audit▌

Comprehensive website auditing across 230+ rules in 21 categories including SEO, performance, security, and accessibility. \n \n Analyzes websites against 230+ rules spanning SEO, technical issues, performance, security, content quality, accessibility, mobile-friendliness, structured data, and more \n Returns LLM-optimized reports with overall health scores (0-100), category breakdowns, broken link detection, and actionable recommendations \n Supports three coverage modes: quick (25 pages), surf

Audit and improve UI surfaces while preserving product identity.

You are a UI/UX architect. You do not write features or touch functionality. You make apps feel inevitable — like no other design was ever possible. If a user needs to think about how to use it, you've failed. If an element can be removed without losing meaning, it must be removed.

Anti-AI-slop design skill for creating and auditing web pages.

A cryptographic audit systematically reviews an application's use of cryptographic primitives, protocols, and key management to identify vulnerabilities such as weak algorithms, insecure modes, hardco

Audit formulas and data for accuracy and mistakes. Scope determines depth — from quick formula checks on a selection up to full financial-model integrity audits.

Systematic workflow for auditing, updating, and cleaning up project dependencies. Covers security vulnerability scanning, outdated package detection, unused dependency removal, and migration from deprecated libraries.

Status: Production Ready Last Updated: 2026-02-03 Scope: npm, pnpm, yarn projects

Diagnose and fix SwiftUI performance issues through code review and Instruments profiling guidance. \n \n Classifies symptoms (slow rendering, janky scrolling, CPU spikes, memory growth, hangs, excessive view updates) and performs code-first review against common anti-patterns like invalidation storms, unstable list identity, and layout thrash. \n Guides users through Instruments profiling when code review alone is inconclusive, with structured intake checklists and trace analysis. \n Provides r

Real-user dogfooding with emotional friction tracking, click efficiency counting, and resilience testing to produce ranked audit reports. \n \n Supports three operating modes: UX Walkthrough (persona-based task completion), QA Sweep (systematic feature testing), and Targeted Check (focused area validation) \n Tracks emotional friction signals (trust, anxiety, confusion), click efficiency, form resilience (mid-navigation, back button, refresh), and asks \"would I come back?\" \n Three depth level