Stitch Enhance Prompt SkillSAFE
A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claude Code, Cursor.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Install
npx skills add google-labs-code/stitch-skills --skill enhance-prompt --global
Example Prompt
Enhance my prompt "make me a login page" for better Stitch generation results.
Skill Structure
This repository follows the Agent Skills open standard. Each skill is self-contained with its own logic, workflow, and reference materials.
enhance-prompt/ ├── SKILL.md — Core instructions & workflow ├── references/ — UI/UX vocabulary and adjective palettes └── README.md — This file
How it Works
When activated, the agent follows a prompt enhancement pipeline:
- Assessment: Evaluates the input for missing elements (platform, structure, visual style, colors).
- DESIGN.md Check: Looks for an existing design system to inject; recommends creating one if missing.
- Enhancement: Applies UI/UX keywords, vibe adjectives, and structured page sections.
- Formatting: Outputs a Stitch-optimized prompt with design system block and numbered structure.
- Delivery: Returns enhanced text for user review, with optional file output.
32484555efabOBSERVED · 2026-10-21Install
Commands as the repository documents them. They are shown, not run.
npx skills add google-labs-code/stitch-skills --skill enhance-prompt --global
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: enhance-prompt description: Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results. allowed-tools: - "Read" - "Write" --- # 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: - **Stitch Effective Prompting Guide**: https://stitch.withgoogle.com/docs/learn/prompting/ 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: | Element | Check for | If missing... | |---------|-----------|---------------| | **Platform** | "web", "mobile", "desktop" | Add based on context or ask | | **Page type** | "landing page", "dashboard", "form" | Infer from description | | **Structure** | Numbered sections/components | Create logical page structure | | **Visual style** | Adjectives, mood, vibe | Add appropriate descriptors | | **Colors** | Specific values or roles | Add design system or suggest | | **Components** | UI-specific terms | Translate to proper keywords | ### Step 2: Check for DESIGN.md Look for a `DESIGN.md` file in the current project: **If DESIGN.md exists:** 1. Read the file to extract the design system block 2. Include the color palette, typography, and component styles 3. Format as a "DESIGN SYSTEM (REQUIRED)" section in the output **If DESIGN.md does not exist:** 1. Add this note at the end of the enhanced prompt: ``` --- 💡 **Tip:** For consistent designs across multiple screens, create a DESIGN.md file using the `design-md` skill. This ensures all generated pages share the same visual language. ``` ### Step 3: Apply Enhancements Transform the input using these techniques: #### A. Add UI/UX Keywords Replace vague terms with specific component names: | Vague | Enhanced | |-------|----------| | "menu at the top" | "navigation bar with logo and menu items" | | "button" | "primary call-to-action button" | | "list of items" | "card grid layout" or "vertical list with thumbnails" | | "form" | "form with labeled input fields and submit button" | | "picture area" | "hero section with full-width image" | #### B. Amplify the Vibe Add descriptive adjectives to set the mood: | Basic | Enhanced | |-------|----------| | "modern" | "clean, minimal, with generous whitespace" | | "professional" | "sophisticated, trustworthy, with subtle shadows" | | "fun" | "vibrant, playful, with rounded corners and bold colors" | | "dark mode" | "dark theme with high-contrast accents on deep backgrounds" | #### C. Structure the Page Organize content into numbered sections: ```markdown **Page Structure:** 1. **Header:** Navigation with logo and menu items 2. **Hero Section:** Headline, subtext, and primary CTA 3. **Content Area:** [Describe the main content] 4. **Footer:** Links, social icons, copyright ``` #### D. Format Colors Properly When colors are mentioned, format them as: ``` Descriptive Name (#hexcode) for functional role ``` Examples: - "Deep Ocean Blue (#1a365d) for primary buttons and links" - "Warm Cream (#faf5f0) for page background" - "Soft Gray (#6b7280) for secondary text" ### Step 4: Format the Output Structure the enhanced prompt in this order: ```markdown [One-line description of the page purpose and vibe] **DESIGN SYSTEM (REQUIRED):** - Platform: [Web/Mobile], [Desktop/Mobile]-first - Theme: [Light/Dark], [style descriptors] - Background: [Color description] (#hex) - Primary Accent: [Color description] (#hex) for [role] - Text Primary: [Color description] (#hex) - [Additional design tokens...] **Page Structure:** 1. **[Section]:** [Description] 2. **[Section]:** [Description] ... ``` ## Output Options **Default:** Return the enhanced prompt as text for the user to copy. **Optional file output:** If the user requests, write to a file: - `next-prompt.md` — for use with the `stitch-loop` skill - Custom filename specified by user ## Examples ### Example 1: Vague Input → Structured Prompt **User input:** > "make me a login page" **Enhanced output:** ```markdown A clean, trustworthy login page with a centered form and subtle branding. **DESIGN SYSTEM (REQUIRED):** - Platform: Web, Desktop-first - Theme: Light, minimal, professional - Background: Clean White (#ffffff) - Surface: Soft Gray (#f9fafb) for form card - Primary Accent: Deep Blue (#2563eb) for submit button and links - Text Primary: Near Black (#111827) for headings - Text Secondary: Medium Gray (#6b7280) for labels - Buttons: Subtly rounded (8px), full-width on form - Cards: Gently rounded (12px), soft shadow for elevation **Page Structure:** 1. **Header:** Minimal logo, centered 2. **Login Card:** Centered form with email, password fields, "Forgot password?" link 3. **Submit Button:** Primary blue "Sign In" button 4. **Footer:** "Don't have an account? Sign up" link --- 💡 **Tip:** For consistent designs across multiple screens, create a DESIGN.md file using the `design-md` skill. ``` ### Example 2: Feature Request → Targeted Edit **User input:** > "add a search bar" **Enhanced output:** ```markdown Add a search bar to the header navigation. **Specific changes:** - Location: Header, right side before user avatar - Style: Pill-shaped input with subtle gray background (#f3f4f6) - Icon: Magnifying glass icon on the left, inside the input - Placeholder
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
32484555efabfull audit observations/trust-audit/skill/google-labs-code__enhance-prompt.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-21 | 32484555efab | SAFE | B | 89 | first audit |
Questions
What does the enhance-prompt — google-labs-code/stitch-skills skill do?
A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claude Code, Cursor.
Is enhance-prompt — google-labs-code/stitch-skills safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can enhance-prompt — google-labs-code/stitch-skills access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (32484555efab), read on 2026-10-21. The repository is watched, and a new audit runs when it changes — this is the first audit.
Add this badge to your README
Shows this page's audit result and links back to it. It updates when the audit does.
[](https://modelsatlas.com/skills/google-labs-code/enhance-prompt/)
Not your listing, or something out of date? Claim or update your listing.