- Home
- Skills
- Frontend & Web Apps
- frontend anti tech debt
Works with the AI Agents you already use
frontend anti tech debt
Enforce frontend architecture guardrails and minimize technical debt in React, Next.js, and Svelte apps.
Free
frontend anti tech debt
Example session with this skill installed
Audit the new login form in /components/auth/LoginForm.tsx for security and accessibility issues, then propose necessary fixes.
- Read your context and instructions
- Compiled the frontend anti tech
- Generated the UI component
I have inspected the login form and identified several high-severity issues related to server-side validation and ARIA labeling.
Frontend Quality Audit: LoginForm.tsx
| Category | Severity | Issue | Requirement |
|---|---|---|---|
| Security | CRITICAL | Password field lacks server-side length validation. | MUST enforce limits in Server Action. |
| Security | HIGH | Form submission lacks CSRF protection or origin verification. | SHOULD use Next.js headers/cookies validation. |
| Accessibility | HIGH | Input labels are missing for screen readers. | MUST use <label> or aria-labelledby. |
| Performance | MEDIUM | Entire form re-renders on every keystroke. | SHOULD optimize local state or use useDeferredValue. |
Recommended Fixes
// Proposed fix for accessibility and security validation
import { useFormStatus } from 'react-dom';
export function LoginForm({ action }: { action: (formData: FormData) => void }) {
return (
<form action={action} className="flex flex-col gap-4">
<div className="flex flex-col">
<label htmlFor="email" className="text-sm font-medium">Email Address</label>
<input
id="email"
name="email"
type="email"
required
className="border rounded p-2"
aria-required="true"
/>
</div>
<div className="flex flex-col">
<label htmlFor="password">Password</label>
<input
id="password"
name="password"
type="password"
minLength={8}
required
className="border rounded p-2"
/>
</div>
<SubmitButton />
</form>
);
}
function SubmitButton() {
const { pending } = useFormStatus();
return (
<button type="submit" disabled={pending}>
{pending ? 'Logging in...' : 'Login'}
</button>
);
}
Next steps
- Read
security.mdto implement the server-side validation logic in theloginaction. - Run
npm run lintto verify the new accessibility attributes. - Validate the fix with a production build test.
LoginForm.tsx
TSX · React component
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop shipping frontend features that break in production or balloon your technical debt. This skill enforces rigorous architecture and software quality guardrails for modern web stacks, ensuring every change is verifiable, secure, and maintainable. It eliminates the guesswork and "clever" code that leads to future refactoring nightmares.
What it does
- Enforces Guardrails for React, Next.js, Svelte, SvelteKit, and Astro projects to prevent architectural drift.
- Performs Audits across accessibility, security, and performance using specialized review checklists.
- Risk-Based Loading of relevant documentation for specific tasks like API endpoints, forms, or WebGL.
- Verifies Completion against a strict Definition of Done including typechecks, linting, and production build checks.
- Detects Anti-Patterns like unnecessary
useEffectusage, global state abuse, and unsafe client-side assumptions.
How it works
- Inspects your repository structure, framework versions, and existing conventions to align with your current architecture.
- Loads specific reference files (e.g.,
security.md,nextjs.md) based on the task risk profile before writing code. - Applies the Minimal Change Principle to solve problems with the smallest coherent surface area possible.
- Validates all changes against the project's Definition of Done before finalizing the task.
Frameworks & tools
Targeted at React 19+, Next.js, Svelte 5 (runes), SvelteKit 2, Astro, and TypeScript. Works with standard toolchains including Vitest, Playwright, and ESLint.
Why this beats prompting it yourself
Generic prompts often lead to "clever" but brittle abstractions and ignored edge cases. This skill forces a systematic inspection and reference-loading protocol that prioritizes official documentation and project-specific consistency over model hallucinations.
Use cases
- Security Audits to catch IDOR, XSS, and exposed secrets before they reach the main branch.
- Performance Profiling to fix hydration mismatches and unnecessary dependency weight in Next.js or Svelte apps.
- Feature Implementation that follows strict TypeScript, accessibility, and SEO requirements from the start.
- Architecture Reviews to ensure new modules respect existing boundaries and state management patterns.
Known limitations
Does not support legacy React (pre-18) or older Svelte versions effectively. Requires a clean project structure to perform repository inspection accurately.
Focuses on modern frameworks (React 19+, Svelte 5). Accuracy depends on project files being accessible for inspection. Not for legacy migrations.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 27 days ago
- Free with an Agensi account
Requires