Enhance Prompt
Sharpen vague visual requests into design-spec prompts so agents produce clearer UI layouts and design-to-code output.
Overview
enhance-prompt is an agent skill most often used in Build (also Validate prototype work) that improves prompts with design specs and UI/UX vocabulary for design-to-code and visual output.
Install
npx skills add https://github.com/nexu-io/open-design --skill enhance-promptWhat is this skill?
- Enriches prompts with design specifications and UI/UX vocabulary
- Optimized for design-to-code and visual-output agent workflows
- Curated Google Labs (Stitch) design-systems skill in Open Design
- Triggers: enhance prompt, design prompt, ui prompt, design vocabulary
- Catalogue entry—install upstream Google Labs bundle for full references
Adoption & trust: 816 installs on skills.sh; 61.4k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your agent keeps misbuilding screens because your prompt lacks layout, component, and UX terms the model needs.
Who is it for?
Builders using Claude Code, Cursor, or Codex who want design-to-code prompts that spell out UI structure and UX intent.
Skip if: Pure backend API work with no visual deliverable, or when you already have an approved spec and pixel-perfect Figma handoff.
When should I use this skill?
User says enhance prompt, design prompt, ui prompt, or design vocabulary.
What do I get? / Deliverables
You get a design-aware prompt your agent can execute for clearer UI layouts and more faithful visual implementations.
- Design-enriched prompt text ready for design-to-code or visual generation
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical on Build because the skill injects UI/UX vocabulary into prompts right before implementation and design-to-code execution. Frontend subphase reflects clarifying visual output, components, and layout language rather than backend or ops work.
Where it fits
Turn a one-line screen idea into a structured UI prompt before generating a clickable prototype.
Add component and spacing vocabulary before asking the agent to implement a dashboard view.
Clarify early mockup language when exploring multiple layout directions with an agent.
Standardize how your custom agent skill receives design-spec prompts from messy user chat.
How it compares
Prompt refinement with design vocabulary—not a component library, theme pack, or automated code reviewer.
Common Questions / FAQ
Who is enhance-prompt for?
Solo and indie developers who rely on agents for UI work and need prompts translated into design-spec language before codegen or visual generation.
When should I use enhance-prompt?
In Validate when clarifying a prototype screen; in Build before frontend or design-to-code runs; anytime a visual request is ambiguous and you want UI/UX terms baked into the prompt.
Is enhance-prompt safe to install?
Review the Security Audits panel on this Prism page and the Google Labs upstream repository before copying skill files into your agent skills directory.
SKILL.md
READMESKILL.md - Enhance Prompt
# enhance-prompt > Curated from Google Labs (Stitch). ## What it does Improve prompts with design specs and UI/UX vocabulary. Useful for design-to-code workflows and clarifying requests for visual output. ## Source - Upstream: https://github.com/google-labs-code/skills - Category: `design-systems` ## How to use This catalogue entry advertises the skill in Open Design so the agent discovers it during planning. To run the full upstream workflow with its original assets, scripts, and references, install the upstream bundle into your active agent's skills directory: ```bash # Inspect the upstream README for exact paths open https://github.com/google-labs-code/skills ``` Then ask the agent to invoke this skill by name (`enhance-prompt`) or with one of the trigger phrases listed in this skill's frontmatter.