anti slop studio

    1

    Production-house quality control to strip generic AI tells from text, design, and video code.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    anti slop studio

    Example session with this skill installed

    I have this draft for a LinkedIn ad about our new CRM. It feels a bit generic. Can you run the slop scan and give me a specific, high-density rewrite?

    "In today's fast-paced world, staying ahead of the curve is more important than ever. Our robust CRM empowers your team to seamlessly manage workflows and unlock the power of your data."

    • Read your context and instructions
    • Compiled the anti slop studio

    I have analyzed the draft. It contained several high-probability AI tells: a "weather report" opening, the "In X world" trope, and three empty descriptors (robust, seamlessly, unlock). I have run slop_scan.py and applied the Specificity Test to create a version rooted in concrete utility.

    De-slopped LinkedIn Ad Copy

    ElementAnalysis
    Original"In today's fast-paced world, staying ahead of the curve is more important than ever."
    ProblemWeather report opening. Says nothing. Zero information density.
    FixDelete. Start directly with the user's pain or the product's proof.
    Original"Our robust CRM empowers your team to seamlessly manage workflows..."
    ProblemGeneric verbs (empower, manage) and fluff adverbs (seamlessly).
    FixReplace with a specific workflow action: "Syncs lead status across Slack and Salesforce."

    Revised Draft (High-Density)

    "Most CRMs die because sales teams hate manual data entry. Our tool automates the status sync between your Slack channels and your pipeline, saving roughly 4 hours of admin per rep every week. No 'unlocking' potential—just 40 more outbound calls per month, tracked automatically."

    Next steps

    1. Name the proof: Replace "roughly 4 hours" with the exact internal metric from your last case study.

    Visual Check: Ensure the accompanying image is a real screenshot of the Slack sync, not a generic 3D illustration of "data."
    3. Run Voice Pass: If this is for a video ad, I can generate the script beats using references/voice-sound.md.

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

    About this skill

    Generic, robotic AI content is easy to spot. This skill implements a production-house quality control pipeline to strip away the "slop" from briefs, scripts, ad copy, landing pages, and video motion code. It moves beyond simple word-filtering by enforcing a decide-first workflow, ensuring every creative asset is rooted in specific details rather than statistical averages.

    What it does

    • Briefing & Direction locks in specific ideas, proof points, and visual directions before any generation occurs to prevent generic defaults.
    • Copy De-slopping scans prose for structural tells like symmetrical contrasts, lists of three, and repetitive rhythm.
    • Visual & Motion Linting audits design files and motion code to remove unexamined glows, generic transitions, and hollow effects.
    • A/V Analysis uses Python scripts to probe video and audio files for loudness peaks, dead air, and shot rhythm issues.
    • Taste Benchmarking applies human-centric tests like the Swap Test and Mute Test to ensure work survives real-world scrutiny.

    How it works

    1. Define the Brief using direction-brief.md to establish the one idea and specific proof points that drive the creative.
    2. Execute with References following specific guidelines for writing, Hinglish register, visual design, or motion grammar.
    3. Run Scanners using provided Python scripts to flag technical tells in text, HTML/CSS, or video metadata.
    4. Apply Taste Passes to verify the output carries information, has a clear focal point, and avoids competitor interchangeability.

    Frameworks & tools

    Uses Python 3.8+ standard library for scanning scripts. Video and audio analysis requires ffmpeg and ffprobe on the system PATH. Compatible with HTML/CSS for visual linting and JSON for shot planning.

    Why this beats prompting it yourself

    Simple prompts like "be distinctive" often cause models to add more fluff, which increases slop. This skill uses a subtractive approach and external technical scripts to verify that known AI fingerprints are physically removed from the final output.

    Use cases

    • Ad Campaigns to ensure every reel and caption feels unique and branded rather than like a stock template.
    • Technical Content to replace polished abstractions with real numbers, names, and concrete evidence.
    • Motion Graphics to audit code-rendered video for intentional movement and deterministic beat grids.
    • Hinglish Copy to maintain a natural register for localized marketing without robotic translation tells.

    Known limitations

    Does not perform fact-checking or general code review. Not designed to hide AI authorship or bypass detection tools. Script-based scene detection in video may vary based on threshold settings.

    Does not fact-check or review logic. Requires ffmpeg/ffprobe for A/V scripts. Scene detection may miss cuts in dark or busy footage. Not for hiding AI authorship.

    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 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

    Fresh listing

    Recently published to Agensi

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 9 days ago

    • Free with an Agensi account

    Requires

    Node.js
    Python

    Permissions

    Terminal / Shell
    Browser
    Read Files
    Write Files
    Network Access
    Listed9 days ago

    What's inside

    Frequently Asked Questions

    This skill uses a subtractive quality control pipeline and external Python scripts to identify and remove specific AI 'fingerprints' like symmetrical list structures and generic visual effects that typical prompting cannot fix.

    You will receive the full 'Anti Slop' workflow documentation, custom Python scanners for text and code analysis, and a suite of benchmarking tests (like the Swap and Mute tests) to audit your creative output.

    The text and design scanners run on standard Python 3.8+, while the A/V analysis tools require `ffmpeg` and `ffprobe` to be installed on your system's PATH.

    While it excels at English and Hinglish marketing copy, the skill is designed to audit any creative project—including HTML/CSS design files and motion graphics code—to ensure intentionality and brand uniqueness.

    No, this skill is a creative quality control tool designed to improve output standards; it does not perform factual verification or guarantee that content will bypass third-party AI detection software.

    New in Marketing & SEO