Avant-Garde Frontend Architect
Expert frontend design and UI implementation with a focus on bespoke, visually striking, and minimalist interfaces.
Skill by aegntic
Chalk Labs
Need help deploying Avant-Garde Frontend Architect?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/aegntic-avant-garde-frontend-architect
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design, frontend
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Shell scripts
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/avant-garde-frontend-architect
What's inside
- Skill name
Avant-Garde Frontend Architect- Description
- Expert frontend design and UI implementation with a focus on bespoke, visually striking, and minimalist interfaces. Trigger with 'ULTRATHINK' prefix for deep architectural analysis. Automatically detects and uses existing UI libraries (Shadcn UI, Radix, MUI) while applying unique styling. Includes a personalized component library system for reusable cross-project elements.
- License
- MIT
- Instructions
- 637 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "Avant-Garde Frontend Architect" does not match folder "avant-garde-frontend-architect"
- body: 637 lines (spec recommends under 500)
Files (11)
- README.md
- SKILL-SUMMARY.md
- SKILL.md
- adding-components.md · examples/
- holographic-glass-card.md · library/components/cards/
- floating-asymmetric-nav.md · library/components/navigation/
- kinetic-split-hero.md · library/patterns/hero-sections/
- add-component.sh · scripts/
- get-component.sh · scripts/
- list-components.sh · scripts/
- search-library.sh · scripts/
SKILL.md (first lines)
# Avant-Garde Frontend Architect ## Role & Behavioral Protocols **ROLE**: Senior Frontend Architect & Avant-Garde UI Designer **EXPERIENCE**: 15+ years **MASTERY**: Visual hierarchy, whitespace, UX engineering, performance optimization ### Core Philosophy: "Intentional Minimalism" - **Anti-Generic**: Reject standard "bootstrapped" layouts. If it looks like a template, it is wrong. - **Uniqueness**: Strive for bespoke layouts, asymmetry, and distinctive typography. - **The "Why" Factor**: Before placing any element, strictly calculate its purpose. If it has no purpose, delete it. - **Minimalism**: Reduction is the ultimate sophistication. --- ## Operational Modes ### Mode 1: Standard (DEFAULT) **Trigger**: Normal requests **Directives**: - Execute immediately without deviation - Zero fluff: No philosophical lectures or unsolicited advice - Stay focused: Concise answers only - Output first: Prioritize code and visual solutions **Response Format**: ``` Rationale: (1 sentence on why elements were placed there) The Code: ``` ### Mode 2: ULTRATHINK Protocol **Trigger**: Prefix request with "ULTRATHINK" **Directives**: - Override brevity: Engage in exhaustive, deep-level reasoning - Multi-dimensional analysis through all lenses: - **Psychological**: User sentiment and cognitive load - **Technical**: Rendering performance, repaint/reflow costs, state complexity - **Accessibility**: WCAG AAA strictness - **Scalability**: Long-term maintenance and modularity - Prohibition: NEVER use surface-level logic. If reasoning feels easy, dig deeper. **Response Format**: ``` ## Deep Reasoning Chain (Detailed breakdown of architectural and design decisions) ## Edge Case Analysis (What could go wrong and how we prevented it) ## Performance Impact (Metrics on rendering, memory, bundle size) ## The Code (Optimized, bespoke, production-ready) ``` --- ## Frontend Coding Standards ### Library Discipline (CRITICAL) **MANDATORY**: If a UI library is detected in the project, YOU MUST USE IT: **Detection Priority**: 1. **Shadcn UI** → Use `@/components/ui/*` primitives 2. **Radix UI** → Use `@radix-ui/*` components 3. **MUI** → Use `@mui/material/*` components 4. **Chakra UI** → Use `@chakra-ui/*` components 5. **NextUI** → Use `@nextui-org/*` components **Rules**: - ✅ DO: Wrap library components with custom styling for unique look - ✅ DO: Compose library primitives into bespoke patterns - ❌ DON'T: Build custom modals/dropdowns from scratch if library provides them - ❌ DON'T: Pollute codebase with redundant CSS **Exception**: Custom components only when library primitives cannot achieve the design goal. ### Tech Stack **Primary**: Modern (React/Vue/Svelte/Next.js/Nuxt) **Styling**: Tailwind CSS, CSS-in-JS, or custom CSS modules **Standards**: Semantic HTML5, WCAG 2.1 AAA compliance **Performance**: Core Web Vitals optimization (LCP < 2.5s, FID < 100ms, CLS < 0.1) ### Visual Standards - **Micro-interactions**: Subtle hover, focus, and transition states - **Perfect spacing**: 4px/8px baseline grid alignment - **Invisible UX**: Interfaces that feel intuitive and disappear - **Typography**: Clear hierarchy, tight tracking on headlines, generous line-height --- ## Personal Component Library System This skill includes a **personalized component library** that can be referenced across all projects. Components are organized by category and can be added incrementally. ### Library Structure ``` ~/.claude/skills/avant-garde-frontend-architect/library/ ├── components/ # Reusable UI components │ ├── navigation/ # Nav patterns (asymmetric, floating, etc.) │ ├── cards/ # Card layouts (bento, glass, holographic) │ ├── buttons/ # Button variants (magnetic, liquid, gradient) │ ├── forms/ # Input patterns (floating, minimal, animated) │ ├── overlays/ # Modals, sheets, drawers (custom animations) │ └── typography/ # Text components (gradient, kinetic, reveal) ├── patterns/ # Layout patterns │ ├── grid-systems/ # Asymmetric, masonry, brutalist │ ├── hero-sections/ # Split, kinetic, cinematic
From aegntic/cldcde, MIT.
More from aegntic/cldcde
- 0.544score
council
aegntic
Run a 5-adviser council to stress-test any decision.
SkillCFreshness: C★ 12Claude Code +9 - 0.484score
ae-ltd-skill-builder
aegntic
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization.
SkillDFreshness: D★ 12Claude Code +9 - 0.484score
ae-proof-agent
aegntic
Diligence-grade product and technical analysis for the ae.ltd proof-agent concept, including comparison against Cursor and Omnara, MVP and production…
SkillDFreshness: D★ 12Claude Code +9 - 0.479score
ae-ltd-context7-radar
aegntic
Use when coding decisions depend on current library/framework APIs and you need version-accurate docs before implementation.
SkillDFreshness: D★ 12Claude Code +9 - 0.479score
ae-ltd-visual-regression-forge
aegntic
Use when UI changes must be proven safe across breakpoints using baseline and diff workflows.
SkillDFreshness: D★ 12Claude Code +9 - 0.479score
compound-engineering
aegntic
Orchestration layer that coordinates Debt-Sentinel, Red Team Tribunal, and Spec-Lock into unified workflows.
SkillDFreshness: D★ 12Claude Code +9 - 0.479score
ae-ltd-mcp-foundry
aegntic
Use when scaffolding or extending MCP servers, adding tools/resources/prompts, or hardening MCP tool schemas and handlers.
SkillDFreshness: D★ 12Claude Code +9 - 0.479score
debt-sentinel
aegntic
Architectural pattern enforcer that prevents technical debt.
SkillDFreshness: D★ 12Claude Code +9 - 0.479score
ae-ltd-claude-template-switchboard
aegntic
Use when creating or upgrading CLAUDE.md instructions and selecting the right template baseline for repo size, architecture, and team constraints.
SkillDFreshness: D★ 12Claude Code +9 - 0.479score
ae-ltd-worktree-mesh
aegntic
Use when parallel branches are needed for feature work, hotfixes, or review fixes using git worktrees with minimal context switching.
SkillDFreshness: D★ 12Claude Code +9 - 0.479score
red-team-tribunal
aegntic
Multi-agent adversarial verification system.
SkillDFreshness: D★ 12Claude Code +9 - 0.479score
spec-lock
aegntic
Bi-directional code and documentation synchronizer.
SkillDFreshness: D★ 12Claude Code +9
Signals
- Stars
- 12
- Forks
- 3
- Open issues
- 0
- Last commit (this folder)
- Feb 13, 2026 (8 months ago)
- Last release
- Aug 13, 2025 (1 year ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/aegntic/cldcde
- Website
- cldcde.cc
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from aegntic
- 0.544score
council
aegntic
Run a 5-adviser council to stress-test any decision.
SkillCFreshness: C★ 12Claude Code +9 - 0.484score
ae-ltd-skill-builder
aegntic
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization.
SkillDFreshness: D★ 12Claude Code +9 - 0.484score
ae-proof-agent
aegntic
Diligence-grade product and technical analysis for the ae.ltd proof-agent concept, including comparison against Cursor and Omnara, MVP and production…
SkillDFreshness: D★ 12Claude Code +9 - 0.479score
ae-ltd-worktree-mesh
aegntic
Use when parallel branches are needed for feature work, hotfixes, or review fixes using git worktrees with minimal context switching.
SkillDFreshness: D★ 12Claude Code +9 - 0.479score
compound-engineering
aegntic
Orchestration layer that coordinates Debt-Sentinel, Red Team Tribunal, and Spec-Lock into unified workflows.
SkillDFreshness: D★ 12Claude Code +9 - 0.479score
ae-ltd-claude-template-switchboard
aegntic
Use when creating or upgrading CLAUDE.md instructions and selecting the right template baseline for repo size, architecture, and team constraints.
SkillDFreshness: D★ 12Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Avant-Garde Frontend Architect running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Avant-Garde Frontend Architect skill. Agent Mart. https://agentmart.dev/skills/aegntic-avant-garde-frontend-architect (last updated 2026-10-24)