ai-prompt-safety

Community

Safety review for GymBro AI prompts.

Authorjperezdelreal
Version1.0.0
Installs0

System Documentation

What problem does it solve?

GymBro's AI coach can generate responses that may be unsafe, biased, or medically inappropriate. This Skill provides a structured safety review framework to assess prompts and system instructions and ensure responses align with safety guardrails.

Core Features & Use Cases

  • Safety assessment: evaluates prompts, responses, and system prompts against explicit guardrails and risk signals.
  • Bias and boundary checks: detects potential bias and enforces appropriate boundaries for different user contexts.
  • Transparency and guidance: ensures the AI explains its reasoning where appropriate and provides safe, compliant alternatives.

Quick Start

Provide a safety review report for a given GymBro AI coach prompt and system instruction, highlighting risks, biases, guardrails, and recommended mitigations.

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: ai-prompt-safety
Download link: https://github.com/jperezdelreal/GymBro/archive/main.zip#ai-prompt-safety

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.