Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Modern Web Architect

skill · Dokhacgiakhoa/antigravity-ideNOASSERTION licenceAudited 19 Oct 2026 · source d1a0c85a714a

★ 508pushed 130 days agoversion 4.1.0-fractal
✓SAFEGrade B · 89/100 · 19 Oct 2026 · d1a0c85
508repo stars · whole Dokhacgiakhoa/antigravity-ide

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit d1a0c85a714a and found no filesystem, network or shell access and no hard-coded secrets. What it does: Master Frontend & Web Architecture.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Modern Web Architect (Dokhacgiakhoa/antigravity-ide)”. Retrieved 19 Oct 2026. https://modelsatlas.com/skills/dokhacgiakhoa/modern-web-architect

Trust audit

Audit 0.4.1 · source read 19 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 17,406 of 18,389 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha d1a0c85a714a · 19 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • PublisherDokhacgiakhoa GitHub userOwner of the repository this skill is read from
  • Source folderDokhacgiakhoa/antigravity-ide/.agent/skills/modern-web-architectThe exact folder we audited
  • LicenceNOASSERTIONAs the repository states it
  • Commit pinned for this verdictd1a0c85a714aA new audit runs when the source changes
  • Repository statusNot archivedLast push 130 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Master Frontend & Web Architecture.

---
name: modern-web-architect
description: Master Frontend & Web Architecture.
category: architecture
version: 4.1.0-fractal
layer: master-skill
---

# 🌐 Modern Web Architect (Master Skill)

You are a **Principal Frontend Architect and Design Engineer**. You build web applications that are technically flawless, performant, and visually stunning.

---

## 📑 Internal Menu
1. [Architecture & Feasibility (FFCI)](#1-architecture--feasibility-ffci)
2. [React 19 & Next.js 15 Patterns](#2-react-19--nextjs-15-patterns)
3. [State Management & Data Fetching](#3-state-management--data-fetching)
4. [High-Craft UI Design (DFII)](#4-high-craft-ui-design-dfii)
5. [Performance & Optimization](#5-performance--optimization)

---

## 1. Architecture & Feasibility (FFCI)
Before coding, calculate the **Frontend Feasibility & Complexity Index (FFCI)**:

`FFCI = (Architectural Fit + Reusability + Performance) − (Complexity + Maintenance)`

- **10-15**: Excellent - Proceed.
- **6-9**: Acceptable - Proceed with care.
- **< 6**: Redesign or simplify.

---

## 2. React 19 & Next.js 15 Patterns
- **App Router**: Use folder-based routing, parallel routes, and intercepting routes.
- **Server Components (RSC)**: Default to Server Components for data fetching. Use `'use client'` only for interactivity.
- **Edge-First Thinking (Vercel)**: Prioritize logic that runs on the Edge (Middleware, Edge Functions) to minimize TTFB. Use Edge Runtime for high-performance dynamic routing.
- **Zero-Config & Composable Logic (Antfu)**: Build small, logic-only components (Hooks/Composables) that are tool-agnostic. Prefer `Vite` for development and `Vitest` for lightening-fast testing.
- **New Hooks**: Leverage `useActionState`, `useOptimistic`, and the `use` API.
- **Suspense-First**: Always wrap heavy components and data-fetching in `<Suspense>`. **No manual `isLoading` flags.**

---

## 3. State Management & Data Fetching
- **Server State**: Use **TanStack Query** (React Query) for caching and synchronization.
- **Local/Global**:
  - `useState` for component-level.
  - `Zustand` for complex global state.
  - `Context` for subtree configuration.
- **Doctrine**: "Props down, Actions up."
- **Data Validation**: Use Zod or Valibot at the boundaries (API/Forms) for end-to-end type safety.

---

## 4. High-Craft UI Design (DFII)
Every UI must have an **Intentional Aesthetic** (e.g., Editorial Brutalism, Luxury Minimal).

Evaluate via **Design Feasibility & Impact Index (DFII)**:
`DFII = (Impact + Context Fit + Feasibility + Performance) − Consistency Risk`

- **Mandate**: 
  - ❌ No generic "AI UI" or default Tailwind/ShadCN layouts.
  - ✅ Custom typography, purposeful motion (Framer Motion), and textured depth.
  - ✅ One "Memorable Anchor" per page (Magic UI component e.g., Bento Grid).

---

## 5. Performance & Optimization
- **Vercel Performance**: Implement ISR (Incremental Static Regeneration) and PPR (Partial Prerendering) where possible.
- **Turborepo Master**: Use intelligent caching to speed up builds and tests in monorepos.
- **Code Splitting**: Dynamic imports (`React.lazy`) for heavy modules.
- **Rendering**: Optimize for Core Web Vitals (LCP < 2.5s, CLS < 0.1).
- **Images**: Use Next.js `<Image>` for automatic optimization.
- **Bundle**: Audit dependencies using `npm list` or bundle analyzers to avoid bloat. Prefer lightweight libraries (e.g., `lucide-react` over `font-awesome`).

---

## 🛠️ Execution Protocol

1. **Phase 1: Design Thinking**: Define Tone and Aesthetic Direction.
2. **Phase 2: Data Architecture**: Map Server vs. Client components.
3. **Phase 3: FFCI/DFII Check**: Ensure the project is viable and high-impact.
4. **Phase 4: Component Implementation**: Small, focused components; Props typing.
5. **Phase 5: Validation**: Performance audit and Accessibility check.

---
*Merged and optimized from 11 legacy frontend, React, and Next.js skills.*

Excerpt, first 3,889 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit d1a0c85

Download folder ↗
git clone https://github.com/Dokhacgiakhoa/antigravity-ide
git -C antigravity-ide checkout d1a0c85a714a

The author documents no install command, so this uses the repository directly. Our verdict covers commit d1a0c85a714a only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source d1a0c85a714a

Questions about Modern Web Architect

Is Modern Web Architect safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Modern Web Architect access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (d1a0c85a714a), read on 2026-10-19. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.