adversarial-debate

Simulates a structured debate with three personas to help make difficult decisions. Use when the user says "help me decide", "weigh the options", "debate this", "pros and cons", or invokes /adversarial-debate. Best for architectural decisions with significant tradeoffs, technology or framework choices, and design decisions where reasonable people disagree. Skip for trivial decisions or when there's an obviously correct answer.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "adversarial-debate" with this command: npx skills add ameistad/agent-skills/ameistad-agent-skills-adversarial-debate

Adversarial Debate

Helps you make better decisions on difficult tradeoffs by simulating a structured debate between three personas.

The Court

  • Albert: Argues IN FAVOR of the proposal. Skilled, knowledgeable, and fair.
  • Bart: Argues AGAINST the proposal. Skilled, knowledgeable, and fair.
  • Jeff: The judge who rules after hearing both sides. Impartial and thorough.

How It Works

  1. If the user hasn't provided a topic, ask: "What decision or proposal would you like me to debate?"
  2. Once you have the topic, run the full debate automatically
  3. Present the ruling with clear reasoning

Debate Structure

Run through these rounds without interruption:

Round 1: Opening Arguments

  • Albert presents the case FOR the proposal
  • Bart presents the case AGAINST the proposal

Round 2: First Rebuttal

  • Albert responds to Bart's arguments
  • Bart responds to Albert's arguments

Round 3: Second Rebuttal

  • Albert addresses remaining counterpoints
  • Bart addresses remaining counterpoints

Round 4: Final Statements

  • Albert gives closing argument and must acknowledge the strongest point Bart made
  • Bart gives closing argument and must acknowledge the strongest point Albert made

Round 5: Ruling

  • Jeff delivers the verdict, explaining:
    • Which arguments were most compelling and why
    • What factors were decisive
    • The final ruling (for or against, or a nuanced middle ground if appropriate)

Output Format

Use clear headers for each speaker:

## Opening Arguments

**Albert (For):** [argument]

**Bart (Against):** [argument]

## First Rebuttal
...

## Ruling

**Jeff:** [verdict with reasoning]

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

lucia-auth

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

no-rot

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

vercel-composition-patterns

React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.

Repository Source
86.3K23Kvercel
Automation

vercel-react-native-skills

React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.

Repository Source
60.6K23Kvercel