Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Slop Audit — AI UI & Code Inspector

    0

    Detect and track AI-generated slop in UI, frontend code, and copy with 245 catalogued patterns.

    $29.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Slop Audit — AI UI & Code Inspector

    Slop Audit — AI UI & Code Inspector

    Example session with this skill installed

    Run a full slop audit on our frontend repository, scan both UI components and React source files, log findings with evidence levels, and output the prioritized fix order.

    • Read your context and instructions
    • Compiled the slop audit
    • Generated the UI component

    Summary

    Completed a 4-pass audit across 42 component and source files. Detected 7 catalogued slop patterns (1 Blocker, 3 Major, 3 Nits). Initialized ./.slop-tracker/slop-log.json with an evidence trail.


    Audit Findings Ledger

    IDCategoryPattern DescriptionFile & LineEvidenceSeverity
    E38Source SecurityClient bundle environment secret leaksrc/api/client.ts:14ObservedBlocker
    Q9JS ContractFetch in useEffect without AbortControllersrc/hooks/useData.ts:28ObservedBlocker
    M9Motion SlopBlanket transition: all 0.3s easesrc/components/Card.tsx:45ObservedMajor
    A1AccessibilityInsufficient contrast ratio (3.1:1 on body text)src/styles/tokens.css:12MeasuredMajor
    X5CompositionCard-grid archetype aggregation (3 identical pills)src/views/Pricing.tsx:64InferredMajor
    T16TypographyProportional numerals used in tabular pricing columnsrc/views/Billing.tsx:82ObservedNit
    P5CopywritingGeneric AI-slop adjective cliches ("seamlessly")src/views/Hero.tsx:18ObservedNit

    Prioritized 8-Stage Fix Order

    Stage 1 (Immediate Blockers): Strip API_SECRET from src/api/client.ts and add AbortController cleanup to src/hooks/useData.ts.
    2. Stage 2 (Accessibility & Color): Bump text contrast tokens to 4.5:1 (WCAG AA).
    3.

    Stage 3 (Motion Quality): Replace transition: all with explicit opacity, transform transitions and tuned spring easings.
    4.

    Stage 4 (Composition & Copy): Refactor pricing page layout to introduce a clear visual anchor and remove repetitive marketing adjectives.


    Next Steps

    • Run /skill slop-audit --list to inspect pending findings by category.
    • When fixed, run /skill slop-audit --clear to prune resolved items from .slop-tracker/.

    Card.tsx

    TSX · React component

    Generated

    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

    A web page can pass every superficial visual check and still leak an API key, race a fetch in useEffect, and carry any across its entire boundary. A codebase can be cleanly formatted and still render the exact same generic card grid and price pill as every other AI-generated SaaS app.

    Slop Audit scans both surfaces: what the user sees, and the source code that produced it.

    It runs a rigorous 4-pass audit backed by an evidence-based taxonomy of 245 catalogued patterns across 18 categories (Visual, Motion, Typography, Layout, Copy, Accessibility, React/TypeScript Engineering, and Composition).

    The 4-Pass Scan System

    1. Quality Failures: Automated WCAG AA contrast verification via formula/table, text against viewport edges, skipped heading hierarchies, dead click targets, and happy-path-only states.
    2. Catalogued Patterns: 245 anti-patterns across layout, motion (transition: all, untuned easings), typography, copy cliches, and design-token drift.
    3. Composition & Archetypes: Detects card-grid & price-pill aggregation, signature footers, retail menu chrome, and archetype uniformity.
    4. Source Code Contract (E1–E58): React state and lifecycle hygiene, uncleaned effects, un-aborted fetches, god components, array-index keys, any/! escapes at boundaries, and secrets in client bundles.

    Ordered Remediation

    Findings are logged in ./.slop-tracker/slop-log.json with confidence scores and an 8-stage prioritized fix order so you never waste time polishing cosmetic styling over critical security or contract blockers.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Frontend & Web Apps.

    Web-focused (HTML/CSS/JS/TS). Requires local directory write access for logging. Imagery contrast over dynamic media requires manual oversight.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 24 days ago

    Software
    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    ./.slop-tracker/**

    Audit execution is completely read-only on source code. Writes are strictly scoped to the local .slop-tracker/ directory inside the audited project.

    Listed25 days ago

    What's inside

    Frequently Asked Questions

    This skill is optimized for modern web development stacks, specifically React and TypeScript environments, and requires local file system access to maintain its slop-log.json database. It works across any standard IDE or CLI-based AI agent that supports Python execution and shell commands like grep.

    Unlike basic linters that check for syntax, slop audit uses a specialized 4-pass scanning process to detect 245 high-level patterns like 'glassmorphism abuse' and 'div-soup' that signify low-quality AI generation. It focuses on the 'uncanny valley' of UI/UX and architectural technical debt that standard tools typically ignore.

    The audit follows a prioritized 8-stage remediation logic designed to solve structural issues before cosmetic ones, preventing the 'churn' of UI changes breaking underlying code. It classifies findings into Blocker, Major, and Nit severities, allowing you to focus on critical runtime regressions before polishing visual tropes.

    You receive the full suite of auditing scripts, the 245-pattern detection catalog, and the specialized 'Luxury Domain Gating' module for high-end project standards. The purchase also includes the persistent tracking system to monitor your project's code quality over time.

    Setup is instantaneous; once the skill is added to your agent, it initializes by creating local storage directories in your current working directory. From there, you can immediately begin scanning specific files or entire directories to populate your first audit log.

    While the tool automates WCAG contrast and accessibility checks using Python scripts, it cannot perfectly 'see' text layered over complex, dynamic images. In these specific cases, the tool will flag the area for manual verification to ensure 100% compliance.

    New in Frontend & Web Apps