refuse-task

Official

Identify harmful tasks and refuse gracefully.

AuthorThe-Interdependency
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill helps prevent harm and ethical violations by recognizing task requests that trigger categories such as probable harm, canon violations, scope mismatches, or economic exploitation, and refusing them clearly.

Core Features & Use Cases

  • Detects harm signals across medical, legal, financial, safety, and ethical dimensions and declines requests accordingly.
  • Flags scope gaps, missing data, missing authorization, or inappropriate framing, and suggests safe alternatives.
  • Returns a clear, non-judgmental refusal message while offering guidance for safer next steps.

Quick Start

Refuse a clearly misframed or harmful request with a concise, safe alternative.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: refuse-task
Download link: https://github.com/The-Interdependency/a0/archive/main.zip#refuse-task

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.