Debate Practice Coach logo

Debate Practice Coach

Community
travisjneuman
debate-practice-coach

Interactive debate and argument practice with structured feedback, counterargument generation, logical fallacy identification, and scoring rubrics. Use when preparing for debates, improving persuasion skills, or practicing argumentation.

Overview

Publishertravisjneuman
Repository.claude
Skill namedebate-practice-coach
Stars
98
Forks
22
Bundled files
Instructions only
LicenseMIT
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 travisjneuman on GitHub. Read the source before you install it.

Installation

Install the Debate Practice Coach 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/travisjneuman/.claude.git /tmp/.claude
mkdir -p .claude/skills
cp -r /tmp/.claude/skills/debate-practice-coach .claude/skills/debate-practice-coach
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Debate Practice Coach 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 Debate Practice Coach 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 Debate Practice Coach 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.

Debate Practice Coach

Frameworks for structured argumentation, counterargument development, logical analysis, and persuasive communication practice with objective scoring.

Argument Structure

Toulmin Model of Argumentation

ARGUMENT BUILDER (Toulmin Model):

CLAIM:        [Your main assertion]
              What are you arguing?

GROUNDS:      [Evidence and data supporting the claim]
              What facts back this up?

WARRANT:      [The logical connection between grounds and claim]
              Why does this evidence support your claim?

BACKING:      [Support for the warrant itself]
              Why should we trust this reasoning?

QUALIFIER:    [Degree of certainty — most, some, probably]
              How strong is this claim?

REBUTTAL:     [Conditions where the claim doesn't hold]
              When would this argument fail?

EXAMPLE:
  Claim:      "Remote work increases productivity for knowledge workers."
  Grounds:    "Stanford study showed 13% productivity increase in remote workers."
  Warrant:    "Fewer interruptions and commute elimination allow deeper focus."
  Backing:    "Multiple studies confirm interruptions cost 23 min to recover from."
  Qualifier:  "For most knowledge workers in roles not requiring physical presence."
  Rebuttal:   "May not apply to new employees needing mentorship or highly
               collaborative creative roles."

Argument Types

TypeStructureBest ForExample
DeductiveIf premises true → conclusion must be trueLogical proofs, policy arguments"All citizens must follow laws. X is a citizen. Therefore X must follow laws."
InductiveSpecific observations → general conclusionScientific arguments, trend analysis"In 50 studies, X led to Y. Therefore X likely causes Y."
AbductiveBest available explanationDiagnostic arguments"The best explanation for these symptoms is condition X."
AnalogicalSimilar case → similar conclusionPrecedent-based arguments"Policy X worked in Country A, which shares characteristics with Country B."
CausalX causes YPolicy proposals, problem-solution"Increasing minimum wage will reduce poverty because..."

Counterargument Generation

Counterargument Framework

COUNTERARGUMENT WORKSHEET:

ORIGINAL ARGUMENT: [State the argument you're opposing]

STRATEGY 1 — CHALLENGE THE EVIDENCE:
  "The evidence cited is flawed because..."
  - Data is outdated: [Explain]
  - Sample size insufficient: [Explain]
  - Source is biased: [Explain]
  - Correlation ≠ causation: [Explain]

STRATEGY 2 — CHALLENGE THE REASONING:
  "Even if the evidence is correct, the conclusion doesn't follow because..."
  - Logical gap between evidence and claim: [Explain]
  - Alternative explanation for the data: [Explain]
  - False dichotomy (there are other options): [Explain]

STRATEGY 3 — CHALLENGE THE SIGNIFICANCE:
  "Even if the argument is valid, it doesn't matter because..."
  - The impact is overstated: [Explain]
  - Other factors are more important: [Explain]
  - The cost of the proposal outweighs the benefit: [Explain]

STRATEGY 4 — PROVIDE COUNTEREXAMPLES:
  "This argument fails in these real-world cases..."
  - Example 1: [Where the argument doesn't hold]
  - Example 2: [Where the opposite occurred]

STRONGEST COUNTER: [Select best strategy + compose your response]

Steel Man Technique

STEEL MAN PROCESS:

Before arguing against a position, first construct the STRONGEST
possible version of your opponent's argument:

STEP 1: State their argument in your own words
  "[Opponent's position as I understand it]"

STEP 2: Check understanding
  "Is this a fair representation of your view?"

STEP 3: Strengthen it (add their best evidence)
  "In fact, the strongest version of this argument would include..."
  - Best available evidence for their position
  - Most charitable interpretation of their claims
  - Strongest logical chain supporting their conclusion

STEP 4: NOW respond to the strongest version
  "Even in its strongest form, this argument has the following problems..."

WHY STEEL MAN:
  - Demonstrates intellectual honesty
  - Prevents straw man fallacy
  - Your counter is more persuasive when addressing the best version
  - Builds credibility with the audience
  - Forces you to deeply understand the issue

Logical Fallacies Reference

Common Fallacies

FallacyDefinitionExampleResponse
Ad HominemAttacking the person, not the argument"You can't trust their economic analysis, they didn't finish college.""The argument's validity is independent of who makes it. Let's examine the evidence."
Straw ManMisrepresenting the argument to attack it"You want to reduce military spending? So you don't care about national security?""That's not my position. I said [actual position]."
Appeal to AuthorityCiting an authority outside their expertise"A famous actor says vaccines are dangerous.""What do the relevant experts (epidemiologists) say?"
False DichotomyPresenting only two options when more exist"Either we ban all cars or accept pollution.""There are many intermediate options: electric vehicles, public transit, emissions standards."
Slippery SlopeClaiming one event will inevitably lead to extreme outcomes"If we allow X, next thing you know Y and Z will happen.""What evidence exists that X actually leads to Y? Each step requires its own justification."
Circular ReasoningUsing the conclusion as a premise"This policy is good because it's the right thing to do.""You're assuming what you're trying to prove. Why is it the right thing?"
Red HerringIntroducing an irrelevant topic"We should discuss education funding." "But what about the economy?""That's a separate issue. Let's stay focused on education funding."
BandwagonAppealing to popularity"Everyone believes X, so X must be true.""Popularity doesn't determine truth. What does the evidence show?"
Appeal to EmotionUsing emotion instead of logic"Think of the children!" (without relevant evidence)"I share your concern, but let's examine what the data actually shows."
Hasty GeneralizationDrawing broad conclusions from limited examples"I know two people who failed, so the program doesn't work.""Two cases isn't enough to evaluate the program. What do the aggregate results show?"

Debate Format Templates

Lincoln-Douglas Format

LD DEBATE FORMAT (1v1):

AFFIRMATIVE:
  Constructive speech:     6 minutes
  (Present your case with evidence and reasoning)

CROSS-EXAMINATION:
  By Negative:             3 minutes
  (Questions to clarify and challenge the Affirmative case)

NEGATIVE:
  Constructive speech:     7 minutes
  (Present your case + respond to Affirmative arguments)

CROSS-EXAMINATION:
  By Affirmative:          3 minutes

AFFIRMATIVE:
  Rebuttal:                4 minutes
  (Respond to Negative arguments, rebuild your case)

NEGATIVE:
  Rebuttal:                6 minutes
  (Final arguments, summarize why you win)

AFFIRMATIVE:
  Rebuttal:                3 minutes
  (Final word — crystallize your best arguments)

Policy Debate Format

POLICY DEBATE (2v2):

CONSTRUCTIVES (build your case):
  1AC (First Affirmative Constructive):     8 min
  Cross-ex by 2NC:                          3 min
  1NC (First Negative Constructive):        8 min
  Cross-ex by 1AC:                          3 min
  2AC (Second Affirmative Constructive):    8 min
  Cross-ex by 1NC:                          3 min
  2NC (Second Negative Constructive):       8 min
  Cross-ex by 2AC:                          3 min

REBUTTALS (summarize and weigh):
  1NR (First Negative Rebuttal):            5 min
  1AR (First Affirmative Rebuttal):         5 min
  2NR (Second Negative Rebuttal):           5 min
  2AR (Second Affirmative Rebuttal):        5 min

Quick Practice Format

RAPID-FIRE DEBATE (15 minutes total):

SETUP (2 min):
  Topic: [Resolution or question]
  Side A: [For / Affirmative]
  Side B: [Against / Negative]

ROUND 1 — Opening Statements (4 min):
  Side A: 2 minutes — State your position with evidence
  Side B: 2 minutes — State your position with evidence

ROUND 2 — Rebuttals (4 min):
  Side B: 2 minutes — Respond to Side A's arguments
  Side A: 2 minutes — Respond to Side B's arguments

ROUND 3 — Closing Statements (4 min):
  Side A: 2 minutes — Summarize your strongest arguments
  Side B: 2 minutes — Summarize your strongest arguments

DEBRIEF (1 min):
  - Strongest argument from each side
  - Key moment that shifted the debate
  - Areas for improvement

Scoring and Feedback

Debate Scoring Rubric

DEBATE SCORING RUBRIC:

CATEGORY                    | SCORE (1-10) | NOTES
----------------------------|-------------|------
CONTENT (40%):
  Evidence quality          | ___/10      |
  Argument logic            | ___/10      |
  Depth of analysis         | ___/10      |
  Counterargument handling  | ___/10      |

DELIVERY (30%):
  Clarity of expression     | ___/10      |
  Organization/structure    | ___/10      |
  Pacing and time management| ___/10      |

STRATEGY (30%):
  Clash (engaging opponent) | ___/10      |
  Weighing (why your args matter more) | ___/10 |
  Framing (controlling the narrative)  | ___/10 |

TOTAL: ___/100

STRENGTHS:
  1. [What worked well]
  2. [What worked well]

AREAS FOR IMPROVEMENT:
  1. [Specific improvement with example]
  2. [Specific improvement with example]

RECOMMENDED PRACTICE:
  - [Specific drill or exercise]

Self-Assessment After Practice

POST-DEBATE SELF-ASSESSMENT:

Did I...
  [ ] State my position clearly in the first 30 seconds?
  [ ] Support each claim with specific evidence?
  [ ] Address my opponent's strongest arguments (not just weak ones)?
  [ ] Avoid logical fallacies in my own reasoning?
  [ ] Identify fallacies in my opponent's reasoning?
  [ ] Manage my time effectively (not rushing or running out)?
  [ ] Stay calm and composed under pressure?
  [ ] Use signposting ("First... Second... Therefore...")?
  [ ] Conclude with a clear summary of why I win?

My strongest moment: _______________
My weakest moment: _______________
One thing I'll practice next time: _______________

Practice Drills

Drill: Argue Both Sides

EXERCISE: ARGUE BOTH SIDES

Topic: [Choose a debatable topic]

STEP 1: Write the strongest 3-point argument FOR the position (5 min)
  1. [Argument + evidence]
  2. [Argument + evidence]
  3. [Argument + evidence]

STEP 2: Write the strongest 3-point argument AGAINST the position (5 min)
  1. [Argument + evidence]
  2. [Argument + evidence]
  3. [Argument + evidence]

STEP 3: Identify which side has the stronger case and WHY (2 min)
  Stronger side: ___
  Key reason: ___

BENEFIT: Forces you to understand both perspectives deeply

Drill: Rapid Rebuttal

EXERCISE: 60-SECOND REBUTTALS

Read the following argument, then respond in 60 seconds:

Argument: "[Statement to rebut]"

Your rebuttal must include:
  1. Acknowledge the point (avoid straw man)
  2. Identify the flaw (evidence, logic, or significance)
  3. Present your counter with evidence
  4. Explain why your counter matters more

Timer: 60 seconds. Go.

See Also

Frequently asked questions

What does the Debate Practice Coach AI skill do?

Interactive debate and argument practice with structured feedback, counterargument generation, logical fallacy identification, and scoring rubrics. Use when preparing for debates, improving persuasion skills, or practicing argumentation.

Why use Debate Practice Coach on TypingMind?

Because you install it once and use it with any model. Debate Practice Coach 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 Debate Practice Coach in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/travisjneuman/.claude/tree/master/skills/debate-practice-coach. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Debate Practice Coach?

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 Debate Practice Coach?

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

Is the Debate Practice Coach AI skill free?

Yes. It is published on GitHub by travisjneuman under the MIT license. 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 👇