot capture
PluginsModular extensionsDesign system loaders, component libraries
SkillsReusable knowledgeThis file - codified expertise
HooksLifecycle interceptorsPre-commit design checks, post-render audits
MCPModel Context ProtocolTool integration standard
WorkflowsOrchestrated sequencesDesign-to-code pipelines

Agent Architecture Patterns

Pattern 1: Synthesis-Master Architecture

A single powerful agent handles the full UI generation task.

When to Use:

  • Simple, well-defined UI tasks
  • Tight coupling between decisions
  • Speed is critical
  • Context window sufficient for entire task

Structure:

[User Request]
      |
      v
+------------------+
|  Synthesis-Master |
|  (Full Context)  |
+------------------+
      |
      v
[Complete UI Output]

Implementation:

python
class SynthesisMasterAgent:
    """
    Single agent handling all UI generation aspects.
    Best for: Landing pages, simple forms, atomic components
    """

    def __init__(self, model: str = "claude-sonnet-4-5-20250929"):
        self.context = {
            "design_tokens": load_design_tokens(),
            "brand_guidelines": load_brand_context(),
            "component_library": load_component_docs(),
            "accessibility_rules": load_a11y_rules(),
        }

    async def generate(self, request: UIRequest) -> UIOutput:
        prompt = f"""
        You are a senior UI engineer and designer. Generate a complete,
        production-ready component based on this request.

        Context:
        - Design Tokens: {self.context['design_tokens']}
        - Brand Guidelines: {self.context['brand_guidelines']}

        Request: {request.description}

        Output requirements:
        1. React/TypeScript component
        2. Tailwind CSS styling
        3. Accessibility attributes
        4. Responsive breakpoints
        5. Dark mode support
        """

        return await self.model.generate(prompt)

Advantages:

  • Simpler orchestration
  • No handoff overhead
  • Consistent voice/style
  • Lower latency

Disadvantages:

  • Context window limits
  • Single point of failure
  • Hard to scale complexity
  • No specialized expertise

Pattern 2: Specialized Agent Swarm

Multiple specialized agents collaborate on UI tasks.

When to Use:

  • Complex design systems
  • Tasks requiring different expertise
  • Parallel processing beneficial
  • Quality through specialization

Structure:

[User Request]
      |
      v
+------------------+
|   Orchestrator   |
+------------------+
      |
      +-----------------+----------------+----------------+
      |                 |                |                |
      v                 v                v                v
+----------+     +----------+     +----------+     +----------+
| Research |     |  Design  |     |   Code   |     |  Review  |
|  Agent   |     |  Agent   |     |  Agent   |     |  Agent   |
+----------+     +----------+     +----------+     +----------+
      |                 |                |                |
      v                 v                v                v
  [Context]        [Wireframe]      [Component]       [Audit]

Specialized Agent Definitions:

python
# Agent 1: Research Agent
class UIResearchAgent:
    """
    Gathers context and prior art before design begins.
    """

    permissions = ["read_codebase", "search_web", "read_figma"]

    async def research(self, request: UIRequest) -> ResearchContext:
        return {
            "existing_patterns": await self.find_similar_components(),
            "competitive_analysis": await self.analyze_competitors(),
            "user_research": await self.gather_user_insights(),
            "technical_constraints": await self.identify_constraints(),
        }

# Agent 2: Design Agent
class UIDesignAgent:
    """
    Produces design specifications and wireframes.
    """

    permissions = ["generate_images", "access_design_tokens"]

    async def design(self, context: ResearchContext) -> DesignSpec:
        return {
            "layout": await self.generate_layout(),
            "spacing": await self.calculate_spacing(),
            "typography": await self.select_typography(),
            "colors": await self.derive_color_scheme(),
            "interactions": await self.define_interactions(),
        }

# Agent 3: Implementation Agent
class UIImplementationAgent:
    """
    Translates designs into production code.
    """

    permissions = ["write_code", "access_component_library"]

    async def implement(self, spec: DesignSpec) -> CodeOutput:
        return await self.generate_component(
            framework="react",
            styling="tailwind",
            typescript=True,
            spec=spec
        )

# Agent 4: Review Agent
class UIReviewAgent:
    """
    Audits output for quality, accessibility, and standards.
    """

    permissions = ["read_code", "run_tests", "access_browser"]
    mode = "audit"  # Read-only, cannot modify

    async def review(self, code: CodeOutput) -> ReviewReport:
        return {
            "accessibility": await self.audit_a11y(),
            "performance": await self.audit_performance(),
            "design_fidelity": await self.compare_to_spec(),
            "code_quality": await self.lint_and_analyze(),
        }

Pattern 3: Hierarchical Delegation

Master agent delegates to subagents for specific subtasks.

When to Use:

  • Complex pages with many components
  • Need for parallel component generation
  • Different components require different expertise

Structure:

[User Request: "Create a dashboard"]
             |
             v
    +------------------+
    |   Master Agent   |
    | (Task Planning)  |
    +------------------+
             |
    +--------+--------+--------+
    |        |        |        |
    v        v        v        v
[Header] [Sidebar] [Charts] [Tables]
Subagent Subagent Subagent Subagent
    |        |        |        |
    v        v        v        v
  [JSX]    [JSX]    [JSX]    [JSX]
             |
             v
    +------------------+
    |   Master Agent   |
    |  (Integration)   |
    +------------------+
             |
             v
     [Complete Dashboard]

Implementation:

python
class HierarchicalUIOrchestrator:
    """
    Master agent that delegates to specialized subagents.
    """

    def __init__(self):
        self.subagents = {
            "header": HeaderComponentAgent(),
            "sidebar": SidebarComponentAgent(),
            "charts": DataVisualizationAgent(),
            "tables": DataTableAgent(),
            "forms": FormBuilderAgent(),
        }

    async def generate_page(self, request: PageRequest) -> PageOutput:
        # Step 1: Plan the page structure
        plan = await self.plan_page_structure(request)

        # Step 2: Delegate component generation in parallel
        component_tasks = []
        for component in plan.components:
            agent = self.subagents[component.type]
            task = agent.generate(component.spec)
            component_tasks.append(task)

        components = await asyncio.gather(*component_tasks)

        # Step 3: Integrate components into cohesive page
        page = await self.integrate_components(components, plan.layout)

        # Step 4: Final coherence review
        return await self.ensure_coherence(page)

    async def plan_page_structure(self, request: PageRequest) -> PagePlan:
        """
        Master agent determines page structure and delegation.
        """
        prompt = f"""
        Analyze this page request and create a component breakdown:

        Request: {request.description}

        For each component, specify:
        1. Component type (header, sidebar, chart, table, form, etc.)
        2. Component requirements
        3. Data dependencies
        4. Layout position

        Return as structured JSON.
        """
        return await self.model.generate(prompt, format="json")

Multi-Agent Workflow Patterns

Workflow 1: Design-to-Code Pipeline

Sequential workflow from design intent to production code.

python
class DesignToCodePipeline:
    """
    Complete workflow from natural language to deployed UI.
    """

    stages = [
        ("interpret", InterpretationAgent()),    # NL -> Design Intent
        ("design", DesignAgent()),               # Intent -> Wireframe
        ("specify", SpecificationAgent()),       # Wireframe -> Spec
        ("implement", ImplementationAgent()),    # Spec -> Code
        ("review", ReviewAgent()),               # Code -> Audit
        ("refine", RefinementAgent()),           # Audit -> Final Code
    ]

    async def run(self, request: str) -> CodeOutput:
        context = {"request": request}

        for stage_name, agent in self.stages:
            result = await agent.process(context)
            context[stage_name] = result

            # Allow early exit on critical issues
            if result.has_blocking_issues:
                return self.handle_blocker(stage_name, result)

        return context["refine"]
Show full SKILL.md (226 more words)Show less
Workflow 2: Iterative Refinement Loop

Agent loop that refines UI through multiple passes.

python
class IterativeRefinementWorkflow:
    """
    Generate -> Review -> Refine loop until quality threshold met.
    """

    def __init__(self, max_iterations: int = 5):
        self.generator = UIGeneratorAgent()
        self.reviewer = UIReviewerAgent()
        self.refiner = UIRefinerAgent()
        self.max_iterations = max_iterations
        self.quality_threshold = 0.85

    async def run(self, request: UIRequest) -> RefinedOutput:
        # Initial generation
        current = await self.generator.generate(request)

        for iteration in range(self.max_iterations):
            # Review current version
            review = await self.reviewer.review(current)

            # Check if quality threshold met
            if review.score >= self.quality_threshold:
                return current

            # Refine based on feedback
            current = await self.refiner.refine(
                current=current,
                feedback=review.feedback,
                priority=review.critical_issues
            )

        # Return best effort after max iterations
        return current
Workflow 3: Parallel Variant Generation

Generate multiple design variants for comparison.

python
class ParallelVariantWorkflow:
    """
    Generate multiple design variants in parallel for A/B consideration.
    """

    async def generate_variants(
        self,
        request: UIRequest,
        variant_count: int = 3
    ) -> list[DesignVariant]:

        # Define variant strategies
        strategies = [
            {"style": "minimal", "focus": "whitespace"},
            {"style": "bold", "focus": "typography"},
            {"style": "playful", "focus": "interactions"},
        ][:variant_count]

        # Generate in parallel
        tasks = [
            self.generate_variant(request, strategy)
            for strategy in strategies
        ]

        variants = await asyncio.gather(*tasks)

        # Score and rank variants
        scored = await self.score_variants(variants, request.criteria)

        return sorted(scored, key=lambda v: v.score, reverse=True)

Agent Memory Patterns

Pattern: Design Decision Memory

Persist design decisions for consistency across sessions.

python
class DesignMemory:
    """
    Persistent memory of design decisions and preferences.
    """

    def __init__(self, project_id: str):
        self.project_id = project_id
        self.decisions = self.load_decisions()

    def remember_decision(self, decision: DesignDecision):
        """
        Store a design decision for future reference.

        Example decisions:
        - "Primary buttons use bg-blue-600, not bg-blue-500"
        - "Card corners are rounded-xl (12px)"
        - "Error states use red-600 with shake animation"
        """
        self.decisions.append({
            "timestamp": datetime.now(),
            "category": decision.category,
            "rule": decision.rule,
            "rationale": decision.rationale,
        })
        self.persist()

    def recall_relevant(self, context: str) -> list[DesignDecision]:
        """
        Retrieve decisions relevant to current context.
        """
        # Semantic search over past decisions
        return self.vector_search(context, top_k=5)

    def inject_into_prompt(self, base_prompt: str) -> str:
        """
        Augment prompt with relevant past decisions.
        """
        relevant = self.recall_relevant(base_prompt)

        if not relevant:
            return base_prompt

        decisions_context = "\n".join([
            f"- {d.rule} (Rationale: {d.rationale})"
            for d in relevant
        ])

        return f"""
        {base_prompt}

        ## Past Design Decisions (maintain consistency):
        {decisions_context}
        """

Modes and Permissions

Agent Modes

Configure agent behavior for different contexts:

python
class UIAgentModes:
    """
    Different operational modes for UI agents.
    """

    MODES = {
        "draft": {
            "description": "Fast, exploratory generation",
            "quality_threshold": 0.6,
            "iterations": 1,
            "include_comments": True,
            "placeholder_content": True,
        },
        "production": {
            "description": "High-quality, deployment-ready",
            "quality_threshold": 0.9,
            "iterations": 5,
            "include_comments": False,
            "placeholder_content": False,
        },
        "audit": {
            "description": "Read-only review mode",
            "can_modify": False,
            "generate_report": True,
        },
        "learning": {
            "description": "Explain decisions, teach patterns",
            "verbose_reasoning": True,
            "cite_sources": True,
        },
    }
Permission Boundaries

Define what agents can and cannot do:

python
class AgentPermissions:
    """
    Capability boundaries for UI agents.
    """

    # File system permissions
    READ_CODEBASE = "read_codebase"
    WRITE_COMPONENTS = "write_components"
    WRITE_STYLES = "write_styles"
    MODIFY_CONFIG = "modify_config"

    # Tool permissions
    ACCESS_BROWSER = "access_browser"
    ACCESS_FIGMA = "access_figma"
    RUN_TESTS = "run_tests"
    DEPLOY_PREVIEW = "deploy_preview"

    # Common permission sets
    READONLY_REVIEWER = [READ_CODEBASE, ACCESS_BROWSER]
    COMPONENT_BUILDER = [READ_CODEBASE, WRITE_COMPONENTS, WRITE_STYLES]
    FULL_ACCESS = [READ_CODEBASE, WRITE_COMPONENTS, WRITE_STYLES,
                   MODIFY_CONFIG, ACCESS_BROWSER, RUN_TESTS]

Anti-Patterns to Avoid

1. Monolithic Mega-Prompt

Problem: Stuffing all instructions into one giant prompt Solution: Use hierarchical delegation with focused agents

2. Context Overflow

Problem: Exceeding context window with full design system Solution: Use RAG to inject relevant context dynamically

3. No Feedback Loop

Problem: Single-pass generation with no validation Solution: Implement review-refine loops with quality thresholds

4. Hardcoded Workflows

Problem: Rigid pipelines that can't adapt Solution: Dynamic orchestration based on task complexity

5. Agent Anarchy

Problem: Too many agents with unclear responsibilities Solution: Clear separation of concerns, explicit handoff protocols


Quick Reference

ScenarioRecommended Pattern
Simple componentSynthesis-Master
Full page designHierarchical Delegation
Design system workSpecialized Agent Swarm
Rapid prototypingDraft mode + single agent
Production deploymentFull pipeline with review
A/B testing designsParallel Variant Generation

Integration with LibreUIUX

This skill works best when combined with:

  • design-mastery/design-principles - Feed principles to Design Agent
  • archetypal-alchemy/jungian-archetypes - Personality for UI generation
  • context-management/design-system-context - Token management
  • mcp-integrations/browser-devtools-mcp - Live inspection tools

"The agent is not the code - it is the intention made executable."

© HermeticOrmus, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/agent-orchestration/skills/ui-agent-patterns of HermeticOrmus/LibreUIUX-Claude-Code.

Open the folder on GitHubat commit 41a968c

Compare with similar skills

UI Agent Patterns 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.

UI Agent Patterns compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
UI Agent Patterns this skillHermeticOrmus/LibreUIUX-Claude-Code112—~4.6kAutomated safety check: PassMIT
Lago Frontend Patternsgetlago/lago-front163—~497Automated safety check: PassAGPL-3.0
Design System Starteraiskillstore/marketplace430—~3.8kAutomated safety check: PassNone
System Designopenxlings/xlings6151 repos~328Automated safety check: PassApache-2.0
Improve UI Audit and Plansibelick/ui-skills9.5k—~2kAutomated safety check: PassMIT
Fast Agent Designevalstate/fast-agent3.9k—~220Automated safety check: PassApache-2.0

Similar skills

  • Lago Frontend Patterns

    getlago/lago-front

    Implementation guidelines for lago-front's recurring UI patterns and design-system/layout components - an index below pointing to references/<topic.md, covering both established architecture…

    163 GitHub stars~497 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Design System Starter

    aiskillstore/marketplace

    A skill your agent uses when creating or evolving design systems for applications.

    430 GitHub stars~3.8k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • System Design

    openxlings/xlings

    Design systems, services, and architectures. An agent skill from openxlings/xlings.

    615 GitHub starsUsed in 1 repo~328 tokens
    Backend & APIsAuto-check passed
  • Audits one product surface against its own design evidence and writes self-contained implementation plans for another agent, without touching product source.

    9.5k GitHub stars~2k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Fast Agent Design

    evalstate/fast-agent

    A skill your agent uses to generate well-branded interfaces and assets for fast-agent, either for production or throwaway prototypes/mocks/etc.

    3.9k GitHub stars~220 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Repo Healthcheck Node

    commercetools/ui-kit

    Verify a Node.js/TypeScript repo's development environment is correctly set up.

    154 GitHub stars~1.6k tokensUpdated 5 days ago
    Frontend & DesignAuto-check: notes

More from HermeticOrmus/LibreUIUX-Claude-Code

All 15 skills in this repo
  • Deployment Pipeline Design

    HermeticOrmus/LibreUIUX-Claude-Code

    Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration.

    112 GitHub starsUsed in 11 repos~2.1k tokens
    Auto-check passed
  • Langchain Architecture

    HermeticOrmus/LibreUIUX-Claude-Code

    Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns.

    112 GitHub starsUsed in 11 repos~2.5k tokens
    Auto-check passed
  • Archetypal Combinations

    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.

    112 GitHub stars~3.4k tokensUpdated 3 days ago
    Auto-check passed
  • Multi Cloud Architecture

    HermeticOrmus/LibreUIUX-Claude-Code

    Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, and GCP.

    112 GitHub starsUsed in 11 repos~1.2k tokens
    Auto-check passed
  • Brand Systems

    HermeticOrmus/LibreUIUX-Claude-Code

    Brand identity building blocks: positioning, personality, archetypes, logo systems, color palettes, type pairing, voice, and guidelines documentation.

    112 GitHub stars~2.3k tokensUpdated 3 days ago
    Auto-check passed
  • Design Principles

    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.

    112 GitHub stars~2k tokensUpdated 3 days ago
    Auto-check passed

Questions about UI Agent Patterns

What does UI Agent Patterns do?

Patterns for delegating UI work to agents: one synthesis agent versus specialized agents, multi-agent pipelines for research, design, implementation, and review, and clean handoffs between them. UI Agent Patterns is an agent skill from HermeticOrmus/LibreUIUX-Claude-Code. Patterns for delegating UI work to agents: one synthesis agent versus specialized agents, multi-agent pipelines for research, design, implementation, and review, and clean handoffs between them.

When should I use UI Agent Patterns?

UI Agent Patterns fits situations like: A UI task is too large for one pass; you are designing an agent workflow for components.

How do I install UI Agent Patterns in Claude Code?

Run `npx skills add HermeticOrmus/LibreUIUX-Claude-Code --skill ui-agent-patterns -a claude-code`. Or copy the skill folder (plugins/agent-orchestration/skills/ui-agent-patterns in HermeticOrmus/LibreUIUX-Claude-Code) into .claude/skills/ui-agent-patterns in your project. Claude Code loads it when a task matches its description.

How do I install UI Agent Patterns in Codex?

Run `npx skills add HermeticOrmus/LibreUIUX-Claude-Code --skill ui-agent-patterns -a codex`. Or copy the skill folder (plugins/agent-orchestration/skills/ui-agent-patterns in HermeticOrmus/LibreUIUX-Claude-Code) into .agents/skills/ui-agent-patterns in your project. Codex loads it when a task matches its description.

Can I use UI Agent Patterns in Cursor, Gemini CLI or GitHub Copilot?

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 ui-agent-patterns -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ui-agent-patterns, .gemini/skills/ui-agent-patterns, .github/skills/ui-agent-patterns and .opencode/skills/ui-agent-patterns in your project.

What does UI Agent Patterns need to run?

SKILL.md names no scripts, command-line tools or credentials: UI Agent Patterns is instructions for the agent only. Our summary lists: Python 3.

Does UI Agent Patterns access the network?

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.

Is UI Agent Patterns safe to install?

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.

What licence does UI Agent Patterns use?

UI Agent Patterns is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does UI Agent Patterns use?

About 4.6k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to UI Agent Patterns?

Skills that share tags, products or a category with UI Agent Patterns: Lago Frontend Patterns (getlago/lago-front, 163 stars), Design System Starter (aiskillstore/marketplace, 430 stars), System Design (openxlings/xlings, 615 stars) and Improve UI Audit and Plans (ibelick/ui-skills, 9.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains UI Agent Patterns?

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.