harm-aware-editor

Review and rewrite text to reduce discrimination, stigma, and retraumatization risks.

Updated Aug 22, 2026
One-click install
npx skills add https://github.com/JustinChangTW/ai-skills-core --skill harm-aware-editor-justinchangtw
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: harm-aware-editor
Source: https://github.com/JustinChangTW/ai-skills-core/tree/main/skills/06-writing-editing/harm-aware-editor
Command: npx skills add https://github.com/JustinChangTW/ai-skills-core --skill harm-aware-editor-justinchangtw

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve? Texts such as announcements, customer service scripts, surveys, and technical documentation often contain discriminatory labels, stereotypes, stigmatizing wording, or trauma-triggering phrasing that harms readers and communities. This Skill audits such text for inclusive-language and trauma-informed risks, then produces usable rewrites with clear reasoning instead of mechanical word swaps. ## Core Features & Use Cases - Risk-Graded Text Review: Locates specific problematic phrases, classifies them by risk category (labeling, blame, stereotypes, exclusion, retraumatization, historical wounds), and assigns severity levels. - Trauma-Informed Rewriting: Produces ready-to-use rewritten versions that preserve original meaning, precision, and required legal, medical, or technical terminology. - Inclusive Terminology Guides: Builds sensitive-word replacement tables, review checklists, and team inclusive-language guidelines, including technical terms like master/slave and blacklist/whitelist with API compatibility plans. - Use Case: A social services team pastes an announcement saying "these alcoholics are undisciplined and keep missing appointments" and receives a risk summary, a destigmatized rewrite, modification rationale, and items needing community confirmation. ## Quick Start Ask the assistant to review your pasted announcement or document for discriminatory, stigmatizing, or trauma-triggering language and provide an inclusive rewrite with explanations.

Frequently Asked Questions about harm-aware-editor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I check text for discriminatory or stigmatizing language?▼

Paste the text with its intended audience and purpose, and the Skill returns a risk summary locating specific problematic phrases, severity levels, a rewritten version, and the reasoning behind each change. It covers labeling, blame, stereotypes, exclusion, and trauma-related risks.

How do I rewrite content in trauma-informed language?▼

Provide the original text and context, and the Skill produces a trauma-informed rewrite that removes victim-blaming, pressure to disclose, and false safety promises while keeping the original meaning. It also flags items needing confirmation from affected communities or professionals.

Can I replace master/slave and blacklist/whitelist without breaking APIs?▼

Yes. The Skill suggests precise alternatives like primary/replica, controller/worker, or allowlist/blocklist based on your architecture, keeps old field names in code formatting on first mention, and recommends a deprecation plan instead of breaking existing integrations.

Does this Skill determine whether text is legally discriminatory?▼

No. It only performs language-risk analysis and explicitly refuses to issue legal, medical, or psychological conclusions. For compliance determinations, it recommends consulting legal or professional reviewers.

When should I not use inclusive-language review?▼

Skip it for general polishing, plain translation, summarization, or SEO copywriting with no identity, stigma, or trauma concerns. Those tasks belong to general rewriting or translation workflows, and the Skill is designed not to over-trigger on them.