skills/stitch-loop/SKILL.md
Teaches agents to iteratively build websites using Stitch with an autonomous baton-passing loop pattern
npx skillsauth add Chris-Maskey/opencode-config stitch-loopInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are an autonomous frontend builder participating in an iterative site-building loop. Your goal is to generate a page using Stitch, integrate it into the site, and prepare instructions for the next iteration.
The Build Loop pattern enables continuous, autonomous website development through a "baton" system. Each iteration:
next-prompt.md)Required:
DESIGN.md file (generate one using the design-md skill if needed)SITE.md file documenting the site vision and roadmapOptional:
The next-prompt.md file acts as a relay baton between iterations:
---
page: about
---
A page describing how jules.top tracking works.
**DESIGN SYSTEM (REQUIRED):**
[Copy from DESIGN.md Section 6]
**Page Structure:**
1. Header with navigation
2. Explanation of tracking methodology
3. Footer with links
Critical rules:
page field in YAML frontmatter determines the output filenameDESIGN.mdParse next-prompt.md to extract:
page frontmatter fieldBefore generating, read these files:
| File | Purpose |
|------|---------|
| SITE.md | Site vision, Stitch Project ID, existing pages (sitemap), roadmap |
| DESIGN.md | Required visual style for Stitch prompts |
Important checks:
Use the Stitch MCP tools to generate the page:
list_tools to find the Stitch MCP prefixstitch.json exists, use the projectId from it[prefix]:create_project and save the ID to stitch.json[prefix]:generate_screen_from_text with:
projectId: The project IDprompt: The full prompt from the baton (including design system block)deviceType: DESKTOP (or as specified)[prefix]:get_screen to get:
htmlCode.downloadUrl — Download and save as queue/{page}.htmlscreenshot.downloadUrl — Download and save as queue/{page}.pngqueue/{page}.html to site/public/{page}.htmlhref="#") and wire them to the new pageIf the Chrome DevTools MCP Server is available, verify the generated page:
list_tools to see if chrome* tools are presentnpx serve site/public)[chrome_prefix]:navigate to open http://localhost:3000/{page}.html[chrome_prefix]:screenshot to capture the rendered pagequeue/{page}.png) for fidelityNote: This step is optional. If Chrome DevTools MCP is not installed, skip to Step 5.
Modify SITE.md:
[x]You MUST update next-prompt.md before completing. This keeps the loop alive.
SITE.md Section 5 (Roadmap) for pending items---
page: achievements
---
A competitive achievements page showing developer badges and milestones.
**DESIGN SYSTEM (REQUIRED):**
[Copy the entire design system block from DESIGN.md]
**Page Structure:**
1. Header with title and navigation
2. Badge grid showing unlocked/locked states
3. Progress bars for milestone tracking
project/
├── next-prompt.md # The baton — current task
├── stitch.json # Stitch project ID (persist this!)
├── DESIGN.md # Visual design system (from design-md skill)
├── SITE.md # Site vision, sitemap, roadmap
├── queue/ # Staging area for Stitch output
│ ├── {page}.html
│ └── {page}.png
└── site/public/ # Production pages
├── index.html
└── {page}.html
The loop can be driven by different orchestration layers:
| Method | How it works |
|--------|--------------|
| CI/CD | GitHub Actions triggers on next-prompt.md changes |
| Human-in-loop | Developer reviews each iteration before continuing |
| Agent chains | One agent dispatches to another (e.g., Jules API) |
| Manual | Developer runs the agent repeatedly with the same repo |
The skill is orchestration-agnostic — focus on the pattern, not the trigger mechanism.
This skill works best with the design-md skill:
DESIGN.md using the design-md skill from an existing Stitch screennext-prompt.md (breaks the loop)href="#") instead of wiring real navigationstitch.json after creating a new project| Issue | Solution |
|-------|----------|
| Stitch generation fails | Check that the prompt includes the design system block |
| Inconsistent styles | Ensure DESIGN.md is up-to-date and copied correctly |
| Loop stalls | Verify next-prompt.md was updated with valid frontmatter |
| Navigation broken | Check all internal links use correct relative paths |
tools
Anti-patterns and mistakes to avoid as a product manager. Use when evaluating leadership behaviors, improving team dynamics, reflecting on management practices, or onboarding new product managers.
development
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
testing
Design effective CTAs using visual attention and gaze psychology principles. Use when designing landing pages, button hierarchies, conversion elements, or optimizing user attention flow through interfaces.
tools
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.