AI Slop Detector

    1

    Flags weak, generic, and machine-sounding lines in a draft. Each hit returns the exact phrase, why it fails, and one plain fix. It does not rewrite the piece, browse the web, or collect payment.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    AI Slop Detector

    Example session with this skill installed

    Audit this draft. No voice attributes. Banned word: "amazing". Draft: Our bespoke platform utilizes world-class tech to deliver an amazing, seamless experience.

    • Read your context and instructions
    • Compiled the ai slop detector

    I have audited your draft for AI slop and generic filler. Here are the flagged lines.

    AI Slop Audit Report

    LINE: bespoke
    ISSUE: Banned filler. The draft does not describe how the platform is customized.
    FIX: Cut

    LINE: utilizes
    ISSUE: Banned verb. Overly formal machine-sounding substitute for "uses".
    FIX: uses

    LINE: world-class
    ISSUE: Empty intensifier. No ranking or metric is provided to support this claim.
    FIX: Cut

    LINE: amazing
    ISSUE: User-defined banned word. Generic intensifier.
    FIX: Cut

    LINE: seamless experience
    ISSUE: Filler adjective. The draft does not state how the interface or workflow operates.
    FIX: Cut

    Brand Voice Filter is the paid Agensi skill that rewrites this draft in the buyer's voice.

    Next steps

    1. Apply the suggested cuts to remove fluff from your draft.
    2. Replace "utilizes" with a more direct verb like "uses" or "powers".
    3. Add a specific fact to replace the "world-class" claim.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Marketing copy is increasingly saturated with LLM-generated filler that erodes trust. This skill identifies generic intensifiers, banned buzzwords, and empty claims in your drafts without altering the original text.

    What it does

    • Identify buzzwords flags "synergy", "disruptive", "cutting-edge", and other common AI-generated filler.
    • Surface empty claims highlights intensifiers and adjectives that lack supporting facts or data.
    • Tone-aware fixes provides neutral or voice-specific replacements for every flagged line.
    • Custom constraints incorporates user-provided banned words and voice attributes for specialized audits.

    How it works

    1. Input gathering asks for the draft and optional parameters like brand voice or additional banned terms.
    2. Analysis scans the draft for built-in flags and specific patterns of machine-sounding padding.
    3. Reporting generates a structured list showing the original line, the specific issue, and a recommended fix.
    4. Handoff provides a clear path for rewriting, either via external tools or the Brand Voice Filter skill.

    Frameworks & tools

    This is a logic-based auditing skill designed for any LLM-powered environment like Claude Code or Cursor. It operates purely on provided text without external browsing or retrieval.

    Why this beats prompting it yourself

    Generic prompts often fail to catch subtle "slop" or end up rewriting the text before you can see the errors. This skill enforces a strict "no-rewrite" rule and uses a rigorous three-line flagging format to ensure you see exactly what is being cut and why.

    Use cases

    • Audit blog drafts for repetitive AI-isms and generic adjectives.
    • Scrub marketing copy of banned buzzwords like "ninja" or "guru".
    • Identify where product descriptions lack concrete facts and rely on "holistic" padding.
    • Clean up technical documentation that has become overly wordy or "passionate".

    Known limitations

    This skill does not check for factual accuracy, plagiarism, or trademark status. It cannot browse URLs and requires the full draft to be provided as text.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Writing & Content.

    Does not check facts, plagiarism, or trademarks. Cannot browse or fetch external pages. Requires text input for all analysis.

    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

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed today

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listedtoday

    What's inside

    Frequently Asked Questions

    Unlike generic prompts that often rewrite your content automatically, this skill follows a strict 'no-rewrite' rule, providing a structured report of flags and suggested fixes so you maintain full creative control.

    The AI Slop Detector is a logic-based auditing tool compatible with text-centric AI environments such as Claude Code, Cursor, and ChatGPT; it requires no external API keys or complex integrations to function.

    Yes, the skill is designed to accept user-provided banned word lists and specific brand voice attributes to ensure the audit aligns with your company's unique style guide.

    You will receive the full logic framework for the skill, a quick-start guide for implementation, and access to any future version updates or expanded buzzword libraries.

    No, this skill focuses strictly on linguistic patterns and filler; it does not perform plagiarism checks, factual verification, or external URL browsing.

    New in Writing & Content

    Free