Cognitive A11y

Organization

KyaniteLabs

cognitive-a11y

Cognitive accessibility pass for ADHD, autism, dyslexia, and neurodivergent users. Use for readability, plain language, predictability, sensory load, memory burden, time pressure, forms, onboarding, dashboards, docs, and flows.

Overview

Publisher	KyaniteLabs
Repository	`tastecheck`
Skill name	`cognitive-a11y`
Stars	10
Forks	7
Bundled files	4
License	MIT
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
4 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by KyaniteLabs on GitHub. Read the source before you install it.

Installation

Install the Cognitive A11y AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/KyaniteLabs/tastecheck/tree/main/skills/cognitive-a11y
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/KyaniteLabs/tastecheck.git /tmp/tastecheck
mkdir -p .claude/skills
cp -r /tmp/tastecheck/skills/cognitive-a11y .claude/skills/cognitive-a11y

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cognitive A11y in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cognitive A11y on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cognitive A11y is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Cognitive Accessibility (ADHD · autism · dyslexia · neurodivergence)

a11y-pass covers mechanical WCAG defects. This pass asks whether someone can read, understand, remember, and finish without avoidable cognitive cost. Profiles are friction lenses, never diagnoses or universal rules.

Non-negotiables (help every profile)

Plain and structured: literal, front-loaded language; short chunks; summaries, visible steps, and progress for long work.
Predictable and low-memory: consistent labels/help; no surprise changes; carry forward information instead of requiring recall.
Calm and readable: controllable motion, no sensory overload, readable ragged-left type (about 1.5 line-height and 45–75ch), and no justified/all-caps blocks.
Forgiving: explain fixes, preserve work, allow pause/extension, and confirm or undo destructive actions.

Profile lenses

Use references/profiles.md. ADHD highlights distraction, progress, and save/resume; autism predictability and sensory control; dyslexia reading support and alternatives to text-only cues. Apply shared rules to every user, including kind, non-judgmental recovery.

Use this skill

Map friction before profiles

Trace one real task through interruption/error and recovery. Record observed friction and demand, a non-diagnostic profile hypothesis, repair, and task-path proof that start, correction, or resume became easier. Make purpose/next action skimmable; externalize memory/progress; preserve work/time control; offer motion, density, and reading support without changing meaning.

Reference files

references/profiles.md — profile-specific barriers and repairs.
references/patterns.md — checkable cross-cutting patterns/examples.
references/decision-records.md — meta-patterns + ADR rules for novel cases.

Self-check (before claiming cognitively accessible)

Plain, chunked, predictable, low-memory content with one clear next action?
Calm, controllable sensory/readability conditions and kind, recoverable errors?
Real path separates observed friction from hypothesis and proves start, recovery, or resume?

How to deliver

Name profiles and concrete moves. This is the cognitive layer; hand technical/WCAG defects to a11y-pass.

Provenance — principle, not property

Grounded in the W3C Cognitive and Learning Disabilities Accessibility Task Force (COGA) "Making Content Usable for People with Cognitive and Learning Disabilities" and established neurodivergent-design practice. Independent synthesis, credited — not copied.

Contract (generated)

Canonical detail: contract.json.

Route: A flow imposes avoidable memory, attention, predictability, reading, or recovery load for ADHD, autistic, dyslexic, or other neurodivergent users.; avoid: The issue is only color contrast, semantic markup, or translation expansion.
Exclude: Do not flatten personality or remove useful complexity without evidence. (+1 in contract.json)
Stop / handoff: Stop when the task context or observed friction is unknown. (+1 in contract.json); receives [improve-existing-website, form-ux, empty-states, theming] -> sends [a11y-pass, humanize-copy, tastecheck-pass]
Output: prioritized cognitive repair ledger preserving product voice
Evidence: table_with_evidence with status, reason, remediation, evidence, provenance.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cognitive A11y AI skill do?

Why use Cognitive A11y on TypingMind?

Because you install it once and use it with any model. Cognitive A11y is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cognitive A11y in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/KyaniteLabs/tastecheck/tree/main/skills/cognitive-a11y. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cognitive A11y?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cognitive A11y?

As many as you like. As long as a model supports skills, you can use Cognitive A11y with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cognitive A11y AI skill free?

Yes. It is published on GitHub by KyaniteLabs under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Gemini

openclaw

OrganizationPopular

Gemini CLI one-shot prompts, summaries, generation, skills, hooks, MCP, or Gemma routing.

Writing Skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Skill Host Compat

Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR.

Brand Voice

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Cognitive Accessibility (ADHD · autism · dyslexia · neurodivergence)

Non-negotiables (help every profile)

Profile lenses

Use this skill

Map friction before profiles

Reference files

Self-check (before claiming cognitively accessible)

How to deliver

Provenance — principle, not property

Contract (generated)

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now