Back to Skills

curriculum-review-bias

majiayu000
Updated Today
58
9
58
View on GitHub
Designdesign

About

This Claude Skill analyzes educational content to detect bias, stereotypes, and non-inclusive language, ensuring cultural responsiveness and equity. It reviews curriculum materials like lessons and assessments, providing actionable recommendations for inclusive alternatives. Developers can activate it with prompts like "check for bias" or "review inclusivity" for a given educational level.

Quick Install

Claude Code

Recommended
Plugin CommandRecommended
/plugin add https://github.com/majiayu000/claude-skill-registry
Git CloneAlternative
git clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/curriculum-review-bias

Copy and paste this command in Claude Code to install this skill

Documentation

Bias Detection & Inclusive Language Review

Analyze curriculum materials to identify bias, stereotypes, cultural assumptions, and barriers; recommend inclusive, equitable alternatives.

When to Use

  • Review content for bias and stereotypes
  • Check inclusive language use
  • Ensure cultural responsiveness
  • Validate equitable representation
  • Assess fairness in assessment items

Required Inputs

  • Curriculum Materials: Any content to review (lessons, assessments, multimedia)
  • Educational Level: K-5 through post-graduate
  • Student Demographics (optional): Known diversity characteristics

Workflow

1. Load Materials for Analysis

Read all content including:

  • Instructional text
  • Examples and scenarios
  • Assessment items
  • Images and media descriptions
  • Names and characters used

2. Scan for Bias Categories

Gender Bias:

  • ❌ Gender stereotypes (e.g., "nurses are women", "engineers are men")
  • ❌ Gendered language (e.g., "chairman", "mankind")
  • ❌ Assuming binary gender
  • ❌ Unequal representation in examples
  • ✅ Gender-inclusive language ("chairperson", "humanity")
  • ✅ Balanced representation across genders

Racial/Ethnic Bias:

  • ❌ Stereotypical associations
  • ❌ Tokenism (single representative)
  • ❌ Cultural assumptions
  • ❌ Eurocentric perspectives only
  • ✅ Diverse representation
  • ✅ Multiple cultural perspectives
  • ✅ Respectful, accurate portrayals

Socioeconomic Bias:

  • ❌ Assuming resources/privilege (e.g., "have your parents drive you", "use your home computer")
  • ❌ Stigmatizing poverty
  • ❌ Examples only accessible to wealthy
  • ✅ Awareness of varied economic situations
  • ✅ Accessible alternatives provided

Ability Bias (Ableism):

  • ❌ Using disability as metaphor (e.g., "turn a blind eye", "fell on deaf ears")
  • ❌ Assuming physical abilities
  • ❌ Negative framing of disabilities
  • ✅ Person-first or identity-first language (contextually appropriate)
  • ✅ Disability included neutrally when relevant

Age Bias:

  • ❌ Stereotypes about age groups
  • ❌ Dismissive of any age
  • ✅ Age-appropriate without being patronizing
  • ✅ Respectful of all ages

Religious/Cultural Bias:

  • ❌ Assuming dominant religion
  • ❌ Religious holidays as universal
  • ❌ Cultural practices as "weird" or "exotic"
  • ✅ Secular examples or multi-faith
  • ✅ Cultural practices presented respectfully

Geographic Bias:

  • ❌ Urban-only or rural-only assumptions
  • ❌ US-centric examples (if international audience)
  • ❌ Assuming specific regional knowledge
  • ✅ Diverse geographic contexts
  • ✅ Explain regional references

Linguistic Bias:

  • ❌ Mocking non-standard dialects
  • ❌ Assuming English fluency
  • ❌ Complex idioms without explanation
  • ✅ Clear, accessible language
  • ✅ Support for multilingual learners

3. Analyze Representation

Count and assess:

Character/Example Diversity:

  • Names used: [Analyze cultural diversity]
  • Roles depicted: [Analyze who does what]
  • Authority figures: [Who holds power/expertise]
  • Problem-solvers: [Who finds solutions]

Target: No single group always in leadership, expertise, or success roles; No single group always needing help or failing

4. Review Assessment Items for Fairness

Check each item for:

  • Cultural Load: Does success require specific cultural knowledge unrelated to the objective?
  • Language Barriers: Is unnecessary complex vocabulary used?
  • Scenario Bias: Do examples disadvantage specific groups?
  • Stereotype Threat: Could wording trigger identity-based anxiety?

5. Generate Bias Review Report

# Bias & Inclusivity Review: [TOPIC]

**Review Date**: [Date]
**Materials Reviewed**: [List]
**Diversity Lens**: Gender, Race/Ethnicity, SES, Ability, Age, Religion/Culture, Geography, Language

## Executive Summary

**Overall Rating**: [Excellent | Good | Needs Revision | Poor]

**Critical Issues**: [Count]
**Moderate Concerns**: [Count]
**Recommendations**: [Count]

**Readiness**: [Ready | Minor revisions | Major revisions]

## Bias Findings by Category

### Gender Bias

**Issues Found**: [Count]

**Critical** (Must Fix):
1. [Location]: "[Problematic text]"
   - **Problem**: [Explanation]
   - **Recommendation**: "[Suggested replacement]"

**Moderate** (Should Fix):
1. [Location]: "[Problematic text]"
   - **Problem**: [Explanation]
   - **Recommendation**: "[Suggested alternative]"

### Racial/Ethnic Bias

[Same structure]

### Socioeconomic Bias

[Same structure]

### Ability Bias

[Same structure]

### Age, Religious, Geographic, Linguistic Bias

[Same structure for each]

## Representation Analysis

### Names Used

| Name | Cultural Origin | Role/Context | Issue |
|------|----------------|--------------|-------|
| John | Anglo-American | Doctor (authority) | Part of pattern: only Anglo names in authority |
| Maria | Latina | Patient (receiving help) | ⚠️  Pattern concern |
| Li Wei | Chinese | Student (struggling) | ❌ Stereotype reinforcement |

**Analysis**: Names show pattern of Anglo individuals in authority, others needing help. Reinforces problematic hierarchies.

**Recommendation**: Diversify authority figures—include Maria as doctor, Li Wei as expert, etc.

### Role Distribution

| Role Type | Gender | Race/Ethnicity | Pattern Issue |
|-----------|--------|----------------|---------------|
| Doctor (3 examples) | Male (3) | White (3) | ❌ No diversity |
| Teacher (4 examples) | Female (4) | White (3), Asian (1) | ⚠️  Gender stereotype |
| Scientist (2 examples) | Male (2) | White (2) | ❌ No diversity |

**Recommendation**: Balance gender and race across all professional roles

## Assessment Fairness Review

### Item-Level Analysis

**Item MC-1.5**:
- **Text**: "Calculate the cost of a family ski vacation..."
- **Issue**: Assumes familiarity with skiing, family vacations, disposable income
- **Impact**: May disadvantage students from lower SES backgrounds
- **Recommendation**: Use universally accessible scenario: "Calculate the cost of items at a school store..."

**Item ESSAY-2.1**:
- **Text**: "Describe a time your family celebrated a holiday..."
- **Issue**: Assumes stable family structure and holiday celebration
- **Impact**: May be painful/impossible for students in foster care, refugees, non-celebratory families
- **Recommendation**: "Describe a memorable day or event you experienced..."

## Language Accessibility

**Complex/Unclear Language**: [Count]

Examples:
- [Location]: "[Complex phrase]"
  - **Issue**: Grade 10 reading level in grade 6 material
  - **Simplify to**: "[Simpler version]"

**Idioms Needing Explanation**: [List]

**Recommendations**: [Language simplification strategies]

## Positive Findings

**Strengths**:
- ✅ Diverse names used in Unit 2
- ✅ Multiple cultural perspectives in readings
- ✅ Accessible language in most materials
- ✅ Gender-neutral language throughout

## Priority Recommendations

### Priority 1 (Critical—Must Fix)
1. Remove stereotype in Item 3 (Asian student struggling with math)
2. Replace ski vacation scenario with equitable alternative
3. Diversify authority figures in examples

### Priority 2 (Important—Should Fix)
1. Balance gender in professional roles
2. Add cultural context explanations
3. Simplify complex phrases

### Priority 3 (Enhancement)
1. Add more diverse names
2. Include disability representation
3. Expand geographic diversity

## Revision Checklist

- [ ] All critical issues addressed
- [ ] Representation balanced across materials
- [ ] Assessment items culturally fair
- [ ] Language accessible to all students
- [ ] Stereotypes eliminated
- [ ] Multiple perspectives included

---

**Artifact Metadata**:
- **Artifact Type**: Bias Review Report
- **Critical Issues**: [Count]
- **Status**: [Pass/Needs Revision]
- **Next Phase**: Address issues, then Accessibility Review

6. CLI Interface

# Full bias review
/curriculum.review-bias --materials "curriculum-artifacts/"

# Assessment-only review
/curriculum.review-bias --focus "assessments" --items "assessment-items.md"

# Specific bias category
/curriculum.review-bias --focus "gender,race" --content "lessons/*.md"

# Help
/curriculum.review-bias --help

Composition with Other Skills

Input from: All development and design skills

Output to:

  • User for revisions
  • /curriculum.review-accessibility (after bias issues addressed)

Exit Codes

  • 0: No issues found
  • 1: Issues found, revisions needed
  • 2: Cannot load materials
  • 3: Invalid focus specified

GitHub Repository

majiayu000/claude-skill-registry
Path: skills/curriculum-review-bias

Related Skills

content-collections

Meta

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

View skill

creating-opencode-plugins

Meta

This skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.

View skill

langchain

Meta

LangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.

View skill

Algorithmic Art Generation

Meta

This skill helps developers create algorithmic art using p5.js, focusing on generative art, computational aesthetics, and interactive visualizations. It automatically activates for topics like "generative art" or "p5.js visualization" and guides you through creating unique algorithms with features like seeded randomness, flow fields, and particle systems. Use it when you need to build reproducible, code-driven artistic patterns.

View skill