google-labs-code avatar

Enhance Prompt

Takes your half-baked UI ideas and turns them into detailed Stitch prompts that actually work. It checks for missing platform info, translates vague terms like "menu at the top" into proper component names, and structures everything into numbered sections. The real value is in how it handles design systems - it looks for your DESIGN.md file and incorporates those tokens, or reminds you to create one if missing. Instead of getting random-looking screens from Stitch, you get consistent results that follow your design language. Best for when you know what you want but can't articulate it properly to an AI.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.
8
skills.sh installs
59.4K
GitHub stars
8.7K
last updated
Aug 21, 2026

Install

$ npx -y skills add google-labs-code/stitch-skills --skill enhance-prompt --agent claude-code

Installs into .claude/skills of the current project.

Files

Enhance Prompt for Stitch

You are a Stitch Prompt Engineer. Your job is to transform rough or vague UI generation ideas into polished, optimized prompts that produce better results from Stitch.

Prerequisites

Before enhancing prompts, consult the official Stitch documentation for the latest best practices:

This guide contains up-to-date recommendations that may supersede or complement the patterns in this skill.

When to Use This Skill

Activate when a user wants to:

  • Polish a UI prompt before sending to Stitch
  • Improve a prompt that produced poor results
  • Add design system consistency to a simple idea
  • Structure a vague concept into an actionable prompt

Enhancement Pipeline

Follow these steps to enhance any prompt:

Step 1: Assess the Input

Evaluate what's missing from the user's prompt:

Sponsors

Details

Repository
github.com/google-labs-code/stitch-skills
Categories
AI & Agent Building, Design & UI/UX

More from google-labs-code/stitch-skills

All 8
1pexoai avatarpexo-agentpexoai/pexo-skillsAI video generation skill with auto model selection across Seedance 2, Kling 3.0, HappyHorse, and 10+ models. Produces finished multi-shot videos (5–120s) from 40.6Kskills.sh installs
2zhaono1 avatarself-improving-agentzhaono1/agent-playbookUse after a failure, user correction, repeated workflow problem, or validated success reveals a reusable lesson. Captures bounded redacted candidates, runs exec35.6Kskills.sh installs
3mcp-use avatarmcp-apps-buildermcp-use/mcp-useBuild, modify, debug, migrate, or review TypeScript MCP servers and interactive MCP Apps using mcp-use v2. Use for tools, resources, prompts, Views, React host 33.1Kskills.sh installs
4charon-fan avatarself-improving-agentcharon-fan/agent-playbookUniversal self-improving agent that learns from all skill experiences using multi-memory architecture.31.9Kskills.sh installs
5googleworkspace avatargws-modelarmor-sanitize-promptgoogleworkspace/cliGoogle Model Armor: Sanitize a user prompt through a Model Armor template.30.3Kskills.sh installs
6dontbesilent2025 avatardbs-ai-checkdontbesilent2025/dbskill扫描文案中的 AI 写作特征并输出检测报告,默认只诊断不改写。用户要求检查 AI 味、AI 痕迹或机器化表达时使用。28.4Kskills.sh installs