agentic
bergside/awesome-design-skills
Design system for conversational AI interfaces with minimal controls and delegated task flows.
What is agentic?
Agentic is a design-system skill for building conversational AI-first interfaces that emphasize clear outcomes and delegated workflows. Use it when designing interfaces where users delegate tasks to AI rather than manually managing complex processes.
- Provides foundational design tokens (typography, color, spacing) for agentic UI patterns
- Defines component anatomy, states, and interaction behavior for conversational interfaces
- Establishes accessibility standards (WCAG 2.2 AA) with keyboard-first interactions and semantic HTML
- Documents writing tone and content standards for AI-delegated workflows
- Includes anti-patterns, QA checklists, and migration guidance for consistent implementation
- Specifies responsive behavior, empty/loading/error states, and touch-target sizing
How to install agentic
npx skills add https://github.com/bergside/awesome-design-skills --skill agenticHow to use agentic
- 1.Review the style foundations (typography scale, color palette, spacing grid) to understand the design language
- 2.Study the accessibility requirements (WCAG 2.2 AA, keyboard navigation, focus states) before implementing components
- 3.Use the guideline authoring workflow to create component-specific rules for your agentic interfaces
- 4.Define component anatomy, states (default, hover, focus, active, disabled, loading, error), and interaction behavior
- 5.Document content and tone standards aligned with the concise, action-oriented voice
- 6.Apply the QA checklist during code review to ensure consistency and accessibility compliance
Use cases
- Building conversational AI chat interfaces with minimal control surfaces
- Designing task-delegation workflows where users instruct AI to handle complex operations
- Creating design systems for agentic products emphasizing clear outcomes over manual controls
- Establishing accessibility and interaction standards for AI-first applications
- Documenting design tokens and component patterns for multi-team implementation
- Design system authors and maintainers
- Product designers building AI-first interfaces
- Engineers implementing conversational UI components
- Teams standardizing agentic workflow patterns
agentic FAQ
The system provides typography (Playfair Display for primary/display, JetBrains Mono for mono), a color palette (primary #FF5701, secondary #F6F6F1, success #16A34A, warning #D97706, danger #DC2626), and an 8pt baseline spacing grid.
No, it is framework-agnostic and provides implementation-ready guidance applicable to any tech stack.
It requires WCAG 2.2 AA compliance, keyboard-first interactions, visible focus states, semantic HTML, screen-reader testing, reduced-motion support, and 44px+ touch targets.
While designed for agentic (AI-delegated) workflows, the foundational design tokens and component patterns can be adapted for other conversational or task-oriented interfaces.
No; it provides design principles, token definitions, and authoring guidance for creating component rules, not pre-built components.
Full instructions (SKILL.md)
Source of truth, from bergside/awesome-design-skills.
name: agentic description: Conversational AI-first interface with minimal controls, clear outcomes, and delegated task flows for agentic workflows. license: MIT metadata: author: typeui.sh
<!-- TYPEUI_SH_MANAGED_START -->Agentic Design System Skill (Universal)
Mission
You are an expert design-system guideline author for Agentic. Create practical, implementation-ready guidance that can be directly used by engineers and designers.
Brand
The agentic design style emphasizes conversational interactions, clear outcomes, and minimal controls, allowing users to delegate tasks to AI instead of manually managing complex workflows.
Style Foundations
- Visual style: modern, bold
- Typography scale: 14/16/18/24/32/40 | Fonts: primary=Playfair Display, display=Playfair Display, mono=JetBrains Mono | weights=100, 200, 300, 400, 500, 600, 700, 800, 900
- Color palette: surface/subtle layers | Tokens: primary=#FF5701, secondary=#F6F6F1, success=#16A34A, warning=#D97706, danger=#DC2626, surface=#FFFFFF, text=#111827
- Spacing scale: 8pt baseline grid
Accessibility
WCAG 2.2 AA, keyboard-first interactions, visible focus states, semantic HTML before ARIA, screen-reader tested labels, reduced-motion support, 44px+ touch targets, high-contrast support
Writing Tone
concise, confident, helpful, clear, friendly, professional, action-oriented, low-jargon
Rules: Do
- prefer semantic tokens over raw values
- preserve visual hierarchy
- keep interaction states explicit
- design for empty/loading/error states
- ensure responsive behavior by default
- document accessibility rationale
Rules: Don't
- avoid low contrast text
- avoid inconsistent spacing rhythm
- avoid decorative motion without purpose
- avoid ambiguous labels
- avoid mixing multiple visual metaphors
- avoid inaccessible hit areas
Expected Behavior
- Follow the foundations first, then component consistency.
- When uncertain, prioritize accessibility and clarity over novelty.
- Provide concrete defaults and explain trade-offs when alternatives are possible.
- Keep guidance opinionated, concise, and implementation-focused.
Guideline Authoring Workflow
- Restate the design intent in one sentence before proposing rules.
- Define tokens and foundational constraints before component-level guidance.
- Specify component anatomy, states, variants, and interaction behavior.
- Include accessibility acceptance criteria and content-writing expectations.
- Add anti-patterns and migration notes for existing inconsistent UI.
- End with a QA checklist that can be executed in code review.
Required Output Structure
When generating design-system guidance, use this structure:
- Context and goals
- Design tokens and foundations
- Component-level rules (anatomy, variants, states, responsive behavior)
- Accessibility requirements and testable acceptance criteria
- Content and tone standards with examples
- Anti-patterns and prohibited implementations
- QA checklist
Component Rule Expectations
- Define required states: default, hover, focus-visible, active, disabled, loading, error (as relevant).
- Describe interaction behavior for keyboard, pointer, and touch.
- State spacing, typography, and color-token usage explicitly.
- Include responsive behavior and edge cases (long labels, empty states, overflow).
Quality Gates
- No rule should depend on ambiguous adjectives alone; anchor each rule to a token, threshold, or example.
- Every accessibility statement must be testable in implementation.
- Prefer system consistency over one-off local optimizations.
- Flag conflicts between aesthetics and accessibility, then prioritize accessibility.
Example Constraint Language
- Use "must" for non-negotiable rules and "should" for recommendations.
- Pair every do-rule with at least one concrete don't-example.
- If introducing a new pattern, include migration guidance for existing components.
Related skills
More from bergside/awesome-design-skills and the wider catalog.

ant
Enterprise design system for data-dense web applications with structured, accessible components.

artistic
High-contrast, expressive design system with bold typography and creative color for visually striking interfaces.

bento
Modular grid layout system for organized, scannable interfaces with card-like blocks and clear hierarchy.

bold
Strong visual presence with heavyweight typography, high-contrast colors, and commanding layouts.

brutalism
Raw, anti-design aesthetic system inspired by concrete architecture with unadorned elements and functional minimalism.

cafe
Cozy café-inspired design system with warm tones, soft typography, and accessible component guidance.