How to use the Inclusive Language Checker agent skill

What does the inclusive-language skill make the agent do?

The skill focuses on wording. When it applies, the agent reviews content for ableist language such as "crazy", "lame" and "blind to", for gendered assumptions such as defaulting to "he" or "she", for cultural bias and for exclusionary terminology. It also checks that error messages and instructions are respectful and constructive.

When it finds a problem, the skill guides the agent to propose a replacement. Examples from the source include "they", "users" and "people" in place of gendered defaults, and error messages that guide the user rather than blame them.

• Ableist terms: replace with neutral alternatives (for example "crazy" becomes "unexpected" or "intense")
• Gendered defaults: use "they", "users" or "people"
• Idioms: avoid ones that may not translate across cultures
• Error messages: guide rather than blame

How do I install the inclusive-language skill?

Download the ZIP for this skill from this page and unzip it. You can then put the skill folder in one of two places: your personal skills folder at ~/.claude/skills/, or a project's .claude/skills/ folder if you want it available only for that project.

Alternatively, upload the skill in the Claude apps under Settings → Capabilities → Skills.

• Personal install: unzip into ~/.claude/skills/
• Project install: unzip into the project's .claude/skills/ folder
• Claude apps: Settings → Capabilities → Skills, then upload

How do I trigger the skill with a natural request?

You do not need a special command. The skill's description tells the agent when to use it, so ask for what you need in plain language. The skill is aimed at reviewing text and interface content, so paste the copy or describe the screen and say what you want checked.

The description also mentions reviewing rendered HTML and interactive components. Treat that as a secondary use, because the skill's content is mostly about wording.

• "Check this button label and error message for inclusive language."
• "Review this onboarding copy for gendered wording and suggest neutral alternatives."
• "Is the word 'crazy' or 'lame' used anywhere in this page text?"

What does a typical review look like?

Paste the text you want reviewed. The agent checks it against the points above and returns the flagged phrases with proposed neutral or constructive rewrites. Read each suggestion in context, since a word that is fine in one sentence may need a different fix in another.

For error messages, ask for a version that explains what happened and what to do next, without blaming the user. The source's own examples show the same pattern: replace ableist terms with plain, neutral words.

What does the skill need, and is it safe to run?

The skill lists no required dependencies. It does not run scripts and does not use the network, according to its listing. It is a set of instructions and reference material that the agent reads.

The package contains two files: SKILL.md, which holds the checklist, and references/rule.md, which holds more detail and examples, including a table of ableist terms and alternatives. Because it does not run code, the main thing to review is the wording the agent produces before you publish it.

• Dependencies: none listed
• Scripts: none
• Network access: none

What are the limits of this skill?

This is a general style checklist for wording. It is not a legal or compliance review and does not replace one. It is also not a deep accessibility audit: the description mentions keyboard behaviour, focus flow, accessible names and screen-reader output, but the skill's content covers those only briefly.

For translated or localised content, cultural nuance needs judgement from a native speaker. Use the skill as a fast first pass, then have people with the right expertise check the result.

• Not a substitute for legal or compliance sign-off
• Not a detailed keyboard, focus or screen-reader audit
• Not suited to translation or localisation decisions on its own