Accessibility Review

Trust Score 81/100

Audit designs and pages for WCAG 2.1 AA issues (contrast, keyboard, labels, focus, touch targets) and produce prioritized, actionable fixes.

triggers:accessibility reviewa11y auditwcagcontrast checkkeyboard walkthroughscreen reader test

GitHub SKILL.md

What it does

Performs a structured accessibility audit focused on WCAG 2.1 AA. It walks through automated contrast and structure checks, a keyboard-only walkthrough, and a screen reader pass to produce a grouped findings report with severity, affected elements, WCAG criteria, and recommended fixes. Output includes a summary, color-contrast table, keyboard walkthrough notes, and top priority fixes.

When to use it

Use during design reviews, pre-engineering handoff, or QA to catch accessibility regressions early. Trigger when shipping new UI components, landing pages, forms, or any modal/dialog flows. Good for teams wanting a repeatable checklist for WCAG AA readiness.

What's included

Scripts: none indicated in the repo for this skill (has_scripts=false)
References: none included in skill folder (has_references=false)
Instructions: step-by-step testing approach (automated contrast scan, keyboard navigation, screen reader pass, zoom to 200%), common issues to check first, and deliverable format (summary, findings, priority fixes).

Compatible agents

Best used by agents with web-audit or UI testing capabilities (e.g., agents that can run contrast checks, simulate keyboard navigation, or integrate with NVDA/VoiceOver).

Audit Summary

Accessibility review skill that guides agents through WCAG 2.1 AA audits of designs and pages. Well-structured content with clear quick-reference, common issues checklist, testing approach, and output format. No scripts bundled — purely instructional. Useful for design review workflows but narrowly scoped to accessibility checking rather than general-purpose.

Watch Out

No scripts — purely instructional, relies entirely on agent interpretation
No frontmatter metadata beyond name/description (no triggers, version, author)

Notes

Clean skill with no security concerns. Content is thorough and well-organized for its niche. Architecture is basic — single SKILL.md with no scripts/ or references/ directories, minimal frontmatter. Quality is good but limited by lack of executable validation; the skill depends entirely on the agent's ability to interpret WCAG guidelines.

Information

Repository: crew44
Stars: 229

Trust Score

Overall81

Security100

Code Quality72

Architecture48

Usefulness65

Related Skills

Starlark Dev

Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.

Run Execute

Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati

Scientific Schematics & Diagrams

Generate publication-quality scientific diagrams via AI with iterative quality review and smart regeneration for journal, conference, poster, and presentation o

Alpha Forge Pre-Ship Quality Gates

Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.

Colorize (Strategic UI Color)

Introduce purposeful color into monochromatic or dull interfaces to improve hierarchy, meaning, and emotional warmth while preserving accessibility.

OpenTestAI

Automated, high-confidence AI testing: bug detection, persona feedback, and prioritized test-case generation using many specialized tester profiles.

Shopify Store Audit

Structured, page-by-page audit of Shopify storefronts to find conversion blockers and prioritized fixes for copy, UX, trust signals, and checkout friction.

Blender Build-Go (bgo)

Automate build → remove → install → enable → launch cycle for Blender extensions or add-ons to speed up iteration and CI workflows.

Back to Skills