dragoon0x/everything-design-taste

voice-ui-design

Voice user interface design, conversational design, and voice-first interaction patterns.

First seen Jul 18, 2026

Installation

$ npx skills add dragoon0x/everything-design-taste --skill voice-ui-design

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from dragoon0x/everything-design-taste · top by installs.

npx skills add dragoon0x/everything-design-taste

Browse all from dragoon0x/everything-design-taste

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 11
License LICENSE
Default branch main
Open issues 0
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,221 B
  • docs SUMMARY.md 112 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 2 installs

SKILL.md

Voice Ui Design

Conversational Design Principles

  1. Be brief. Voice responses longer than 15 seconds lose users.
  2. Be relevant. Answer the question first, then offer options.
  3. Be transparent. Tell users what you can and can't do.
  4. Provide escape hatches. "You can say 'stop' at any time."
  5. Confirm destructive actions. "Delete all reminders. Are you sure?"

Prompt Design

  • Open prompts: "What would you like to do?" (broad, intimidating)
  • Closed prompts: "Would you like to order the same as last time?" (specific, easy)
  • Guided prompts: "You can say 'reorder,' 'browse menu,' or 'check order.'" (helps discovery)

Error Handling

  • "I didn't catch that. Could you say it again?"
  • After 2 failures: "Let me show you some options instead."
  • After 3 failures: transfer to screen-based UI or human.

Multimodal

  • Voice + screen: show what you're saying.
  • Allow switching between voice and touch mid-task.
  • Visual confirmation of voice commands.