### Example /create Workflow Session
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/create/page.mdx
This example demonstrates an interactive session using the /create command, showing user input and agent responses during application setup.
```bash
/create todo app with dark mode
```
```agent
**Analyzing request...**
Tech Stack: Next.js + Tailwind + Zustand
Proceed? (Y/N)
```
```user
Y
```
```agent
**🚀 App Created!**
Preview: http://localhost:3000
```
--------------------------------
### Start Local Development Server
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/preview/page.mdx
Use this command to launch your local development server. Ensure you have the necessary environment setup.
```bash
/preview start
```
--------------------------------
### Example Planning Session
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/plan/page.mdx
This example demonstrates a typical interaction with the `/plan` workflow, including user input, agent clarifying questions, and the final plan confirmation.
```bash
/plan SaaS dashboard with analytics
```
```bash
Users + revenue, real-time, Recharts
```
--------------------------------
### Example Preview Session Output
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/preview/page.mdx
This block shows the typical output when starting the preview server, including confirmation messages, port details, and the readiness status with the development server URL.
```text
**🚀 Starting preview...**
Port: 3000
Type: Next.js
```
```text
**✅ Preview ready!**
URL: http://localhost:3000
```
--------------------------------
### Global Install and Init CLI Commands
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/README.md
Alternatively, install the CLI globally and then run the init command. This makes the `ag-kit` command available system-wide.
```bash
npm install -g @vudovn/ag-kit
ag-kit init
```
--------------------------------
### Terminal Session Example
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/test/page.mdx
Example output showing the interaction flow for generating tests for a specific service file.
```text
/test src/services/auth.ts
**Analyzing auth.ts...**
Found 4 functions: login, register, verifyToken, resetPassword
**✅ Tests Generated!**
Created: `tests/auth.test.ts`
Test cases: 12
Coverage: 95%
```
--------------------------------
### Install Antigravity Kit via CLI
Source: https://context7.com/vudovn/antigravity-kit/llms.txt
Use these commands to initialize the .agent folder or manage the toolkit installation.
```bash
# Quick install with npx
npx @vudovn/ag-kit init
# Or install globally
npm install -g @vudovn/ag-kit
ag-kit init
# Install with options
ag-kit init --force # Overwrite existing .agent folder
ag-kit init --path ./myapp # Install in specific directory
ag-kit init --branch dev # Use specific branch
ag-kit init --quiet # Suppress output (for CI/CD)
ag-kit init --dry-run # Preview actions without executing
# Check installation status
ag-kit status
# Update to latest version
ag-kit update
```
--------------------------------
### Initiate App Creation with /create
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/create/page.mdx
Use the /create command followed by a description of your desired application to start the AI-powered creation process.
```bash
/create e-commerce site with product listing and cart
```
--------------------------------
### Quick Install CLI Command
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/README.md
Use this command to quickly initialize the Antigravity Kit in your project.
```bash
npx @vudovn/ag-kit init
```
--------------------------------
### Example Brainstorming Session
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/brainstorm/page.mdx
This example demonstrates a typical interaction with the /brainstorm command, showing user input, agent exploration, presented options with pros and cons, and a final recommendation.
```bash
/brainstorm state management for complex form
```
--------------------------------
### Example Agent Session with /orchestrate
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/orchestration/page.mdx
This example demonstrates a typical session where the orchestrator activates specialist agents and assigns tasks. It shows the user command, agent responses, and task progress.
```bash
/orchestrate Build E-commerce MVP
```
```text
**Activating Squad...**
Assigning tasks based on `PLAN.md`:
```
```text
**Backend-Specialist:** Configuring Prisma Schema...
```
```text
**Frontend-Specialist:** Building ProductCard component...
```
```text
**Security-Auditor:** Reviewing auth flow...
```
```text
**✅ Project Complete!**
All tasks finished. Run `npm run dev` to start.
```
--------------------------------
### Initiate Project Planning
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/plan/page.mdx
Use the `/plan` command to start the planning-only mode. Describe the project you want to build to initiate the process.
```bash
/plan e-commerce site with cart and checkout
```
--------------------------------
### Example UI/UX Pro-Max Session
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/ui-design/page.mdx
This terminal output shows an example interaction with the /ui-ux-pro-max workflow, from user input to agent response and completion confirmation.
```terminal
user> /ui-ux-pro-max Create a friendly pet grooming service landing page with claymorphism cards, service packages, pet gallery, booking system, and testimonials from pet owners. Use playful warm colors
agent> **Analyzing Style...**
Loading "Modern SaaS"...
🎨 Colors: Indigo-500 primary, Slate-900 bg
✨ Effects: Glassmorphism cards
agent> **✅ Page Complete!**
Created `app/page.tsx`
Run `/preview start` to view.
```
--------------------------------
### Workflow Invocation Examples
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/README.md
Examples of how to invoke workflows using slash commands for various tasks like brainstorming, creation, debugging, and deployment.
```text
/brainstorm authentication system
/create landing page with hero section
/debug why login fails
```
--------------------------------
### Example Deployment Session Output
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/deployment/page.mdx
This output demonstrates a successful production deployment session. It shows the agent running pre-flight checks, confirming all passed, and then completing the deployment to Vercel.
```text
**Running Pre-Flight Checks...**
🔄 Security Scan... PASSED
🔄 Lint Check... PASSED
🔄 Type Validation... PASSED
✅ All checks passed!
Deploying to Vercel...
**🚀 Deployment Complete!**
🌐 URL: https://my-app.vercel.app
💚 Health Check: OK
```
--------------------------------
### Initialize Antigravity Kit
Source: https://github.com/vudovn/antigravity-kit/blob/main/README.md
Commands to initialize the kit in a project, either via npx or global installation.
```bash
npx @vudovn/ag-kit init
```
```bash
npm install -g @vudovn/ag-kit
ag-kit init
```
--------------------------------
### Initiate Brainstorming Workflow
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/brainstorm/page.mdx
Use the /brainstorm command to start exploring different approaches for your challenge. Be specific about constraints.
```bash
/brainstorm authentication system for my SaaS app
```
--------------------------------
### Initiate Debugging Workflow
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/debugging/page.mdx
Use the /debug command to start the investigation process for a specific issue.
```bash
/debug Login returns 403 even with correct credentials
```
--------------------------------
### Agent Interaction Examples
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/README.md
Demonstrates how the AI automatically detects and applies specialist agents based on user requests. No explicit agent mention is required.
```text
You: "Add JWT authentication"
AI: 🤖 Applying @security-auditor + @backend-specialist...
You: "Fix the dark mode button"
AI: 🤖 Using @frontend-specialist...
You: "Login returns 500 error"
AI: 🤖 Using @debugger for systematic analysis...
```
--------------------------------
### Multi-Agent Orchestration Example
Source: https://context7.com/vudovn/antigravity-kit/llms.txt
Initiate complex task coordination by using the /orchestrate command. The orchestrator decomposes tasks, assigns agents, and manages execution.
```bash
/orchestrate build a full-stack e-commerce app
```
--------------------------------
### Terminal Session Output
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/status/page.mdx
Example output showing project statistics, agent progress, and preview health status.
```jsx
/status
=== Project Status ===
📁 Project: my-ecommerce
🏷️ Type: nextjs-ecommerce
📄 Files: 73 created, 12 modified
=== Agent Status ===
✅ database-architect → Completed
✅ backend-specialist → Completed
🔄 frontend-specialist → 60%
=== Preview ===
🌐 URL: http://localhost:3000
💚 Health: OK
```
--------------------------------
### Execute Dark Mode Enhancement Session
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/new-feature/page.mdx
Example terminal interaction showing the /enhance workflow for adding a dark mode toggle.
```text
/enhance add dark mode toggle
**Analyzing codebase...**
Found: Tailwind CSS with no dark mode config
Plan: Update tailwind.config, add ThemeProvider, create toggle component
Frontend: Creating ThemeToggle...
Testing: Adding theme tests...
**✅ Feature Added!**
Run `/preview start` to test.
```
--------------------------------
### Agent Auto-Selection Examples
Source: https://context7.com/vudovn/antigravity-kit/llms.txt
The system automatically selects appropriate agents based on user input. No manual agent invocation is required.
```text
# Automatic agent selection examples
User: "Add JWT authentication"
AI: Applying @security-auditor + @backend-specialist...
User: "Fix the dark mode button"
AI: Using @frontend-specialist...
User: "Login returns 500 error"
AI: Using @debugger for systematic analysis...
User: "Optimize database queries"
AI: Using @database-architect...
User: "Deploy to AWS"
AI: Using @devops-engineer...
# Available agents (20 total):
# - orchestrator: Multi-agent coordination
# - project-planner: Discovery, task planning
# - frontend-specialist: Web UI/UX, React/Next.js
# - backend-specialist: API, business logic
# - database-architect: Schema, SQL, Prisma
# - mobile-developer: iOS, Android, React Native
# - game-developer: Game logic, Unity, Godot
# - devops-engineer: CI/CD, Docker, deployment
# - security-auditor: Security compliance, OWASP
# - penetration-tester: Offensive security
# - test-engineer: Testing strategies, E2E
# - debugger: Root cause analysis
# - performance-optimizer: Speed, Web Vitals
# - seo-specialist: Ranking, visibility
# - documentation-writer: Manuals, docs
# - product-manager: Requirements, user stories
# - product-owner: Strategy, backlog, MVP
# - qa-automation-engineer: E2E testing, CI pipelines
# - code-archaeologist: Legacy code, refactoring
# - explorer-agent: Codebase analysis
```
--------------------------------
### Debug Session Terminal Output
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/debugging/page.mdx
Example of a terminal interaction showing the progression through the discovery, hypothesis, and resolution phases.
```text
/debug Form submission fails silently
**Phase 1: Discovery**
Reading `CheckoutForm.tsx`... Found `handleSubmit`.
ERROR: Cannot read properties of undefined
**Phase 2: Hypothesis**
1. `emailRef.current` is null on mount
2. Event handler not bound correctly
**Phase 4: Resolution**
Fix applied: Added null check to `emailRef`.
✅ Test passed: Form submits successfully.
```
--------------------------------
### Test Generation Pattern (Arrange-Act-Assert)
Source: https://context7.com/vudovn/antigravity-kit/llms.txt
Generate tests using the Arrange-Act-Assert pattern. This example demonstrates testing an AuthService login function, including valid credentials and invalid password scenarios.
```typescript
// Test structure generated by /test workflow
describe('AuthService', () => {
describe('login', () => {
it('should return token for valid credentials', async () => {
// Arrange
const credentials = { email: 'test@test.com', password: 'pass123' };
// Act
const result = await authService.login(credentials);
// Assert
expect(result.token).toBeDefined();
});
it('should throw for invalid password', async () => {
// Arrange
const credentials = { email: 'test@test.com', password: 'wrong' };
// Act & Assert
await expect(authService.login(credentials)).rejects.toThrow('Invalid credentials');
});
});
});
// Usage:
// /test src/services/auth.service.ts
// /test user registration flow
// /test coverage
```
--------------------------------
### Scaffold New Projects with App Builder Templates
Source: https://context7.com/vudovn/antigravity-kit/llms.txt
Use the /create workflow to scaffold new projects using pre-configured templates. The AI reads the template's README to set up the project.
```bash
/create landing page with hero section
```
```bash
/create mobile app for todo tracking
```
--------------------------------
### CLI Init Command Options
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/README.md
Shows various options for the `ag-kit init` command, including forcing overwrite, specifying a path, using a specific branch, running quietly, and performing a dry run.
```bash
ag-kit init --force # Overwrite existing .agent folder
ag-kit init --path ./myapp # Install in specific directory
ag-kit init --branch dev # Use specific branch
ag-kit init --quiet # Suppress output (for CI/CD)
ag-kit init --dry-run # Preview actions without executing
```
--------------------------------
### Run UI/UX Pro-Max Workflow
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/ui-design/page.mdx
Use this command to generate a landing page. Provide a style prompt and content requirements for the AI.
```bash
/ui-ux-pro-max Create a friendly pet grooming service landing page with claymorphism cards,
service packages, pet gallery, booking system, and testimonials from pet owners.
Use playful warm colors.
```
--------------------------------
### Check Dependencies with Python
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/new-feature/page.mdx
Run the provided checklist script to monitor bundle size and prevent bloat.
```bash
checklist.py
```
--------------------------------
### Initiate Project with /orchestrate
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/orchestration/page.mdx
Use the /orchestrate command to define the high-level goal of your project. The orchestrator will then clarify requirements.
```bash
/orchestrate Build a "Course Platform" MVP with:
- User Authentication (NextAuth)
- Stripe Payments
- Video Hosting (Mux)
- Dashboard for Instructors
```
--------------------------------
### Run Full Verification Script
Source: https://github.com/vudovn/antigravity-kit/blob/main/AGENT_FLOW.md
Execute the full verification script for pre-deployment checks. This script includes all quick checks plus additional audits and tests.
```bash
python .agent/scripts/verify_all.py .
--url http://localhost:3000
```
--------------------------------
### Stack-Specific Guidelines for Design Systems
Source: https://context7.com/vudovn/antigravity-kit/llms.txt
Generate guidelines tailored to specific technology stacks. The default stack is html-tailwind.
```bash
python3 .agent/.shared/ui-ux-pro-max/scripts/search.py "layout responsive" --stack html-tailwind
```
```bash
python3 .agent/.shared/ui-ux-pro-max/scripts/search.py "state hooks" --stack react
```
```bash
python3 .agent/.shared/ui-ux-pro-max/scripts/search.py "ssr routing" --stack nextjs
```
```bash
python3 .agent/.shared/ui-ux-pro-max/scripts/search.py "composables state" --stack vue
```
--------------------------------
### Execute All Tests
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/test/page.mdx
Run the entire test suite using the base command.
```bash
/test
```
--------------------------------
### Execute Production Deployment
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/deployment/page.mdx
Trigger the production deployment pipeline. This command initiates the pre-flight checklist and subsequent deployment if all checks pass.
```bash
/deploy
```
--------------------------------
### Run Project Status Command
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/status/page.mdx
Execute the status command to trigger the project dashboard view.
```bash
/status
```
--------------------------------
### Generate UI/UX Pro Max Design System
Source: https://context7.com/vudovn/antigravity-kit/llms.txt
Use this command to generate a complete design system for a given service. Specify the output format with the -f flag.
```bash
python3 .agent/.shared/ui-ux-pro-max/scripts/search.py "beauty spa wellness service" --design-system -p "Serenity Spa"
```
```bash
python3 .agent/.shared/ui-ux-pro-max/scripts/search.py "fintech crypto" --design-system --persist -p "CryptoWallet"
```
```bash
python3 .agent/.shared/ui-ux-pro-max/scripts/search.py "dashboard analytics" --design-system --persist -p "CryptoWallet" --page "dashboard"
```
```bash
python3 .agent/.shared/ui-ux-pro-max/scripts/search.py "fintech" --design-system # ASCII box (default)
```
```bash
python3 .agent/.shared/ui-ux-pro-max/scripts/search.py "fintech" --design-system -f markdown # Markdown
```
--------------------------------
### Initiate Feature Enhancement
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/new-feature/page.mdx
Use the /enhance command to specify requirements for new functionality.
```bash
/enhance Add an analytics dashboard for user activity
Requirements:
- Track daily active users and page views
- Visual charts using Recharts
- API endpoint to aggregate data
```
--------------------------------
### Check Local Development Server Status
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/preview/page.mdx
Run this command to verify if your local development server is running and accessible. It provides a quick health check.
```bash
/preview
```
--------------------------------
### Run Validation Scripts
Source: https://context7.com/vudovn/antigravity-kit/llms.txt
Execute these scripts to perform security, quality, and performance audits on your project.
```bash
# Quick validation during development (Core checks)
python .agent/scripts/checklist.py .
# Full verification before deployment
python .agent/scripts/verify_all.py . --url http://localhost:3000
# Core checks include:
# - P0: Security Scan (vulnerabilities, secrets)
# - P1: Lint & Type Check (code quality)
# - P2: Schema Validation (if database exists)
# - P3: Test Runner (unit/integration tests)
# - P4: UX Audit (psychology laws, accessibility)
# - P5: SEO Check (meta tags, structure)
# - P6: Performance (lighthouse - requires URL)
```
--------------------------------
### Run Checklist Script
Source: https://github.com/vudovn/antigravity-kit/blob/main/AGENT_FLOW.md
Execute the checklist script for quick development checks. This script performs various scans and validations.
```bash
python .agent/scripts/checklist.py .
```
--------------------------------
### Antigravity Kit Directory Structure
Source: https://context7.com/vudovn/antigravity-kit/llms.txt
The `.agent` folder structure for extending AI capabilities. It includes directories for agents, skills, workflows, rules, and scripts.
```plaintext
.agent/
├── ARCHITECTURE.md # System architecture documentation
├── agents/ # 20 Specialist Agent definitions
│ ├── orchestrator.md # Multi-agent coordination
│ ├── frontend-specialist.md
│ ├── backend-specialist.md
│ ├── database-architect.md
│ ├── security-auditor.md
│ ├── test-engineer.md
│ └── ... (14 more agents)
├── skills/ # 36 Domain-specific skills
│ ├── api-patterns/
│ │ ├── SKILL.md # Main instructions
│ │ ├── rest.md
│ │ ├── graphql.md
│ │ └── scripts/ # Validation scripts
│ ├── app-builder/
│ │ ├── SKILL.md
│ │ └── templates/ # 13 project templates
│ ├── ui-ux-pro-max/ # Design system skill
│ └── ... (33 more skills)
├── workflows/ # 11 Slash command procedures
│ ├── brainstorm.md
│ ├── create.md
│ ├── debug.md
│ ├── deploy.md
│ ├── test.md
│ └── ... (6 more workflows)
├── rules/ # Global rules
└── scripts/ # Master validation scripts
├── checklist.py # Quick validation
└── verify_all.py # Full verification
```
--------------------------------
### Generate Tests for a Specific File
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/test/page.mdx
Target a specific file to generate corresponding test suites.
```bash
/test src/auth.ts
```
--------------------------------
### Rollback to Previous Version
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/deployment/page.mdx
Instantly revert to the last stable version of the application using the 'rollback' subcommand. This is a safety measure for quickly undoing recent deployments.
```bash
/deploy rollback
```
--------------------------------
### Domain-Specific Searches for Design Systems
Source: https://context7.com/vudovn/antigravity-kit/llms.txt
Perform domain-specific searches to find relevant design elements. Available domains include style, chart, ux, typography, and landing.
```bash
python3 .agent/.shared/ui-ux-pro-max/scripts/search.py "glassmorphism dark" --domain style
```
```bash
python3 .agent/.shared/ui-ux-pro-max/scripts/search.py "real-time dashboard" --domain chart
```
```bash
python3 .agent/.shared/ui-ux-pro-max/scripts/search.py "animation accessibility" --domain ux
```
```bash
python3 .agent/.shared/ui-ux-pro-max/scripts/search.py "elegant luxury" --domain typography
```
```bash
python3 .agent/.shared/ui-ux-pro-max/scripts/search.py "hero social-proof" --domain landing
```
--------------------------------
### Check Test Coverage
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/test/page.mdx
Generate a report on current test coverage.
```bash
/test coverage
```
--------------------------------
### Invoke Workflow Slash Commands
Source: https://context7.com/vudovn/antigravity-kit/llms.txt
Execute structured development procedures by using slash commands in your AI-powered IDE.
```bash
# Application creation workflow
/create blog site
/create e-commerce app with product listing and cart
/create Instagram clone
# Debugging workflow
/debug login not working
/debug API returns 500
/debug form doesn't submit
# Testing workflow
/test src/services/auth.service.ts
/test user registration flow
/test coverage
# Deployment workflow
/deploy # Interactive deployment wizard
/deploy check # Run pre-deployment checks only
/deploy preview # Deploy to preview/staging
/deploy production # Deploy to production
/deploy rollback # Rollback to previous version
# Planning and brainstorming
/brainstorm authentication system
/plan large-scale refactoring
/orchestrate full-stack e-commerce build
# Preview and status
/preview # Preview changes locally
/status # Check project status
# UI/UX Design
/ui-ux-pro-max # Design with 50+ styles, 97 color palettes
```
--------------------------------
### Stop Local Development Server
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/preview/page.mdx
Use this command to gracefully shut down your local development server. This is useful for freeing up resources or before making significant changes.
```bash
/preview stop
```
--------------------------------
### Dry-run Deployment Checks
Source: https://github.com/vudovn/antigravity-kit/blob/main/web/src/app/docs/guide/examples/deployment/page.mdx
Use the 'check' subcommand to perform a dry-run of the pre-flight validations without initiating a deployment. This is useful for verifying code health before a full deployment.
```bash
/deploy check
```
--------------------------------
### Debug Workflow Output Format
Source: https://context7.com/vudovn/antigravity-kit/llms.txt
Use this markdown format for structured problem investigation in debug workflows. It outlines symptoms, gathered information, hypotheses, investigation steps, root cause, fix, and prevention.
```markdown
## Debug: [Issue]
### 1. Symptom
[What's happening]
### 2. Information Gathered
- Error: `[error message]`
- File: `[filepath]`
- Line: [line number]
### 3. Hypotheses
1. [Most likely cause]
2. [Second possibility]
3. [Less likely cause]
### 4. Investigation
**Testing hypothesis 1:**
[What I checked] -> [Result]
### 5. Root Cause
[Explanation of why this happened]
### 6. Fix
```typescript
// Before
[broken code]
// After
[fixed code]
```
### 7. Prevention
[How to prevent this in the future]
```
=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.