---
name: hashgraph-online/ethical-persuasion-design
source: https://app.decimal.ai/s/hashgraph-online-ethical-persuasion-design@1/SKILL.md
source_sha256: 1c7a12cebd4f
---

# Ethical Persuasion Design

Design persuasive requests by matching a real user benefit with truthful cues that help the audience decide. Use Influence principles as evidence-routing tools, not as shortcuts to bypass judgment.

## Quick Start

1. Read `guidelines.md` to choose the smallest useful reference set.
2. Load `references/persuasion/knowledge.md` for concepts and `references/persuasion/rules.md` for operating rules.
3. Use `workflows/design-persuasive-request.md` for repeatable tasks.
4. For audits, surface both the active influence cue and the ethical rewrite.

## Contents

| File | Purpose |
| --- | --- |
| references/persuasion/knowledge.md | Core concepts and source-grounded definitions |
| references/persuasion/rules.md | Rules, boundaries, and practical guidelines |
| references/persuasion/examples.md | Bad/better examples for applied situations |
| references/persuasion/smells.md | Red flags and anti-patterns to detect |
| references/persuasion/checklist.md | Fast review checklist |
| workflows/design-persuasive-request.md | Create persuasive messaging that is useful, credible, and agency-preserving. |

## Operating Principles

- Use only honest evidence. Do not invent popularity, scarcity, credentials, endorsements, or social connection.
- Separate helping a good decision from pushing a shortcut response. If the cue is counterfeit, treat it as a red flag.
- When rewriting, preserve user agency: add context, alternatives, and enough time to decide when stakes are meaningful.

## Output Pattern

1. **Diagnosis** - name the influence principle or cue.
2. **Evidence Check** - state what proof supports or is missing from the cue.
3. **Risk** - explain manipulation, trust, or decision-quality risk.
4. **Rewrite or Recommendation** - provide an ethical alternative.

## Validation

Use the prompts in `evals/evals.json` as smoke tests. A good result identifies the relevant Influence principle, preserves user agency, and avoids fabricated evidence or coercive pressure.