Providing Feedback logo

Providing Feedback

Community
ancoleman
providing-feedback

Implements feedback and notification systems including toasts, alerts, modals, progress indicators, and error states. Use when communicating system state, displaying messages, confirming actions, or showing errors.

Overview

Publisherancoleman
Repositoryai-design-components
Skill nameproviding-feedback
Stars
523
Forks
73
Bundled files
18
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.

  • 18 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ancoleman on GitHub. Read the source before you install it.

Installation

Install the Providing Feedback 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.
  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/ancoleman/ai-design-components.git /tmp/ai-design-components
mkdir -p .claude/skills
cp -r /tmp/ai-design-components/skills/providing-feedback .claude/skills/providing-feedback
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Providing Feedback 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 Providing Feedback 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 Providing Feedback 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.

Providing User Feedback and Notifications

This skill implements comprehensive feedback and notification systems that enhance all other component skills by providing consistent patterns for communicating system state, displaying messages, and handling user confirmations.

When to Use This Skill

Activate this skill when:

  • Implementing toast notifications or snackbars
  • Displaying success, error, warning, or info messages
  • Creating modal dialogs or confirmation dialogs
  • Implementing progress indicators (spinners, progress bars, skeleton screens)
  • Designing empty states or zero-result displays
  • Adding tooltips or contextual help
  • Determining notification timing, stacking, or positioning
  • Implementing accessible feedback patterns with ARIA
  • Communicating any system state to users

Feedback Type Decision Matrix

Choose the appropriate feedback mechanism based on urgency and attention requirements:

Critical + Blocking       → Modal Dialog
Important + Non-blocking  → Alert Banner
Success/Info + Temporary  → Toast/Snackbar
Contextual Help          → Tooltip/Popover
In-progress              → Progress Indicator
No Data                  → Empty State

Quick Reference by Urgency

Urgency LevelComponentDurationBlocks Interaction
CriticalModal DialogUntil actionYes
ImportantAlert BannerUntil dismissedNo
StandardToast3-7 secondsNo
ContextualInline MessagePersistentNo
HelpTooltipOn hoverNo
ProgressSpinner/BarDuring operationOptional

Implementation Approach

Step 1: Determine Feedback Type

Assess the situation using these criteria:

  1. Urgency: How critical is the information?
  2. Duration: How long should it persist?
  3. Action Required: Does user need to respond?
  4. Context: Is it related to specific UI element?

Step 2: Choose Implementation Pattern

For Toasts/Snackbars:

  • Position: Bottom-right (recommended)
  • Duration: 3-4s (success), 5-7s (warning), 7-10s (error)
  • Stack limit: 3-5 maximum
  • See references/toast-patterns.md for detailed patterns

For Modal Dialogs:

  • Focus management: Trap focus within modal
  • Accessibility: ESC to close, proper ARIA labels
  • Backdrop: Click outside to close (optional)
  • See references/modal-patterns.md for implementation

For Progress Indicators:

  • <100ms: No indicator needed
  • 100ms-5s: Spinner with message
  • 5s-30s: Progress bar (determinate if possible)
  • 30s: Progress bar + time estimate + cancel

  • See references/progress-indicators.md for patterns

For Empty States:

  • Include: Illustration, headline, body text, CTA
  • Types: First use, zero results, error, permission denied
  • See references/empty-states.md for designs

Step 3: Implement with Recommended Libraries

Modern React Stack (Recommended):

bash
npm install sonner @radix-ui/react-dialog

For Toasts - Use Sonner:

tsx
import { Toaster, toast } from 'sonner';

// In your app root
<Toaster position="bottom-right" />

// Trigger notifications
toast.success('Changes saved successfully');
toast.promise(saveData(), {
  loading: 'Saving...',
  success: 'Saved!',
  error: 'Failed to save'
});

For Modals - Use Radix UI:

tsx
import * as Dialog from '@radix-ui/react-dialog';

<Dialog.Root>
  <Dialog.Trigger>Open</Dialog.Trigger>
  <Dialog.Portal>
    <Dialog.Overlay />
    <Dialog.Content>
      <Dialog.Title>Confirm Action</Dialog.Title>
      <Dialog.Description>Are you sure?</Dialog.Description>
      <Dialog.Close>Cancel</Dialog.Close>
    </Dialog.Content>
  </Dialog.Portal>
</Dialog.Root>

See references/library-comparison.md for alternative libraries and selection criteria.

Step 4: Apply Accessibility Patterns

ARIA Live Regions for Announcements:

html
<!-- For non-critical notifications -->
<div role="status" aria-live="polite">
  File uploaded successfully
</div>

<!-- For critical alerts -->
<div role="alert" aria-live="assertive">
  Error: Failed to save
</div>

Focus Management for Modals:

  1. Save current focus before opening
  2. Move focus to first interactive element in modal
  3. Trap focus within modal (Tab cycles)
  4. Restore focus to trigger on close

See references/accessibility-feedback.md for complete patterns.

Step 5: Integrate Design Tokens

All feedback components use the design-tokens skill for consistent theming:

css
/* Example token usage */
.toast {
  background: var(--toast-bg);
  color: var(--toast-text);
  padding: var(--toast-padding);
  border-radius: var(--toast-border-radius);
  box-shadow: var(--toast-shadow);
  animation-duration: var(--toast-enter-duration);
}

Token categories used:

  • Colors: Toast, alert, modal, tooltip backgrounds
  • Spacing: Internal padding for all components
  • Typography: Font sizes for titles and messages
  • Shadows: Elevation for floating elements
  • Motion: Animation durations and easing

Notification Timing Guidelines

Auto-dismiss durations:

  • Success: 3-4 seconds
  • Info: 4-5 seconds
  • Warning: 5-7 seconds
  • Error: 7-10 seconds or manual dismiss
  • With action button: 10+ seconds or no auto-dismiss

Progress indicator thresholds:

  • <100ms: No indicator
  • 100ms-5s: Spinner
  • 5s-30s: Progress bar
  • 30s: Progress bar + cancel option

Resources

Scripts (Token-Free Execution)

  • scripts/generate_toast_manager.js - Generate toast configurations with timing and stacking
  • scripts/format_messages.py - Format user-facing messages based on context
  • scripts/calculate_timing.js - Calculate auto-dismiss timings

References (Detailed Documentation)

  • references/toast-patterns.md - Toast positioning, stacking, animations
  • references/alert-patterns.md - Alert banner implementations
  • references/modal-patterns.md - Modal dialogs with focus management
  • references/progress-indicators.md - Loading states and progress
  • references/empty-states.md - No-data and zero-result patterns
  • references/accessibility-feedback.md - ARIA patterns and focus management
  • references/library-comparison.md - Detailed library analysis

Examples (Implementation Code)

  • examples/success-toast.tsx - Success notification with Sonner
  • examples/confirmation-modal.tsx - Delete confirmation with Radix UI
  • examples/progress-upload.tsx - File upload with progress bar
  • examples/inline-validation.tsx - Form validation errors

Assets (Templates and Configs)

  • assets/message-templates.json - Reusable message templates
  • assets/error-catalog.json - Error code to message mappings
  • assets/timing-config.json - Timing recommendations

Cross-Skill Integration

This skill enhances all other component skills:

  • Forms: Validation feedback, success confirmations
  • Data Visualization: Loading states, error messages
  • Tables: Bulk operation feedback, action confirmations
  • AI Chat: Streaming indicators, rate limit warnings
  • Dashboards: Widget loading, system status
  • Search/Filter: Zero results, search progress
  • Media: Upload progress, processing status
  • Design Tokens: All visual styling via token system

Library Quick Comparison

LibraryTypeSizeBest For
SonnerToastSmallModern React 18+, accessibility
react-hot-toastToast<5KBMinimal bundle size
react-toastifyToast~16KBRTL support, mobile
Radix UIModalSmallDesign systems, headless
Headless UIModalSmallTailwind projects

Choose based on project requirements. See references/library-comparison.md for detailed analysis.

Key Principles

  1. Match urgency to attention: Don't use modals for non-critical info
  2. Be consistent: Same feedback type for similar actions
  3. Provide context: Explain what happened and what to do
  4. Enable recovery: Include undo, retry, or help options
  5. Respect preferences: Honor reduced motion settings
  6. Test accessibility: Verify with screen readers and keyboard

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 Providing Feedback AI skill do?

Implements feedback and notification systems including toasts, alerts, modals, progress indicators, and error states. Use when communicating system state, displaying messages, confirming actions, or showing errors.

Why use Providing Feedback on TypingMind?

Because you install it once and use it with any model. Providing Feedback 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 Providing Feedback in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ancoleman/ai-design-components/tree/main/skills/providing-feedback. 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 Providing Feedback?

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 Providing Feedback?

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

Is the Providing Feedback AI skill free?

Yes. It is published on GitHub by ancoleman 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 👇