English Speech & Rehearsal Pack

    1

    Turn rough notes into a clear English speech, a shorter fallback, and a practical rehearsal pack, with honest timing estimates and no invented credentials or results.

    $4

    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 CLIDeepSeekDeepSeekMuseMuse+22 more

    English Speech & Rehearsal Pack

    Example session with this skill installed

    Fictional test input: overloaded meeting statement

    I only have 30 seconds in the meeting. Please keep every detail and example from the source draft below, but make it natural. I recommend a two-week pilot, NOT a full rollout. The vendor's speed claim hasn't been verified; security approval is pending. Customer data must stay out until security approval is complete. Today I want agreement on the pilot scope and success measures. I have not promised to run the pilot before approval. If everything won't fit, tell me rather than making me speak too fast. Give me the rehearsal pack.

    Source draft (fictional scenario, not evidence that the vendor claim is true):

    I want to begin by explaining why I think we should explore the new request-routing tool, and why I do not think exploring it means we should approve a full rollout today. The vendor says it can process requests faster, but we have not verified that claim in our own workflow. For example, a request that arrives without a deadline may still need a person to ask a follow-up question. A request that uses an unfamiliar project name may still need someone to decide which team should receive it. A request with an attachment may still need a person to check whether the attachment contains the information the team actually needs. Those examples matter because a demonstration can look smooth while everyday work is less tidy. I recommend a two-week pilot rather than a full rollout. Security approval is still pending, and we must not put customer data into the tool until that approval is complete. We also need to decide which request types belong in the pilot, which examples are appropriate to test, and what success would look like before we interpret any results. We should not assume the vendor's advertised speed will translate into our own time savings. Today, I am asking us to agree the pilot's scope and success measures. I am not asking us to approve a full rollout or to start using customer data before the security questions are resolved.

    • Read your context and instructions
    • Compiled the english speech

    Meeting statement: a genuine 30-second priority version

    Brief and fact checks

    Audience: internal meeting. Goal: agree pilot scope and success measures, not approve a rollout. Hard limit: 30 seconds. The original contains 238 spoken words and takes an estimated 98–125 seconds at 115–145 words per minute, before extra pauses. Keeping every detail in 30 seconds would require at least 476 words per minute with no pauses, so that request cannot be met at the stated planning pace. The version below preserves the decision, uncertainty, security restriction, and ask. It omits the three operational examples, the explanation about demonstrations, and repeated caveats. Those can be used in discussion or a written follow-up; no follow-up has been sent.

    Main script

    I recommend a two-week pilot,

    not a full rollout. [pause 1s] The vendor's speed claim is unverified, and security approval is still pending. Keep customer data out until approval is complete. [pause 1s] Today, can we agree the pilot's scope and success measures?

    Timing estimate

    40 spoken words, 18–23 seconds, using 115–145 words per minute and including 2 seconds of marked pauses.

    Short fallback

    Use this if you are cut off before your turn. The security boundary and unverified speed claim still stay in.

    Let's agree the scope and success measures for a two-week pilot, not a rollout. [pause 1s] The speed claim is unverified. Customer data must stay out until security approval is complete.

    Timing estimate

    30 spoken words, 13–17 seconds, using 115–145 words per minute and including 1 second of marked pauses.

    Likely Q&A

    Does agreeing the pilot mean approving a rollout?
    No. The request today is to agree the scope and success measures for a two-week pilot, not a full rollout.

    Can we use real customer data during the trial?
    Not until security approval is complete.

    What would the pilot test?
    We still need to agree its scope and success measures. The draft gives examples involving missing deadlines, unfamiliar project names, and attachments that may need a person's check.

    How much faster will the tool be?
    We don't know. The vendor's speed claim has not been verified in our workflow.

    Rehearsal checklist

    • Confirm the current security status before you speak.
    • Read the main script aloud with both one-second pauses, then record the stopwatch time.
    • The planning range ends at 23 seconds, leaving at least seven estimated seconds below the 30-second limit. This buffer is not a guarantee.
    • If your measured read exceeds 30 seconds, use the fallback. Don't speed through the security condition.
    • Practice the first sentence and final ask without reading.
    • Keep the three examples for questions rather than adding them back into the timed statement.

    How the estimates were checked

    The included Python helper counted only main.txt or short.txt, not this document's headings, cue text, Q&A, or checklist. Contractions count as one word; hyphenated parts count separately. Quantities are written as spoken words. Normal punctuation is included in the assumed pace, and marked pauses are added separately. Results are rounded outward to whole seconds. No audio was recorded and no stopwatch delivery was measured. Replace these assumptions with your own timed read before relying on the limit.

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

    About this skill

    A good speech draft should survive being said out loud. This skill turns your own facts into a business introduction, meeting statement, or project update that is easier to deliver and easier to follow.

    You get:

    • A main script in natural spoken English, with sparse pause and emphasis cues.
    • A shorter fallback for a meeting that runs late or an introduction round that moves quickly.
    • A word count and estimated delivery range with the speaking pace and pause assumptions shown.
    • Likely audience questions and concise answers that preserve what is known, uncertain, or not yet approved.
    • A focused rehearsal checklist, including a real stopwatch read before you rely on a time limit.

    The skill keeps important qualifications intact. It does not turn trial feedback into proven business results, a target date into a commitment, or an interest into a credential. If the notes will not fit the available time, it prioritizes the main message and tells you what was cut instead of pretending everything fits.

    Best for

    Professionals, founders, project leads, and English learners preparing everyday business speaking. Bring rough notes, a draft, or a readable source excerpt, plus your audience and time limit when known.

    Example request

    “Give me a 30-second meeting statement recommending a two-week pilot, not a full rollout. The vendor's speed claim is unverified and security approval is still pending. Customer data must stay out until approval is complete. End by asking us to agree the pilot's scope and success measures. Include a shorter fallback and likely questions.”

    The included demonstration's main statement contains 40 spoken words and two seconds of marked pauses. Its estimated range is 18–23 seconds at 115–145 words per minute. This is a calculation, not a recorded delivery or a performance guarantee.

    What is included

    The skill instructions, three speaking-format guides, a copyable intake template, two complete fictional worked examples with actual generated text, and an optional timing-check script. The script requires Python 3.9+ and uses only the standard library.

    Setup and boundaries

    Use a compatible assistant that can load Markdown skills. Installation and tool access depend on your host. Text drafting works without Python; the helper adds repeatable timing arithmetic where local code execution is available. No API key or specialist paid voice model is required. Any host or model usage fees are separate from this skill purchase.

    This is a text drafting and rehearsal-planning skill. It does not create audio, listen to your voice, evaluate pronunciation, record a performance, create slides, independently verify supplied facts, or send or publish anything. You remain responsible for confirming facts and timing a real rehearsal.

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

    No audio/voice features. Timing estimates are based on WPM averages and require stopwatch verification. Python 3.9+ required for the timing_check script.

    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

    Money-back guarantee

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

    Trust & safety

    Security scan

    Security scan passed 8 days ago

    Nothing to install. It runs in your AI agent.

    Optional
    Python 3.9+ for local timing arithmetic

    Permissions

    Terminal / Shell
    Read Files

    Read supplied notes and bundled references. Optional local timing helper; local file output when requested. No microphone, audio analysis, browser, network or connected accounts needed.

    Listed8 days ago

    What's inside

    Frequently Asked Questions

    It tracks supplied facts and uncertainty, removes unsupported claims, and estimates delivery time from word count, pace and marked pauses. It cannot guarantee factual accuracy or a delivery time: confirm your source facts and perform a stopwatch rehearsal.

    Use an assistant that can load SKILL.md packages. Text drafting works without code execution. The optional local timing helper requires Python 3.9+ standard library; host subscription and model fees are separate.

    Skill instructions, three speaking-format guides, an intake template, two complete fictional worked examples and an optional timing-check script. This is a text workflow, not standalone software or recorded lessons.

    While the skill optimizes text for natural delivery and provides cues, it does not record audio or generate synthetic voices; it is designed to prepare human speakers for live delivery.

    The output includes a shorter fallback preserving the main message and critical qualifications. Check its estimated timing and rehearse it against your actual reduced slot.

    New in Agents & Orchestration