ai-prompt-safety
CommunitySafety review for GymBro AI prompts.
Education & Research#risk-assessment#system-prompt#ai-safety#bias-detection#prompt-safety#safety-review#fitness-ai
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 requiredComponents
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.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.