Write Like Me: Your Voice, Zero AI Tells

    1

    **It writes as you.** You fill in a short profile (who you are, your work, where you're from) and swap in a few phrases you actually use.

    $1

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Write Like Me: Your Voice, Zero AI Tells

    Example session with this skill installed

    /human

    Rewrite this email to my manager so it sounds like me, not like a chatbot:

    "Dear Sir, I hope this email finds you well. I wanted to reach out regarding the Q3 dealer report. It is important to note that the data plays a pivotal role in our strategy. Moreover, I would like to request an extension of two days to ensure accuracy, consistency and completeness. In conclusion, I am committed to delivering high-quality work. Please let me know if you have any questions!"

    • Read your context and instructions
    • Compiled the write like me

    Mode detected: Professional (email to a senior)

    Rewritten email

    Dear Sir,

    Requesting two more days for the Q3 dealer report, so the new due date would be Thursday.

    The reason: 14 dealers in the south zone sent their September numbers late, and three of them don't match what we have in the system. I'd rather sort those out with the branch teams first than send you figures I'll have to correct next week.

    Everything else in the report is ready. As discussed with you last week, I'll keep the format the same as Q2 so it's easy to compare.

    Thanks,
    Priya

    What changed and why

    BeforeAfterRule
    "I hope this email finds you well"RemovedOpens directly, no filler
    "plays a pivotal role in our strategy"RemovedBanned words, inflated significance
    "accuracy, consistency and completeness"The real reason: late and mismatched dealer dataNo reflexive rule-of-three; specific detail over generic
    No reason for the delay14 late dealers, 3 mismatchesProfessional mode always gives the reason behind a request
    "In conclusion, I am committed to..."RemovedNo summary closers, no self-praise
    "Please let me know if you have any questions!""Thanks,"Banned chatbot sign-off

    Next steps

    • The dealer count and dates are examples; swap in your real numbers before sending.
    • The skill stays on, so your next message, post or note will be written the same way.

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

    About this skill

    What it does

    Most AI writing sounds the same: "delve", "pivotal", "it's not just X, it's Y", three neat bullet points and a tidy summary at the end. People spot it straight away.

    This skill fixes two things at once:

    1. It writes as you. You fill in a short profile (who you are, your work, where you're from) and swap in a few phrases you actually use. The skill then picks the right mode on its own:
      • Personal: journals, stories, daydreams. Flowing, specific, quietly emotional.
      • Casual: texts and quick notes. Direct, a bit blunt, no small talk.
      • Professional: emails, reports, requests. Straight to the point, gives reasons, respectful.
    2. It removes AI tells. A banned-word list, banned patterns (fake balance, rule-of-three, "In conclusion"), style rules (no bullet points standing in for prose, no bolding every line) and structural rules (asides, uneven pacing, not wrapping everything up neatly).

    Type /human or say "write like me" and the rules stay on for the rest of the chat. They apply while writing, not as a proofread pass afterwards.

    Who it's for

    Anyone who uses an agent to draft emails, messages, posts or personal writing and is tired of editing out the AI voice.

    Setup

    One file, no scripts, no network access. Open SKILL.md, fill in Part 1 (about you) and replace the example phrases in Part 2 with your own. The more real detail you give, the more it sounds like you.

    Credits and licence

    The content, language, style and communication rules are adapted from Wikipedia's "Signs of AI writing" guide (Wikipedia:Signs of AI writing), licensed CC BY-SA 4.0. This skill is shared under the same licence.

    Requires manual population of biographical data and custom phrases. Voice constraints may occasionally conflict with extreme technical precision.

    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

    Money-back guarantee

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

    Trust & safety

    Security scan

    Security scan passed 13 days ago

    Permissions

    No special permissions declared or detected

    Listed13 days ago

    What's inside

    Frequently Asked Questions

    Standard prompts often result in forced slang, but this skill uses a specialized "negative constraint" framework to systematically strip away the specific structural patterns and vocabulary that signal AI-generated text.

    This skill is a platform-agnostic prompt engineering framework that works with any major Large Language Model, including ChatGPT, Claude, and Gemini.

    Your purchase includes the comprehensive system-level constraint set, a configuration template for your personal voice profile, and a library of persona-driven modes.

    Setup involves filling out a specific biographical and lexicon template; once your personal details are added, the skill can be activated instantly in any new session.

    Yes, while the skill removes "robotic" markers, you can adjust the persona mode to ensure the output remains authoritative and appropriate for corporate environments.

    Updates to the banned vocabulary list and structural filters are provided periodically to account for new patterns or "tells" that emerge as LLM models evolve.

    New in Writing & Content