Sensitivity Check

What it does

This skill, jwynia-sensitivity-check, analyzes text for potentially offensive or biased language. It identifies problematic phrases and suggests alternative wording to promote inclusivity and respect. The tool aims to improve the safety and ethical considerations of AI generated content by flagging sensitive topics and offering revisions.

When to use it

• Content Creation: Before publishing blog posts, articles, or marketing materials generated by an AI agent.
• Chatbot Training: To ensure a chatbot's responses are appropriate and avoid causing offense to users.
• Scriptwriting: Reviewing scripts for movies, games, or other media to identify and mitigate potential harm.
• Educational Materials: Checking educational content for bias or stereotypes that could negatively impact learners.

Key capabilities

• Offensive language detection
• Bias identification
• Alternative wording suggestions
• Sensitivity scoring (implied)

Example prompts

• "Check this paragraph for potentially offensive language: [paste text here]"
• "Can you analyze this chatbot response and suggest improvements to avoid bias? [paste response here]"
• "Review this script excerpt for sensitivity concerns. [paste script excerpt here]"

Tips & gotchas

The skill's effectiveness depends on the quality of its training data; it may not catch all nuanced forms of offensive language or cultural sensitivities. Always review the suggested changes critically and consider the specific context.