Public Speaking logo

Public Speaking

Community
Tibsfox
public-speaking

Public speaking and oral presentation skills for effective communication. Covers speech structure (introduction, body, conclusion), delivery techniques (projection, pace, pause, gesture), audience analysis, impromptu and extemporaneous methods, managing anxiety, visual aids, and persuasive versus informative speaking. Use when preparing speeches, practicing delivery, analyzing presentations, or building confidence in oral communication.

Overview

PublisherTibsfox
Repositorygsd-skill-creator
Skill namepublic-speaking
Stars
70
Forks
9
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Tibsfox on GitHub. Read the source before you install it.

Installation

Install the Public Speaking AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Tibsfox/gsd-skill-creator.git /tmp/gsd-skill-creator
mkdir -p .claude/skills
cp -r /tmp/gsd-skill-creator/examples/skills/communication/public-speaking .claude/skills/public-speaking
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Public Speaking in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Public Speaking on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Public Speaking is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Public Speaking

Public speaking is the act of communicating ideas to an audience through structured oral delivery. It is one of the oldest human skills -- Aristotle codified its principles in 335 BCE, Cicero refined them in Rome, and Frederick Douglass weaponized them against slavery. The skill remains foundational because the capacity to stand before others and make yourself understood is a prerequisite for leadership, advocacy, teaching, and civic participation.

Agent affinity: douglass (delivery and advocacy), king (audience connection and rhetoric)

Concept IDs: comm-presentation-structure, comm-audience-adaptation, comm-voice-articulation, comm-managing-presentation-anxiety

The Architecture of a Speech

Every effective speech has three parts, and the audience's attention follows a predictable curve across them.

Introduction

The introduction must accomplish three things in 60--90 seconds:

  1. Hook. Capture attention. Options: a story, a surprising statistic, a provocative question, a quotation, a demonstration. Not: "Today I'm going to talk about..." (this is an announcement, not a hook).
  2. Thesis. State the central claim or purpose in one sentence. The audience should be able to repeat it.
  3. Preview. Tell them what you will cover. "I'll show you three reasons why [thesis]." The preview is a contract with the audience -- they know what to expect, and they will notice if you fail to deliver.

Body

The body develops the thesis through 2--5 main points. More than five exceeds working memory. Each point follows a sub-structure:

  • Claim. State the point in one sentence.
  • Evidence. Support it with data, examples, testimony, or reasoning.
  • Explanation. Connect the evidence to the claim -- don't assume the audience sees the link.
  • Transition. Bridge to the next point. Explicit transitions ("Now that we've seen X, let's turn to Y") are better than implicit ones.

Organizational patterns:

PatternBest forExample
ChronologicalProcesses, histories, narratives"First... then... finally..."
TopicalCategories, aspects, facets"Three reasons why..."
Problem-solutionAdvocacy, proposals"Here's the problem... here's my solution..."
Cause-effectAnalysis, explanation"This happened because..."
Compare-contrastEvaluation, persuasion"Option A vs. Option B"
Monroe's Motivated SequencePersuasion (5 steps)Attention, Need, Satisfaction, Visualization, Action

Conclusion

The conclusion is not a summary -- it is the final impression. It should:

  1. Signal closure. "In closing..." or a shift in tone and pace.
  2. Restate the thesis in slightly different words than the introduction.
  3. End with impact. A call to action, a return to the opening story, a memorable image, or a provocative final question. The last sentence should be something the audience remembers walking out.

Never end with "That's it" or "I guess that's all I have." These undermine everything that came before.

Delivery

Content is necessary but not sufficient. Delivery is how the speaker's body and voice transmit the message.

Vocal delivery

  • Projection. Speak to the back of the room, not the front row. Project from the diaphragm, not the throat.
  • Pace. Conversational pace is 120--150 words per minute. Slow down for emphasis, speed up for energy. Monotone pace is the enemy of attention.
  • Pause. The pause is the most powerful delivery tool. Pause before key points (builds anticipation), after key points (lets them land), and when you need to think (far better than "um"). Most speakers fear silence; audiences welcome it.
  • Articulation. Pronounce every syllable. Mumbling signals a lack of conviction.
  • Vocal variety. Vary pitch, volume, rate, and tone. A dynamic voice keeps attention; a flat voice loses it.

Physical delivery

  • Eye contact. Connect with individuals, not the wall or the ceiling. Hold eye contact with one person for a complete thought (3--5 seconds), then move to another. In large audiences, address sections rather than individuals.
  • Gesture. Gestures should be purposeful and visible. Hands below the waist are invisible; hands above the shoulders are distracting. The "power zone" is waist to shoulder, extending outward from the body.
  • Movement. Move with purpose. Walk toward the audience to emphasize a point, step to the side for transitions. Pacing, swaying, and rocking are nervous habits, not movement.
  • Stance. Plant your feet shoulder-width apart. Weight evenly distributed. Stillness communicates confidence.

Nonverbal congruence

The audience believes the body over the words. If your words say "I'm excited about this" but your body says "I'd rather be anywhere else," the body wins. Rehearse not just what you say but how you look saying it.

Audience Analysis

A speech that ignores its audience is a monologue. Effective speakers analyze their audience before writing a word.

Key questions:

DimensionQuestions
KnowledgeWhat does the audience already know about the topic? What technical terms need definition?
AttitudeAre they favorable, neutral, or hostile toward the thesis?
InterestWhy are they here? What do they care about?
DemographicsAge, profession, cultural background -- what affects how they receive the message?
ContextWhat is the setting? Time of day? What came before this speech?

Adaptation means adjusting language, examples, depth, and persuasive strategy to match the audience. Speaking above the audience's knowledge level causes confusion; speaking below it causes boredom. Either way, the message fails.

Impromptu and Extemporaneous Speaking

Impromptu (no preparation)

When called on unexpectedly:

  1. Take a breath. Three seconds of silence is fine.
  2. Pick a structure. Past-present-future, problem-solution, or "three reasons" -- any structure is better than none.
  3. Commit to one point. Don't try to cover everything. One clear idea delivered with conviction beats five ideas delivered in a muddle.
  4. Land the plane. End with a summary sentence. Don't trail off.

Extemporaneous (prepared but not memorized)

Extemporaneous speaking -- working from an outline or key phrases rather than a script -- is the gold standard for most contexts. It combines the structure of a prepared speech with the naturalness of conversation.

Method:

  1. Write the full speech.
  2. Reduce it to an outline with key phrases and transitions.
  3. Practice from the outline until you can deliver each section in your own words.
  4. On delivery day, use only the outline. If you forget a detail, skip it -- the audience doesn't know your script.

Managing Speech Anxiety

Stage fright is universal and physiological: the amygdala interprets "many eyes on me" as a threat and triggers the fight-or-flight response. The goal is not to eliminate anxiety but to redirect it.

Strategies:

  • Preparation. The number one anxiety reducer. Know your material cold.
  • Practice aloud. Not in your head -- out loud, standing up, with gestures. Practice the opening 30 seconds until you can deliver it in your sleep.
  • Reframe. "I'm nervous" and "I'm excited" produce the same physiological response. Tell yourself you're excited.
  • Breathe. Deep diaphragmatic breaths before speaking lower heart rate.
  • Arrive early. Stand where you'll speak. Make the space familiar.
  • Focus on the audience. Anxiety is self-focused. Shift your attention to serving the audience and the self-consciousness diminishes.

Informative vs. Persuasive Speaking

DimensionInformativePersuasive
GoalUnderstandingAction or belief change
ThesisDescriptiveArgumentative
EvidenceFacts, explanations, demonstrationsFacts, reasoning, emotional appeals
ToneNeutral, clearPassionate, directional
StructureTopical, chronologicalProblem-solution, Monroe's Sequence
Call to actionRarelyAlmost always

Many real speeches blend both: inform first, then persuade. The audience must understand the problem before they will accept the solution.

Cross-References

  • douglass agent: Delivery mastery and the power of the spoken word to drive social change. Primary agent for speech delivery coaching.
  • king agent: Audience connection, emotional resonance, and rhetorical structure. Primary agent for persuasive speech construction.
  • persuasion-rhetoric skill: Aristotle's rhetorical framework (ethos, pathos, logos) and argumentative structure.
  • active-listening skill: Listening is the other half of speaking -- understanding audience reception.
  • interpersonal-communication skill: Adapting communication to different relationships and contexts.

References

  • Aristotle. (c. 335 BCE). Rhetoric. (Kennedy, G. A., Trans., 2007). Oxford University Press.
  • Lucas, S. E. (2020). The Art of Public Speaking. 13th edition. McGraw-Hill.
  • Monroe, A. H. (1935). Principles and Types of Speech. Scott, Foresman.
  • Carnegie, D. (1915). The Art of Public Speaking. Home Correspondence School.
  • Duarte, N. (2010). Resonate: Present Visual Stories that Transform Audiences. Wiley.

Frequently asked questions

What does the Public Speaking AI skill do?

Public speaking and oral presentation skills for effective communication. Covers speech structure (introduction, body, conclusion), delivery techniques (projection, pace, pause, gesture), audience analysis, impromptu and extemporaneous methods, managing anxiety, visual aids, and persuasive versus informative speaking. Use when preparing speeches, practicing delivery, analyzing presentations, or building confidence in oral communication.

Why use Public Speaking on TypingMind?

Because you install it once and use it with any model. Public Speaking is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Public Speaking in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Tibsfox/gsd-skill-creator/tree/main/examples/skills/communication/public-speaking. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Public Speaking?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Public Speaking?

As many as you like. As long as a model supports skills, you can use Public Speaking with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Public Speaking AI skill free?

It is published on GitHub by Tibsfox. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇