forgiveness-confirmation-and-prevention

Community

Require deliberate intent for destructive actions.

AuthorHDeibler
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill prevents users from making irreversible, high-stakes mistakes by calibrating confirmation and structural prevention so the risk is neither ignored nor met with confirmation fatigue.

Core Features & Use Cases

  • Stakes-aware confirmation: Choose none, light, medium, strong type-to-confirm, or re-authentication based on irreversibility and severity.
  • Type-to-confirm as anti-autopilot: Require users to actively verify intent (e.g., typing the resource name) and keep the confirm action disabled until valid.
  • Structural prevention when possible: Make wrong actions impossible via disabled actions, constrained inputs, restricted selection, and required-field blocking.

Quick Start

Use this skill to design a confirmation flow for deleting a project where the action is irreversible and high-stakes, including a clear consequence statement and a type-to-confirm pattern to break autopilot.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: forgiveness-confirmation-and-prevention
Download link: https://github.com/HDeibler/universal-design-principles/archive/main.zip#forgiveness-confirmation-and-prevention

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.