Form Ux

Organization

KyaniteLabs

form-ux

Form UX and accessibility pass. Use for forms, inputs, checkout, signup/login, validation, labels, autocomplete, mobile keyboards, inline errors, required fields, disabled submits, and field-level accessibility.

Overview

Publisher	KyaniteLabs
Repository	`tastecheck`
Skill name	`form-ux`
Stars	10
Forks	7
Bundled files	3
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.
3 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 Form Ux 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/form-ux
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/form-ux .claude/skills/form-ux

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

Use it in TypingMind

Enable Form Ux 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 Form Ux 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 Form Ux 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.

Form UX

A form is a completion path: reduce effort, prevent predictable errors, and make failure truthful, repairable, and accessible.

Model task before styling

Start with outcome, risk, and data authority, not an inherited input array. Remove, defer, or explain each field through this contract:

Field contract	What to decide
User value	What completing this field unlocks now, in the user's words
Data rule	Required/optional condition, source of truth, and whether the rule is client- or server-owned
Input affordance	Label, type, inputmode, autocomplete, format help, and a safe example
Validation moment	What can be checked while editing, on blur, on submit, or only after a server request
Recovery	Exact message, preserved value, focus destination, and next available action
Sensitivity	Whether the field is personal, financial, irreversible, or must never be persisted locally

Unknown rule/ownership stays unresolved; never invent validation; group by task, not database/API shape.

Non-negotiables

Persistent associated label; visible required/optional state; correct type, inputmode, autocomplete, and one-column task flow (short related pairs excepted).
Validate on submit. Validate on blur only when the value is complete enough to judge; after an error, re-check while the person repairs it. Keep server truth server-owned.
Put specific adjacent “what + fix” errors behind aria-invalid/aria-describedby; announce and focus the first error on failed submit.
Never silently disable submit; retain visible focus and explain what is missing.

Error-message formula

Use [what is wrong] + [how to fix it] (+ example), plainly and without blame. Tie it visually/programmatically to the field; long-form summaries link to inline errors.

Validation is a conversation

Give feedback at the earliest truthful moment; browser checks never impersonate server truth. On submit distinguish field errors (focus/retain), conflict (correct branch), transient failure (preserved draft/safe retry), authorization (boundary/route), and irreversible payment (duplicate lock plus receipt/status). Pending work has accessible label/status, rejects duplicates, and restores an explained route on failure. Ignore stale responses so older validation cannot overwrite current value.

Worked contract

Field	Rule owner	When to check	Repair path
Email	server owns account availability; client owns basic shape	submit; blur after a complete address; re-check while repairing	“Enter an address like name@example.com.” Preserve the value; announce an account conflict only after the server responds.

The row separates local affordance from server authority. Apply it to cross-field rules, invitation codes, inventory, pricing, and payment status.

Quick-start

Use references/patterns.md for markup/wiring; retain this field contract.

Reduce effort

Ask only necessary fields; defer optional data. Use safe defaults/autofill, nonblocking formatting, password reveal/paste, inline help, preserved input, and saved progress.

Reference files

references/patterns.md — types, validation, mobile/autofill, and a11y wiring.
references/decision-records.md — novel-case ADR rules.

Evidence

Establish task, fields, rule owner, success/risk/interruption before styling. Record each field/state, validation owner, and recovery; n/a needs subject absence, not unknown rule.

Self-check

Field contract, labels, required state, types/autofill, and keyboard/screen-reader wiring complete?
Submit/blur/repair timing, stale async responses, specific adjacent errors, first-error focus, and retained input work?
No silent disabled submit; pending, duplicate, conflict, authorization, and irreversible outcomes differ?

How to deliver

Deliver one field/state matrix with source rule, affordance, owner/timing, recovery, pending behavior, evidence, and risk; hand adjacent concerns to their skills.

Contract (generated)

Canonical detail: contract.json.

Route: A form has completion, validation, recovery, autofill, or interruption problems.; avoid: The issue is only a control's visual interaction state.
Exclude: Do not hide errors or validate only on blur without a recovery path. (+1 in contract.json)
Stop / handoff: Stop when validation rules or data ownership are unknown. (+1 in contract.json); receives [component-states, design-system-interview, deslop-ui, humanize-copy, responsive-layout, spacing-system, tasteroll] -> sends [a11y-pass, i18n-ready, tastecheck-pass, cognitive-a11y]
Output: completion-oriented form flow and evidence table
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 Form Ux AI skill do?

Why use Form Ux on TypingMind?

Because you install it once and use it with any model. Form Ux 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 Form Ux in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/KyaniteLabs/tastecheck/tree/main/skills/form-ux. 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 Form Ux?

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 Form Ux?

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

Is the Form Ux 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

Simple English

NousResearch

OrganizationPopular

Rewrite text to ASD-STE100 Simplified Technical English.

Watchers

Poll RSS, JSON APIs, and GitHub with watermark dedup.

Karpathy Guidelines

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define…

Create Agent

Create a custom agent (.agent.md) for a specific job.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Form UX

Model task before styling

Non-negotiables

Error-message formula

Validation is a conversation

Worked contract

Quick-start

Reduce effort

Reference files

Evidence

Self-check

How to deliver

Contract (generated)

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now