Ux Empty States logo

Ux Empty States

Organization
Uxcel-Lab
ux-empty-states

Design or critique empty states — first-use screens, cleared states, no-results pages, and 404s that explain why the screen is empty and guide the next action instead of dead-ending. Trigger when the user asks to design or review an empty state, blank screen, zero-data view, first-run dashboard, no-results page, or 404 page.

Overview

PublisherUxcel-Lab
Repositoryproduct-skills
Skill nameux-empty-states
Stars
35
Forks
8
Bundled files
Instructions only
LicenseMIT
Links
  • 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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Uxcel-Lab on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Uxcel-Lab/product-skills/tree/main/ux/screens/empty-states
  4. 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.
2

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/Uxcel-Lab/product-skills.git /tmp/product-skills
mkdir -p .claude/skills
cp -r /tmp/product-skills/ux/screens/empty-states .claude/skills/ux-empty-states
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ux Empty States 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 Ux Empty States 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 Ux Empty States 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.

Empty States Skill

How this skill behaves (read first)

This is a generative skill. The default failure mode is the dead screen: "No tasks found." — a blank dead-end at exactly the moment a user is newest, most confused, or most blocked. Every empty state is secretly one of the product's highest-leverage screens: it's onboarding (first use), reassurance (cleared), or recovery (no results / 404). The opposite failure exists too — an "empty" screen so stuffed with text, illustration, and three CTAs that it's no longer calm. This skill gates:

  1. Establish why the screen is empty — the cause picks the pattern.
  2. Apply the always-true core — explain + guide, never blame, stay calm.
  3. Surface the embellishment decisions (illustration, CTAs, humor) with trade-offs.

Then it hands off to ux-heuristics-audit, ux-accessibility-audit, ux-aesthetics-audit, and ux-microcopy-audit for validation.


Step 0 — Establish why the screen is empty

The cause picks the pattern:

  • First use — the user hasn't created anything yet. This is onboarding's last mile: explain what lives here and make the first action effortless ("Add your first task").
  • Cleared / completed — the user emptied it themselves (inbox zero, done list). Tone shifts to positive reinforcement: "You're all caught up!" + a low-pressure next step.
  • No results — a search/filter came up empty. Not really "empty" — it's a recovery moment: spelling check, search tips, popular categories, recent searches (align with ux-search's no-dead-ends rule).
  • Error / 404 — something's missing or broken. Explain plainly, no jargon, no blame, and route back to safety (homepage, popular content).

Also establish platform and brand voice — they bound illustration style and whether humor is safe.


The always-apply core (correct for almost every case)

Explain + guide — the two jobs every empty state has

  • Say why it's empty, specifically. ❌ "No tasks found" ✅ "You're all caught up! Add a new task to stay productive." Clarity plus encouragement, never a bare negation.
  • Always offer a next step. Even a basic informational empty state hints at what to do ("Your inbox is empty. Start by composing a new message"). An empty state with no path forward is a defect.
  • Action empty states pair message and CTA: the button continues the sentence — "Your cart is empty. Start shopping now!" → [Shop now]. Secondary paths (docs, examples) can live as links in the copy.
  • Never blame the user — especially on no-results and 404 pages. The system explains what happened and offers routes, not fault.

CTAs that actually move users

  • Specific, action-oriented labels: "Add your first task," "Explore features" — not "OK" or "Get started" floating contextless.
  • One primary action. If two are warranted (template vs. custom), the recommended path is visually primary and the alternative clearly secondary — never two equal buttons.

Calm over clutter

  • An empty screen is not a billboard. Concise microcopy + minimal visuals; every element nudges toward the user's primary goal. First-run dashboards especially: guide, don't carpet-bomb with tips, tours, and banners at once.

The context-dependent decisions (surface, don't auto-apply)

DecisionApply whenAvoid / adapt whenDefault recommendation
IllustrationIt communicates the state (sun-behind-clouds for no weather data) and fits brand personalityDecoration that adds noise or delays comprehension; inconsistent styleRelevant, on-brand, subordinate to the message
Humor / personalityBrands where playfulness fits; low-frustration moments (cleared states)Error/404 contexts for serious products; users mid-task and blockedWarmth always; jokes only where frustration is low
Second CTAA genuine alternative path (template vs. custom)Choice paralysis on a screen meant to unblockOne primary; secondary visually subordinate
Educational content (docs links, demos)Complex products where the first action needs contextSimple actions that need no manualLink in copy, not a competing button
Sample/demo dataDashboards where showing the value beats describing itWhen fake data could be mistaken for realClearly-labeled sample content as a preview
404 navigation aidsLinks to homepage + popular content; search boxA bare "page not found"Illustration + plain explanation + ≥2 routes onward

Validate the result (orchestration)

Hand-offs name each lens by its installable skill name. Invoke one only if that skill is installed; if it isn't, this skill's own core already carries these rules — proceed without it rather than blocking.

After generating or revising, hand the result to the audit lenses rather than declaring it done. These are candidate lenses — posture is set by docs/orchestration-policy.md, or route the whole thing through ux-design-review. Here, heuristics and microcopy are Tier A (auto-run); accessibility and aesthetics are Tier B (offered) — under an existing design system aesthetics is suppressed and accessibility narrows to usage. If the user invoked this skill for one specific thing, respect that scope.

  • ux-heuristics-audit (Tier A) — visibility of system status (why is it empty?), error recovery quality, match to user expectations per state type.
  • ux-accessibility-audit (Tier B — offer; narrow under a design system) — illustration alt text, CTA contrast and target size, message readability.
  • ux-aesthetics-audit (Tier B — offer; suppress under a design system) — calm-vs-clutter balance, illustration consistency with the product's visual language.
  • ux-microcopy-audit (Tier A) — this skill lives or dies on copy: explanation specificity, CTA labels, tone (encouraging, never blaming).

If the audits surface a conflict (e.g., brand wants a big illustration vs. fast comprehension), resolve back toward the primary task: the user hit this screen wanting to do something — get them doing it.


Common do/don't patterns

❌ Don't✅ Do
"No data available." and nothing elseWhy it's empty + what to do next, every time
Generic "No tasks found""You're all caught up! Add a new task to stay productive"
Empty cart with no path"Your cart is empty. Start shopping now!" + [Shop now]
Blaming phrasing on no-results ("You entered a bad query")Spelling tips, search suggestions, popular categories
Jargon-filled 404Plain words + illustration + links onward
Three equal CTAs on a first-run screenOne primary action; alternatives subordinate
Tutorial walls on an empty dashboardMinimal copy + one clear first step (+ labeled sample data if helpful)
Random cute illustration everywhereRelevant, on-brand visuals that carry meaning
Ship without checkingHand off to heuristics + accessibility + aesthetics + microcopy

Source lessons (Uxcel)

Frequently asked questions

What does the Ux Empty States AI skill do?

Design or critique empty states — first-use screens, cleared states, no-results pages, and 404s that explain why the screen is empty and guide the next action instead of dead-ending. Trigger when the user asks to design or review an empty state, blank screen, zero-data view, first-run dashboard, no-results page, or 404 page.

Why use Ux Empty States on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Uxcel-Lab/product-skills/tree/main/ux/screens/empty-states. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ux Empty States?

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 Ux Empty States?

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

Is the Ux Empty States AI skill free?

Yes. It is published on GitHub by Uxcel-Lab 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇