Works with the AI Agents you already use
ungptify
A professional security checklist and minimal UI framework for production-grade web applications and infrastructure.
$10
ungptify
Example session with this skill installed
Review this Node.js login route for security flaws and refactor the UI component to remove the "AI look" like oversized corners and gradients.
- Read your context and instructions
- Compiled the ungptify
I have audited the authentication route and refactored the UI to meet production security and design standards. The backend now uses Argon2id for hashing and implements strict HSTS headers. The UI has been stripped of decorative gradients and 32px border radii in favor of a 248px fixed sidebar and 8px container rounding.
Security Audit & UI Refactor
| Component | Security Status | Fix Applied |
|---|---|---|
| Password Storage | Vulnerable (SHA1) | Migrated to argon2 with high memory/time cost settings. |
| Session Management | Insecure | Added HttpOnly, Secure, and SameSite=Strict flags to cookies. |
| Input Validation | Missing | Implemented schema validation for email and password fields. |
| UI: Sidebar | Floating/Rounded | Converted to 248px fixed width with 1px solid border-right. |
| UI: Buttons | Gradient/Pill | Changed to solid brand fill with 8px border-radius. |
| Headers | Missing CSP | Added Content-Security-Policy: default-src 'self'. |
// Hardened Auth Route
const argon2 = require('argon2');
const express = require('express');
const router = express.Router();
router.post('/login', async (req, res) => {
const { email, password } = req.body;
// Generic error to prevent user enumeration
const genericError = "Invalid credentials.";
try {
const user = await db.users.findUnique({ where: { email } });
if (!user) return res.status(401).json({ error: genericError });
const valid = await argon2.verify(user.passwordHash, password);
if (!valid) return res.status(401).json({ error: genericError });
req.session.userId = user.id;
res.setHeader('Set-Cookie', 'session_id=...; HttpOnly; Secure; SameSite=Strict');
res.json({ success: true });
} catch (err) {
console.error(err);
res.status(500).json({ error: "Internal server error" });
}
});
Next steps
- Run
npm auditto check for supply chain vulnerabilities in current dependencies. - Configure
AWS Secrets Managerto move the database URI out of the.envfile. - Update the CSP header to include specific trusted origins for external assets.
Connects securely to your tools. The creator never sees your data.
About this skill
Writing secure, professional code requires more than just functional logic. This package provides a rigorous framework for implementing production-grade security standards and clean, functional UI components. It eliminates common AI design tropes like oversized rounded corners and decorative gradients while enforcing strict security protocols across the entire stack.
What it does
- Security hardening applies OWASP Top 10 protections, including SQL injection prevention via ORM bind variables and parameterization.
- Authentication logic enforces Argon2id/bcrypt hashing, MFA via TOTP, and secure session management with HttpOnly/SameSite flags.
- Infrastructure security provides checklists for container hardening, Kubernetes resource limits, and IaC scanning with tools like Checkov.
- Production UI design generates clean, high-density layouts modeled after Stripe and GitHub, avoiding "AI-aesthetic" clutter.
- Supply chain protection manages dependency integrity via lockfile pinning and SBOM maintenance.
How it works
- Audit existing code against the 15-point security checklist to identify vulnerabilities in auth, logging, or input handling.
- Apply UI constraints to frontend components to remove decorative bloat and enforce system-font-based hierarchy.
- Configure headers for transport security using HSTS, CSP, and X-Frame-Options: DENY.
- Harden deployments using non-root Docker configurations and VPC private subnets for backend services.
Frameworks & tools
Works with any stack including React, Node.js, Python, and Go. Supports infrastructure tools like Docker, Kubernetes, Terraform, AWS, and Azure.
Why this beats prompting it yourself
Generic prompts often produce insecure code and "Codex-style" UI with soft gradients and floating panels. This skill forces the agent to follow professional engineering standards and minimal design patterns used by top-tier tech companies.
Use cases
- Hardening an Express or FastAPI backend before a production release.
- Converting a cluttered, over-designed dashboard into a high-density professional interface.
- Setting up a secure CI/CD pipeline with OIDC and dependency scanning.
- Implementing Row-Level Security and encrypted backups for sensitive PII databases.
Known limitations
Does not perform automated live penetration testing or real-time traffic monitoring. Requires manual integration of recommended security libraries and cloud configurations.
What's included (2 skills)
secure-code
Ui
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scanned
Verified clean today
- Passed all security checks, Safe to install
Requires