Agent Native

stitch::upload-to-stitch

This skill uploads local assets like images, HTML files, and markdown documents to a Stitch project via a Python script, bypassing MCP tool base64 encoding…

by GoogleOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (flutter, google)

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode
License
Apache-2.0 (permissive)
Pin
0337446pinned Oct 9, 2026
Context cost
about 950 tokenswhen the skill loads
GitHub stars
8,442on google-labs-code/stitch-skills
Scripts
1 script

What it does

“Upload local assets (images, mockups, extracted HTML, design markdown) to a Stitch project. ALWAYS use this skill when you need to upload visual assets, HTML pages, or design docs to Stitch, particularly when direct MCP tool calls fail or truncate due to base64 token limits.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill uploads local assets like images, HTML files, and markdown documents to a Stitch project via a Python script, bypassing MCP tool base64 encoding limitations. It handles file type detection, requires API key authentication, and prompts for user confirmation before uploading. The skill supports PNG, JPEG, WebP, HTML, and markdown files.

When to use it

  • Uploading visual assets or design files to Stitch projects
  • Sending extracted HTML pages when MCP tools fail due to token limits
  • Adding design documentation and mockups to design systems
  • Attaching generated files with metadata like route paths or source tool

When not to

  • When direct MCP tool uploads succeed without reaching token limits
  • If Stitch API key is unavailable and cannot be obtained from user
  • When uploading unsupported file formats like PDFs or video files

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add google-labs-code/stitch-skills --skill stitch::upload-to-stitch

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install google-labs-code/stitch-skills stitch::upload-to-stitch@0337446dadde6f8c94210444e2aa9d546126480f

Installs the commit we checked (0337446).

Copy by hand

Download the folder at 0337446 and put it in .claude/skills/upload-to-stitch for Claude Code and in .agents/skills/upload-to-stitch for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 0337446

Claude Code plugin

/plugin install chrome-devtools-mcp@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Claude Code plugin

/plugin install alloydb-omni@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Claude Code plugin

/plugin install bigquery-data-analytics@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "stitch::upload-to-stitch" by Google.

Source, pinned to commit 0337446dadde6f8c94210444e2aa9d546126480f:
https://github.com/google-labs-code/stitch-skills/tree/0337446dadde6f8c94210444e2aa9d546126480f/plugins/stitch-design/skills/upload-to-stitch

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/upload-to-stitch/ for Claude Code and .agents/skills/upload-to-stitch/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/google/stitch-upload-to-stitch

SKILL.md at the pin

---
name: stitch::upload-to-stitch
description: >-
  Upload local assets (images, mockups, extracted HTML, design markdown) to a Stitch project.
  ALWAYS use this skill when you need to upload visual assets, HTML pages, or design docs
  to Stitch, particularly when direct MCP tool calls fail or truncate due to
  base64 token limits.
allowed-tools:
  - "stitch*:*"
  - "Bash"
  - "Read"
  - "Write"
  - "web_fetch"
---

# Upload-to-Stitch

Upload local assets (images, mockups, HTML, and markdown files) to a Stitch project using the
provided upload script, which bypasses the MCP tool's base64 output token limits.

> [!NOTE]
> The AI model cannot upload files via MCP tools directly because the base64
> encoding of even a small file exceeds the model's output token limit (~16K
> tokens). This script reads the file and sends it directly over HTTP.

## Steps

### 1. Identify Target Project

Use `list_projects` to find the correct `projectId`.

### 2. Get the API Key

Locate your active MCP server configuration file and extract the API key:
- **Antigravity**: `.gemini/antigravity/mcp_config.json` or `.gemini/jetski/mcp_config.json`
- **Gemini CLI**: `~/.gemini/settings.json` or `~/.gemini/extensions/Stitch/gemini-extension.json`
- **Claude Code**: `~/.claude.json`

Extract:
- **API Key**: From the `X-Goog-Api-Key` header or auth argument
- **MCP URL** (optional): From the `httpUrl` or endpoint argument (defaults to
  `https://stitch.googleapis.com`)

> [!IMPORTANT]
> If you cannot find the API key in any of these locations, or if you cannot access these files, you MUST ask the user to provide the Stitch API key. Do not proceed without a valid API key.

### 3. Run Upload Script

> [!WARNING]
> **Checkpoint — User Confirmation Required.**
> Before running the upload script, you **MUST** pause and present the file(s)
> to be uploaded (paths, sizes, and types) to the user and wait for explicit
> approval. Do **NOT** execute the upload script until the user confirms.

Use `run_command` to execute the Python script:

```bash
python3 <SKILL_DIR>/scripts/upload_to_stitch.py \
  --project-id <PROJECT_ID> \
  --file-path <PATH_TO_FILE> \
  --api-key <API_KEY> \
  [--api-url <STITCH_API_URL>] \
  [--title <SCREEN_TITLE>] \
  [--generated-by <GENERATED_BY>]
```

> [!TIP]
> **macOS / SSL Certificate Troubleshooting:**
> If the upload fails with `ssl.SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] unable to get local issuer certificate`, this means your Python installation does not have root certificate authorities configured.
> 
> The script automatically attempts to use the `certifi` package to load the CA bundle if it is installed in your python environment. If `certifi` is not installed, you can either install it (`pip install certifi`) or manually supply the `SSL_CERT_FILE` environment variable when running the script:
> ```bash
> SSL_CERT_FILE=$(python3 -c "import certifi; print(certifi.where())") python3 <SKILL_DIR>/scripts/upload_to_stitch.py \
>   --project-id <PROJECT_ID> \
>   --file-path <PATH_TO_FILE> \
>   --api-key <API_KEY> \
>   [--api-url <STITCH_API_URL>] \
>   [--title <SCREEN_TITLE>] \
>   [--generated-by <GENERATED_BY>]
> ```

### Supported File Types

| Extension | MIME Type |
|:---|:---|
| `.png` | `image/png` |
| `.jpg`, `.jpeg` | `image/jpeg` |
| `.webp` | `image/webp` |
| `.html`, `.htm` | `text/html` |
| `.md` | `text/markdown` |

The script auto-detects MIME type from the file extension.

### Script Options

- `--project-id`: **Required**. The Stitch project ID.
- `--file-path`: **Required**. Path to the local file to upload.
- `--api-key`: **Required**. API key for Stitch authorization.
- `--api-url`: Optional. Base URL of the Stitch API. Defaults to `https://stitch.googleapis.com`.
- `--title`: Optional. Title for the uploaded screen. When uploading extracted HTML from a web app, set this to the **route path** of the page (e.g., `'/dashboard'`, `'/settings/profile'`, `'/inbox'`) so that the screen name/title in Stitch clearly identifies the route.
- `--generated-by`: Optional. Specify how the uploaded file was generated (e.g., 'stitch::extract-static-html' skill, 'Claude Code', 'Codex', 'Gemini' etc.).

From google-labs-code/stitch-skills at 0337446, shown as plain text under its license: Apache-2.0 (permissive). The license text is in LICENSE.

View SKILL.md on GitHub at 0337446

Files

2 files, 12 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 0337446
All 50 skills from Google

More from Google

  • skill-creator

    This skill guides agents through creating new skills that extend Gemini CLI with specialized knowledge, workflows, and tool integrations.

    Contains scripts

    Gemini CLI · about 5K tokens · pinned 6 days ago

  • chrome-devtools-cli

    This skill enables agents to automate browser interactions and inspect web pages using Chrome DevTools via command-line interface.

    Claude Code, Codex, Cursor +4 · about 2.9K tokens · pinned 6 days ago

  • cloud-run-basics

    Deploys and manages Google Cloud Run services, jobs, and worker pools for running containerized applications or source code.

    Claude Code, Codex, Cursor +4 · about 3.9K tokens · pinned 6 days ago

  • retail-virtual-tryon

    Creates virtual try-on agents on Google Cloud using Gemini image models and Veo video generation, supporting static image try-ons and catwalk animations.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 3.3K tokens · pinned 6 days ago

  • site-md

    This skill analyzes project briefs and generates a .stitch/SITE.md constitution file that documents the project's identity, visual direction, architecture…

    Claude Code, Codex, Cursor +4 · about 730 tokens · pinned 6 days ago

  • stitch::code-to-design

    This skill converts existing frontend code (React, Vue, Angular, etc.) into a Stitch Design by extracting HTML, analyzing design systems, and uploading both…

    Claude Code, Codex, Cursor +4 · about 760 tokens · pinned 6 days ago

  • web-perf

    Audits website performance by analyzing Core Web Vitals, Lighthouse scores, network requests, and trace data using Chrome DevTools.

    by CloudflareOfficial publisher

    Claude Code, Codex, Cursor +4 · about 2K tokens · pinned 6 days ago

  • figma-design-to-code

    This skill provides the agent with detailed procedures for converting Figma designs into code.

    by FigmaOfficial publisher

    Claude Code · about 860 tokens · pinned 6 days ago

  • figma-generate-library

    Orchestrates multi-phase design system builds in Figma from code.

    by FigmaOfficial publisher

    Contains scripts

    Claude Code · about 5.8K tokens · pinned 6 days ago

  • figma-generate-library

    Builds or updates professional design systems in Figma from code by creating variables, tokens, components with variants, semantic aliases, and documentation.

    by FigmaOfficial publisher

    Contains scripts

    Claude Code · about 5.9K tokens · pinned 6 days ago

  • figma-use-motion

    This skill adds motion and animation capabilities to Figma node editing, enabling the agent to create and modify keyframe animations, apply animation styles…

    by FigmaOfficial publisher

    Claude Code · about 1.6K tokens · pinned 6 days ago

  • wpds

    This skill helps agents build and review UIs using the WordPress Design System, including components, tokens, and patterns.

    by AutomatticOfficial publisher

    Claude Code, Codex, Cursor +4 · about 640 tokens · pinned 6 days ago

Open roles at Google

No open roles at Google on the Agent Native jobs board right now.

Browse the jobs board

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use