Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Email & Message Tone & Clarity Gate

    1

    Because it quotes the exact problem text and never rewrites or sends, it catches what you miss when you're too close to your own message while keeping your words yours.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    5 usesSecurity scanned
    Email & Message Tone & Clarity Gate

    Email & Message Tone & Clarity Gate

    Example session with this skill installed

    Review this message before I send it to a teammate:

    "Hey just following up again on that thing I mentioned, would be great to get it sorted soon if possible, no rush but kind of urgent. Thanks!"

    • Read your context and instructions
    • Compiled the email & message

    VERDICT: REVISE
    CLARITY SCORE: 32
    TONE READ: Apologetic and tentative; the mixed urgency signals may read as either nagging or unimportant.

    ISSUES

    • [clarity-of-ask] "that thing I mentioned" -> the reader may not recall what this refers to -> name the specific item and link or recap it
    • [action-and-ownership] "get it sorted soon" -> no concrete action, owner, or date -> state exactly what you need and by when
    • [tone] "no rush but kind of urgent" -> contradictory signals weaken the request -> pick one priority and say it plainly
    • [context-and-completeness] "following up again" -> no link to the prior thread -> quote or link the earlier message
      THE ASK: unclear

    TOP FIXES

    1. Replace "that thing" with the specific request and a real deadline
    2. Remove the contradictory urgency and state the priority once
      ONE-LINE SUMMARY: Tweak first: name the ask and give a clear deadline before sending.

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

    About this skill

    The Email & Message Tone & Clarity Gate turns your agent into a calm second pair of eyes that reviews any email or chat message before it goes out — and then stops, leaving the wording and the send button to you.

    It runs five fixed passes over your draft: a clarity-of-ask check (is there one unambiguous request and a clear next step?), a tone check (will a busy reader read this as curt, passive-aggressive, defensive, or over-apologetic?), an action-and-ownership check (buried tasks, unstated deadlines, unclear who-does-what), a context-and-completeness check (missing background, undefined jargon, "as discussed" with no recap), and a risk-and-readiness check (sending while angry, ambiguous commitments, a subject line that doesn't match the body).

    Every run returns a structured verdict: SEND, REVISE, or HOLD, plus a 0-100 clarity score, a plain read of how a busy recipient will likely perceive the message, each issue quoted with the reason and the fix, the single clearest ask, and a one-line recommendation. Because it quotes the exact problem text and never rewrites or sends, it catches what you miss when you're too close to your own message while keeping your words yours.

    Who it's for: anyone who sends messages where tone and clarity matter — support and success teams, salespeople, managers, founders, and anyone firing off a reply while rushed or annoyed. It is model-agnostic and read-only: it has no inbox or network access and cannot read, send, or delete mail. It is a pre-send reviewer, not an autoresponder or ghostwriter.

    Tone is contextual and partly subjective: the gate reads for how a typical busy recipient might perceive a message, but it cannot know your specific relationship history, inside jokes, or cultural norms with the reader. Treat tone flags as prompts to reconsider, not absolute rulings. It reviews English prose and may be less reliable on other languages or heavy domain jargon. It does not send, schedule, or store messages, and it makes no judgment about the underlying decision you are communicating.

    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

    5 uses

    Times used to date

    Money-back guarantee

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

    Trust & safety

    Security scan

    Security scan passed 5 months ago

    Permissions

    Read Files

    File Scopes

    email-message-tone-clarity-gate/**

    Read-only by design. The skill only reads the message draft you paste in so it can quote the exact lines that are unclear or off-tone. It has no inbox or network access and cannot read, send, edit, or delete mail, and it needs no shell or environment access.

    Listed5 months ago

    What's inside

    Frequently Asked Questions

    Unlike AI writers that hallucinate or change your voice, this skill is a read-only gate that critiques your existing draft. It provides a structured SEND/REVISE verdict by flagging specific issues like buried asks or unintended passive-aggression without ever rewriting your message.

    This skill is model-agnostic and designed to work with any major LLM (like GPT-4, Claude, or Gemini) that supports structured output. It requires no inbox plugins or API access to your mail server, ensuring it remains a secure, private reviewer.

    No, for security and control, the skill is intentionally 'read-only.' It analyzes the text you provide and gives feedback, but it cannot access your inbox, hit 'send,' or delete messages, leaving you in total control of the final click.

    You will receive a 0-100 clarity score, a 'perceived tone' summary, and a list of specific quotes from your draft labeled with the exact reason for the flag and a suggested fix to bring the message to 'SEND' status.

    This skill excels at catching 'rushed' errors such as missing context, undefined jargon, 'as discussed' references without recaps, and ambiguous deadlines that lead to unnecessary back-and-forth.

    New in Productivity