Skip to content

gabelul/stitch-kit / skills/stitch-mcp-list-screens

stitch-mcp-list-screens

Verified

Lists all screens in a Stitch project. Use this after generate_screen_from_text to find the screenId of the newly generated screen, then call stitch-mcp-get-screen to retrieve it.

Stitch MCP — List Screens

Lists all screens contained within a specific Stitch project. You typically call this right after generate_screen_from_text to find the screenId of the screen that was just created.

Critical prerequisite

Only use this skill when the user explicitly mentions "Stitch".

When to use

  • Immediately after generate_screen_from_text — to find the new screen's ID
  • User wants to browse all screens in a project
  • You need a screenId to call get_screen
  • Checking what screens already exist before generating a new one

Call the MCP tool

Important: Use the projects/ID format — not the numeric ID alone.

{
  "name": "list_screens",
  "arguments": {
    "projectId": "projects/3780309359108792857"
  }
}
✅ "projects/3780309359108792857"
❌ "3780309359108792857"

Output schema

{
  "screens": [
    {
      "name": "projects/3780309359108792857/screens/88805abc123def456",
      "title": "Login Screen",
      "screenshot": {
        "downloadUrl": "https://storage.googleapis.com/..."
      },
      "deviceType": "MOBILE"
    }
  ]
}

After listing

  1. Identify the target screen (usually the most recently generated — last in the list)
  2. Extract the numeric screenId from the name field:
    • "projects/3780309359108792857/screens/88805abc123def456" → screenId = "88805abc123def456"
  3. Call stitch-mcp-get-screen with the numeric projectId and screenId

ID format reminder

For the next call (get_screen), you need the numeric IDs for both project and screen:

  • projectId → 3780309359108792857 (strip projects/ prefix)
  • screenId → 88805abc123def456 (strip projects/.../screens/ prefix)
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall