antislop-human

Validates UI accessibility for contrast, keyboard navigation, focus states, and mobile zoom.

1|Updated Aug 29, 2026
One-click install
npx skills add https://github.com/IzzatFirdaus/task-enterprise-api --skill antislop-human-izzatfirdaus
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: antislop-human
Source: https://github.com/IzzatFirdaus/task-enterprise-api/tree/main/.gemini/skills/antislop-human
Command: npx skills add https://github.com/IzzatFirdaus/task-enterprise-api --skill antislop-human-izzatfirdaus

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated interfaces frequently ship with accessibility defects: low-contrast text, removed focus outlines, mouse-only interactions, and missing loading or error states. This Skill gives coding agents concrete rules and a deterministic contrast checker so UI work meets WCAG AA instead of relying on guesswork. ## Core Features & Use Cases - Contrast Verification: Ships a Python script (contrast-check.py), the WCAG 2.x luminance formula, and a precomputed reference table to verify text and non-text color pairings against 4.5:1 and 3:1 thresholds, plus an MCP stdio server exposing the checker as a tool. - Keyboard and Focus Rules: Enforces reachable tab order, visible focus indicators, Escape-closable dialogs, and forbids outline: none without a replacement. - State and Mobile Checks: Requires perceivable empty, loading, and error states, 200% text zoom without clipping, and inputs that stay visible above the on-screen keyboard. - Use Case: While building a dashboard, an agent pairs #777777 text on a white background; running the checker reports 4.48:1, failing normal text, so the agent darkens the color before shipping. ## Quick Start Ask the agent to review your UI code with the antislop-human checklist and run the contrast checker on every text and background color pairing.

Frequently Asked Questions about antislop-human

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

FAQPage Schema
How do I check WCAG color contrast ratios from the command line?▼

Run the bundled Python script with two hex colors, for example python3 contrast-check.py "#FFFFFF" "#777777". It prints the contrast ratio and PASS or FAIL verdicts for normal text at 4.5:1 and large text at 3:1, exiting nonzero when either fails.

What contrast ratio does WCAG AA require for text?▼

WCAG AA requires 4.5:1 for normal text and 3:1 for large text at 18px or larger. Non-text UI components such as button borders, icons, and focus indicators must meet 3:1 against adjacent colors per WCAG 1.4.11.

Can I use the contrast checker as an MCP tool?▼

Yes, the skill includes contrast-mcp.py, a minimal MCP stdio server exposing a check_contrast tool. It accepts foreground and background hex colors and returns the ratio plus pass or fail verdicts for both text sizes as JSON.

Why does grey text on white backgrounds often fail accessibility checks?▼

The eye overestimates contrast on grey pairs, so combinations like #777777 on white measure only 4.48:1 and fail the 4.5:1 normal-text threshold. Always compute the ratio with the formula or script instead of judging by appearance.

Does the contrast checker require any Python packages?▼

No, both scripts use only the Python standard library. The checker works standalone, and if the script file is unavailable the documented formula and reference table in the skill are sufficient on their own.