Avoid sensory-only instructions

SkillMedia

sensory-instructions is a skill for AI agents that reviews rendered HTML, interactive components, and design-system patterns for sensory-only instructions, such as cues that rely only on color, shape, or position. It checks native semantics first, then inspects keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.

Available today. Use it from your connected AI after setup.

Have an AI agent that can load skills.

Then ask your AI: use the Avoid sensory-only instructions skill

What your AI can do with it

  • Reviews rendered HTML for sensory-only instructions
  • Checks interactive components and design-system patterns
  • Inspects native semantics before other checks
  • Examines keyboard behavior and focus flow
  • Verifies accessible names
  • Reviews screen-reader output where relevant

Getting started

  1. Have an AI agent that can load skills.
  2. Add the sensory-instructions skill to the agent's available skills.
  3. Ask the agent to review rendered HTML, interactive components, or design-system patterns for sensory-only instructions.

What this skill tells your AI

The instructions your AI receives, as published by thedaviddias/front-end-checklist in skills/sensory-instructions/SKILL.md and read by ahel’s review.

Color-blind users can't see 'click the red button,' screen reader users can't perceive 'the menu on the right,' and deaf users miss audio cues—multi-modal instructions include everyone.

Quick Reference

  • Don't use color alone to convey information (red=error)
  • Add text labels to shape and location references
  • Provide visual alternatives for audio cues
  • Combine multiple cues so all users can understand

Check

Review instructions and verify they don't rely only on color ('click the red button'), shape ('the circular icon'), location ('the menu on the right'), or sound ('when you hear the beep'). Ensure text labels supplement visual cues.

Fix

Add text labels to visual instructions. Instead of 'click the green button', use 'click the Submit button (green)'. Combine multiple cues so users who cannot perceive one can still understand via another.

Explain

Explain how color-blind users cannot distinguish color-only cues, screen reader users cannot perceive location or shape, and deaf users miss audio-only signals, making multi-modal instructions essential.

Code Review

Review the rendered markup and interactive states that affect Avoid sensory-only instructions. Flag exact elements, roles, labels, focus behavior, or keyboard interactions that violate the rule, and note how to verify the fix with browser accessibility tooling or assistive tech.


For full implementation details, code examples, and framework-specific guidance, see references/rule.md.

Rule page: https://frontendchecklist.io/en/rules/accessibility/sensory-instructions

Signals

GitHub stars
74k
Forks
7k
Last commit
Aug 2026

Questions

What does it check first?
It checks native semantics first, then inspects keyboard behavior, focus flow, accessible names, and screen-reader output where relevant.
When should it be used?
Use it when reviewing rendered HTML, interactive components, or design-system patterns related to avoiding sensory-only instructions.
What kinds of problems does it catch?
Cues that rely only on color, shape, or position, which can confuse users who cannot perceive those attributes.
Advanced
Item type
skill
Key
sensory-instructions
Source
github.com/thedaviddias/front-end-checklist