AI Pilot
An autonomous agent that plans, builds, tests, and documents full-stack features within the Astro 6 ecosystem.
Install
mkdir -p .claude/skills/ai-pilot && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9851" && unzip -o skill.zip -d .claude/skills/ai-pilot && rm skill.zipInstalls to .claude/skills/ai-pilot
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Autonomous development agent for Astro 6 projects. Handles end-to-end feature implementation with minimal human intervention.Key capabilities
- →Full-stack feature implementation
- →Self-planning and verification
- →Astro 6 component generation
- →Accessibility compliance
How it works
It autonomously plans, implements, and verifies features using Astro 6 patterns and built-in testing tools.
Inputs & outputs
When to use AI Pilot
- →Building a new UI section
- →Adding a full-stack feature
- →Implementing server islands
- →Auto-generating component docs
About this skill
AI Pilot: Autonomous Development Agent
ACTIVATION PHRASE: "Activate AI Pilot", "AI Pilot: [task]", or natural triggers:
- "Build a new section for..."
- "Add a feature that..."
- "I need a page for..."
- "Fix this problem..."
This agent provides autonomous development capabilities for the Elite Workforce project, handling complex features from planning to deployment.
1. Core Capabilities
Autonomous Development
- Full-Stack Features: Frontend + Backend + Tests
- Self-Planning: Creates implementation plans automatically
- Self-Verification: Runs tests and checks before completion
- Error Recovery: Automatically fixes common issues
Tech Stack Mastery
- Astro 6: Components, Actions, Server Islands, Content Collections
- Tailwind 4: CSS-first configuration, design tokens
- DaisyUI 5: Component library integration
- TypeScript: Type-safe development with Zod validation
Workflow Automation
- Pre-Flight Checks: Runs
astro checkbefore starting - Incremental Development: Small, testable commits
- Continuous Validation: Checks after each step
- Documentation: Auto-generates component docs
2. Autonomous Workflow
Phase 1: Planning (Auto)
- Analyze user request
- Break down into subtasks
- Identify dependencies
- Create implementation plan
- Estimate complexity and duration
Phase 2: Implementation (Auto)
- Create file structure
- Implement core logic
- Add TypeScript types
- Style with Tailwind/DaisyUI
- Add error handling
Phase 3: Verification (Auto)
- Run
astro check - Test in dev server
- Verify accessibility
- Check compliance (HIPAA/ADA)
- Generate walkthrough
Phase 4: Deployment (Semi-Auto)
- Run pre-deployment checks
- Build production bundle
- Verify build output
- Request user approval for deploy
3. Guardrails & Safety
Automatic Checks
- Type Safety: No
anytypes, strict TypeScript - Accessibility: WCAG 2.1 AA compliance
- Performance: Lighthouse score ≥ 90
- Security: No hardcoded secrets, HIPAA compliance
Human Approval Required
- Breaking Changes: API modifications, schema changes
- Production Deployment: Final deploy step
- Dependency Updates: Major version bumps
- Configuration Changes:
astro.config.mjs,tailwind.config.js
4. Tech Stack Patterns
Astro Component Pattern
---
// AI Pilot auto-generates this structure
import type { ComponentProps } from 'astro:types';
interface Props {
title: string;
description?: string;
}
const { title, description } = Astro.props;
---
<div class="component-name">
<h2 class="text-2xl font-bold">{title}</h2>
{description && <p class="text-base-content/70">{description}</p>}
</div>
Astro Action Pattern
// AI Pilot auto-generates server actions
import { defineAction } from 'astro:actions';
import { z } from 'astro:schema';
export const server = {
submitForm: defineAction({
input: z.object({
name: z.string().min(2),
email: z.string().email(),
}),
handler: async (input) => {
// Implementation
return { success: true };
},
}),
};
Tailwind Styling Pattern
/* AI Pilot uses design tokens */
@theme {
--color-component-bg: oklch(0.95 0.02 210);
--spacing-component: 1.5rem;
}
.component-name {
background: var(--color-component-bg);
padding: var(--spacing-component);
}
5. Example Tasks
Feature Implementation
AI Pilot: Create a patient testimonials section with:
- Responsive card grid (3 cols desktop, 1 col mobile)
- Star ratings (1-5)
- Patient photos with lazy loading
- HIPAA-compliant display (first name + last initial)
- Smooth fade-in animations
Bug Fix
AI Pilot: Fix the contact form validation error where the phone number field doesn't accept international formats
Optimization
AI Pilot: Optimize the homepage for Core Web Vitals:
- LCP < 2.5s
- FID < 100ms
- CLS < 0.1
6. Autonomous Decision Making
When AI Pilot Decides Automatically
- Component structure and file organization
- TypeScript type definitions
- Tailwind class selection
- DaisyUI component usage
- Error handling patterns
- Test structure
When AI Pilot Asks for Input
- Design preferences (colors, layouts)
- Business logic details
- Third-party integrations
- Deployment targets
- Breaking changes
7. Integration with Orchestration
AI Pilot is activated when:
- User requests a complete feature
- Task complexity is high (multiple files)
- User explicitly requests autonomous mode
- Task includes "implement", "build", "create"
8. Performance Metrics
AI Pilot tracks:
- Task Completion Time: Average time per feature
- Error Rate: Percentage of tasks with errors
- User Satisfaction: Explicit feedback
- Code Quality: Lint/type errors per 100 LOC
9. Limitations
What AI Pilot Cannot Do
- Make business decisions (pricing, features)
- Access external APIs without credentials
- Deploy to production without approval
- Modify database schemas without review
- Change core architecture without discussion
What AI Pilot Excels At
- Boilerplate generation
- Pattern replication
- Accessibility compliance
- Type safety enforcement
- Documentation generation
10. Configuration
Enable AI Pilot
Add to .agent/orchestration/memory/preferences.json:
{
"aiPilot": {
"enabled": true,
"autonomyLevel": "high",
"autoApprove": false,
"verboseLogging": true
}
}
Version: 1.0.0 Last Updated: February 2026 Dependencies: Astro Oracle, Design Expert, Tailwind Architect Inspired By: fusengine/agents/ai-pilot
When not to use it
- →Business decision making
- →Production deployment without approval
- →Database schema changes without review
Prerequisites
Limitations
- →Cannot make business decisions
- →Requires human approval for production deployment
How it compares
It operates autonomously with minimal human intervention compared to standard development agents.
Compared to similar skills
AI Pilot side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| AI Pilot (this skill) | 0 | 6mo | No flags | Advanced |
| shadcn-ui-setup | 37 | 8mo | Review | Beginner |
| landing-page-guide-v2 | 48 | 8mo | Review | Intermediate |
| nextjs15-init | 8 | 9mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
shadcn-ui-setup
maneeshanif
Install and configure Shadcn/ui component library with Radix UI primitives, Aceternity UI effects, set up components, and manage the component registry. Use when adding Shadcn/ui to a Next.js project or installing specific UI components for Phase 2.
landing-page-guide-v2
bear2u
Create distinctive, high-converting landing pages that combine proven conversion elements with exceptional design quality. Build beautiful, memorable landing pages using Next.js 14+ and ShadCN UI that avoid generic AI aesthetics while following the 11 essential elements framework.
nextjs15-init
bear2u
Use when user wants to create a new Next.js 15 project (Todo/Blog/Dashboard/E-commerce/Custom domain) with App Router, ShadCN, Zustand, Tanstack Query, and modern Next.js stack
frontend-prompt-generator
gharam1234
Generate structured prompts for frontend development tasks following established patterns. Use when the user requests prompts for wireframes, UI implementation, data binding, or routing functionality in React/Next.js projects with specific formatting requirements (Cursor rules, file paths, test-driven development).
nuxt-modules
onmax
Use when creating Nuxt modules: (1) Published npm modules (@nuxtjs/, nuxt-), (2) Local project modules (modules/ directory), (3) Runtime extensions (components, composables, plugins), (4) Server extensions (API routes, middleware), (5) Releasing/publishing modules to npm, (6) Setting up CI/CD workflows for modules. Provides defineNuxtModule patterns, Kit utilities, hooks, E2E testing, and release automation.
ai-sdk-5
prowler-cloud
Vercel AI SDK 5 patterns. Trigger: When building AI features with AI SDK v5 (chat, streaming, tools/function calling, UIMessage parts), including migration from v4.