Back to Skills

trust-and-recovery

verified

Use when designing error handling, confirmation dialogs, undo functionality, or any interaction where user trust matters. Covers building confidence through predictability and graceful failure.

View on GitHub

Marketplace

agi-marketplace

bfmcneill/agi-marketplace

Plugin

ux

Repository

bfmcneill/agi-marketplace

ux/skills/trust-and-recovery/SKILL.md

Last Verified

January 21, 2026

Install Skill

Select agents to install to:

Scope:
npx add-skill https://github.com/bfmcneill/agi-marketplace/blob/main/ux/skills/trust-and-recovery/SKILL.md -a claude-code --skill trust-and-recovery

Installation paths:

Claude
.claude/skills/trust-and-recovery/
Powered by add-skill CLI

Instructions

# Trust and Recovery

Trust is built through predictability and tested through failure. Users trust systems that behave consistently and recover gracefully when things go wrong.

## Evidence Tiers

```
[Research]   — Peer-reviewed studies, controlled experiments
[Expert]     — Nielsen Norman Group, recognized UX authorities
[Case Study] — Documented examples from major products
[Convention] — Industry practice, limited formal validation

Multiple tags = stronger evidence: [Research][Expert]
Mixed findings noted as: [Research — Mixed]
```

---

## Research Foundations

### Peak-End Rule

**[Research][Expert]** Daniel Kahneman's research (Nobel Prize in Economics, 2002) established that people judge experiences based on:

1. The **peak** moment (most intense, positive or negative)
2. The **end** (how it concluded)

They do not average the entire experience.

**UX implication:** A single graceful recovery can redeem an otherwise frustrating experience. Don't let the last interaction be an error.

**Source:** Kahneman, D. (1999). Objective happiness. In *Well-being: Foundations of hedonic psychology*.

### Loss Aversion

**[Research][Expert]** Kahneman & Tversky's Prospect Theory showed losses feel approximately 2x as painful as equivalent gains feel good.

**UX implication:** Users are highly motivated to avoid losing their work. Auto-save, undo, and data preservation are disproportionately important.

**Source:** Kahneman, D. & Tversky, A. (1979). Prospect Theory: An Analysis of Decision under Risk.

---

## Undo vs. Confirmation Dialogs

**[Expert]** Nielsen Norman Group and multiple UX authorities recommend undo over confirmation dialogs in most cases.

### Why Confirmation Often Fails

**[Expert]** From NNg and practitioner observation:
- Users habitually click "OK" without reading
- Frequent confirmations train users to ignore them
- Confirmations interrupt flow

### When to Use Each

| Approach | Use When | Evidence |
|----------|----------|----------|
| **Undo**

Validation Details

Front Matter
Required Fields
Valid Name Format
Valid Description
Has Sections
Allowed Tools
Instruction Length:
6528 chars