Stop Slop Writing

    2

    The problem AI-generated drafts are often cluttered with predictable filler, dramatic fragments, and "AI tells" that signal to the reader the content wasn't written by a human.

    Free

    6 installsSecurity scanned

    Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    Stop Slop Writing

    Example session with this skill installed

    Review this update: Certainly! I'd be happy to help. In today's competitive landscape, it's not just about code—it's about culture. Truly. The PR should be reviewed by EOD. That's the path.

    • Read your context and instructions
    • Compiled the stop slop writing

    I have removed the AI filler, converted the passive phrasing to active voice, and replaced the dramatic fragments with a concrete update.

    Revised Internal Update

    We are prioritizing team culture alongside our technical output to stay competitive. Review the pending PRs by the end of the day to keep the release on schedule.

    Next steps

    • Post this version to the #engineering-updates Slack channel.
    • Assign the specific PR reviewers in the project management tool.

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

    About this skill

    The problem

    AI-generated drafts are often cluttered with predictable filler, dramatic fragments, and "AI tells" that signal to the reader the content wasn't written by a human. This creates friction, reduces trust, and forces readers to wade through fluff to find the actual point.

    What it does

    • Identifies and removes common AI filler openers like "Certainly" or "In today's fast-paced world."
    • Enforces active voice to ensure accountability and clarity in every sentence.
    • Eliminates cryptic binary contrasts and dramatic one-word fragments that obscure meaning.
    • Converts clever but confusing prose into concrete, plain-language nouns and verbs.
    • Standardizes sentence structures to ensure every line carries a fact, an ask, or a next step.

    Why this beats prompting it yourself

    Generic "write like a human" prompts often result in overly casual or inconsistent tone. This skill applies a specific heuristic to strip away the structural artifacts of LLMs, ensuring your output reads like a competent professional, not a chatbot trying to sound smart.

    Use cases

    • Reviewing internal team updates to ensure they are direct and actionable.
    • Polishing client-facing emails to remove robotic formalisms and fluff.
    • Refining technical blog posts to keep the focus on facts rather than flowery transitions.
    • Editing documentation to prioritize concrete instructions over abstract slogans.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    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

    6 installs

    Downloaded by developers to date

    Free forever

    No account required to browse

    Trust & safety

    Security scanned

    Verified clean 17 days ago

    • Free to download with an account

    Listed17 days ago

    What's inside

    Frequently Asked Questions