agentsclimarketplace

Stitch mcp apply design system

Skill gabelul/stitch-kit/skills/stitch-mcp-apply-design-system

Applies a Stitch Design System to existing screens — updates their colors, fonts, and roundness to match the design system's theme. Requires an assetId from list or create operations.From its SKILL.md

Install
npx -y skills add gabelul/stitch-kit --skill stitch-mcp-apply-design-system

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

3.2 KB, 812 tokens by cl100k_base, as published. Nobody here has run it

Stitch MCP — Apply Design System

Applies a previously created Stitch Design System to one or more screens. This updates the screen's visual theme (colors, font, roundness) to match the design system, ensuring visual consistency across a project.

Critical prerequisite

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

You must have:

  1. A projectId (numeric)
  2. One or more screenId values (numeric)
  3. An assetId from a design system (from list_design_systems or create_design_system)

When to use

  • After creating a design system and wanting to apply it to screens
  • User says "make all screens match this theme" or "apply the design system"
  • The orchestrator's Step 5b stores an assetId and offers to apply it
  • Ensuring visual consistency across a multi-screen project

Call the MCP tool

{
  "name": "apply_design_system",
  "arguments": {
    "projectId": "3780309359108792857",
    "selectedScreenInstances": [
      {
        "id": "a1b2c3d4e5f6",
        "sourceScreen": "projects/3780309359108792857/screens/98b50e2ddc9943efb387052637738f61"
      }
    ],
    "assetId": "15996705518239280238"
  }
}

Parameter reference

projectId — numeric ID only, no prefix

✅ "3780309359108792857"
❌ "projects/3780309359108792857"

selectedScreenInstances — array of objects, not screen IDs

This is the one that catches people. It takes screen instances, each a {id, sourceScreen} pair — not a list of screen ids.

✅ [{ "id": "a1b2c3d4e5f6",
      "sourceScreen": "projects/3780.../screens/98b5..." }]

❌ ["88805abc123def456"]                    ← bare screen ids
❌ [{ "id": "98b50e2ddc99...", ... }]        ← source screen id in the id slot

Get both values from get_projectscreenInstances. The id is the instance id; sourceScreen is the full projects/{p}/screens/{s} path of the screen behind it. They are different values, and swapping them fails.

Same shape as create_design_system_from_design_md, which takes a single instance rather than an array.

assetId — bare numeric, no prefix

✅ "15996705518239280238"
❌ "assets/15996705518239280238"

Get it from:

  • stitch-mcp-list-design-systems → take the name field (assets/15996...) and strip the assets/ prefix
  • stitch-mcp-create-design-system → same, strip the prefix from the returned name

apply_design_system wants it bare, but generate_screen_from_text's designSystem param wants it prefixed (assets/15996...). Same identifier, two formats, depending on the tool.

Output

Returns updated screen data reflecting the applied design system.

After applying

  1. Re-fetch affected screens: stitch-mcp-get-screen for each screenId
  2. Show updated screenshots to the user
  3. Offer:
    • "Edit the updated screens?" → stitch-mcp-edit-screens
    • "Convert to code?" → framework conversion
    • "Apply to more screens?" → another apply_design_system call

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most mcp tooling skills give in 812 tokens

Counted across 780 of the 1,136 authors here whose files we hold, read 2026-09-06

  • Use Zod for input validationin 34 of 780, across 21 files
  • Use stdio for local clientsin 27 of 780, across 10 files
  • Restart Claude Code after configurationin 26 of 780, across 23 files
  • Verify MCP server connection before using toolsin 23 of 780, across 17 files
  • Define input schemas for every toolin 20 of 780, across 11 files
  • Use Streamable HTTP for remote clientsin 18 of 780, across 8 files
  • Pin SDK version in package.jsonin 17 of 780, across 6 files
  • Keep server logic independent of transportin 16 of 780, across 6 files
  • Verify SDK methods against official documentationin 15 of 780, across 5 files
  • Format evaluation results as an XML filein 15 of 780, across 12 files
  • Test servers using the MCP Inspectorin 15 of 780, across 14 files
  • Create ten complex and independent evaluation questionsin 14 of 780, across 11 files

Said here and by no other author read

  • Use only when user mentions Stitch
  • Strip assets prefix for apply_design_system assetId
  • Obtain projectId and screenId values
  • Obtain assetId from design system tools
  • Pass screen instances as objects with id and sourceScreen
  • Re-fetch affected screens after application

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.