From google-stitch
Converts natural-language descriptions or UI spec files into optimized Google Stitch prompts focused on screens, structure, and visual hierarchy. Use for creating, refining, or validating Stitch design directives.
How this skill is triggered — by the user, by Claude, or both
Slash command
/google-stitch:authoring-stitch-promptsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
1. **Collect context** – accept natural language, specs, or referenced files describing the screen/app.
design-intent/:
design-intent/memory/constitution.mdUse this Skill whenever users need Stitch-ready wording, prompt refinements, or style-consistent rewrites.
Prompts are saved to feature-based directories under design-intent/google-stitch/{feature}/:
prompt-v{version}.md (auto-incremented from existing versions)exports/ (Stitch outputs) and wireframes/ (reference mockups)<!-- Layout: {Name} --> header, then --- separators between component sections (<!-- Component: {Name} -->)prompt-v{version}-part{N}.md files (max 6 per part)See WORKFLOW.md for detailed file composition rules, REFERENCE.md for Stitch best practices, and EXAMPLES.md for worked examples (Examples 14–16 cover multi-component and split scenarios).
Accepted
/specs/dashboard.md)/prompt command (see below)When invoked via /prompt, the skill may receive pre-parsed preferences (Brief, Components, Style, Structure). Parse structured fields and apply style mappings before proceeding. See WORKFLOW.md for field handling and style mapping tables.
All input detail levels are valid — Stitch infers patterns from minimal descriptions. Use adjectives to convey vibe when details are sparse ("vibrant fitness app", "minimal meditation app").
High-level loop: parse → condense → format → validate. Detailed branching logic, including cue extraction and revision handling, lives in WORKFLOW.md.
Prompts must follow the Stitch-friendly template:
Reference templates/authoring-stitch-prompts-template.md for wording patterns and templates/layout-prompt-template.md for layout/foundation prompts.
Representative before/after samples (SaaS dashboard, banking app, iterative edits, spec conversions) are in EXAMPLES.md. Use them to mirror tone and formatting; keep this file lean by not re-embedding the full transcripts here.
When design-intent/ exists in the project, the skill enhances style cues with project context:
The skill does NOT inject specific tokens (hex colors, spacing values)—only high-level descriptors that help Stitch generate contextually appropriate designs.
Fallback behavior: If design-intent/ is not found, the skill works standalone using default style cues.
See WORKFLOW.md for discovery logic and WORKFLOW.md for injection rules.
When @_davideast/stitch-mcp is configured, prompts can be sent directly to Stitch for generation after authoring.
With MCP: Author prompt -> Generate screens -> Fetch images/code Without MCP: Author prompt -> Copy to Stitch manually
After authoring, offer: "Stitch MCP is available. Generate screens now? [Yes / No / Just save prompts]"
If accepted, invoke the generating-stitch-screens skill with the authored prompt file.
For advanced usage:
npx claudepluginhub joaquimscosta/arkhe-claude-plugins --plugin google-stitchTransforms vague UI ideas into polished prompts for Stitch (Google UI generation tool). Enhances specificity, adds UI/UX keywords, injects design system context from DESIGN.md, and structures output for better generation results.
Generates Stitch UI prompts: Path A refines vague ideas into structured formats with design system and page structure; Path B merges Design Spec JSON + user requests.
Generates UI designs using Google Stitch AI with optimized prompts, review documents, and processes exported Figma/HTML/CSS for frontend integration. For rapid prototyping and design iteration.