Stitch Design Skills is a collection of Agent Skills and plugins for Google Stitch, a design tool accessed through the Stitch MCP server. It is for coding agents such as Codex, Antigravity, Gemini CLI, Claude Code, Cursor, and OpenCode, with catalogue entries covering Stitch design, build, and utility workflows.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/google-labs-code/stitch-skillsnpx agentmods add skills/google-labs-code/stitch-skills/manage-design-systemWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/google-labs-code/stitch-skills/manage-design-system)<a href="https://agentmods.dev/skills/google-labs-code/stitch-skills/manage-design-system"><img src="https://agentmods.dev/badge/skills/google-labs-code/stitch-skills/manage-design-system/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/google-labs-code/stitch-skills/manage-design-system"><img src="https://agentmods.dev/badge/skills/google-labs-code/stitch-skills/manage-design-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00035 | $0.01392 |
| Opus 5 | $0.00017 | $0.00696 |
| Sonnet 5 | $0.00007 | $0.00278 |
| Haiku 4.5 | $0.00003 | $0.00139 |
Grade A, and why
stitch::manage-design-system scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design-System
Create a "source of truth" for your project's design language to ensure consistency across all future screens.
[!NOTE] Refer to your system prompt for instruction on handling MCP tool prefixes for all tools mentioned in this skill (e.g.,
get_screen,create_design_system_from_design_md,apply_design_system).
📥 Retrieval
To analyze a Stitch project, you must retrieve metadata and assets using the Stitch MCP tools:
- Project lookup: Use
list_projectsto find the targetprojectId. - Screen lookup: Use
list_screensfor thatprojectIdto find representative screens (e.g., "Home", "Main Dashboard"). - Metadata fetch: Call
get_screenfor the target screen to getscreenshot.downloadUrlandhtmlCode.downloadUrl. - Asset download: Use
read_url_contentto fetch the HTML code.
🧠 Synthesis from Description
If you need to extract a design system from existing screens, use the design-md skill (in the stitch-utilities plugin).
If there are no existing screens (new project), or the user provides a direct description (e.g., "dark theme, blue and purple, rounded, Inter font"):
- Map the user's vague terms to precise values using the design mappings (see
design-mdskill institch-utilitiesorgenerate-designskill). - Select concrete hex codes, font families, and roundness values.
- Generate the
DESIGN.mdfile (refer to thedesign-mdskill institch-utilitiesfor structure). - Proceed to the "Create or Update Design System in Stitch" step below.
📝 Output Structure
The DESIGN.md file should follow the structure defined in the design-md skill (in the stitch-utilities plugin).
🚀 Create or Update Design System in Stitch
After generating .stitch/DESIGN.md, make sure to also create or update the
design system in Stitch.
Two-step design system creation:
[!WARNING] Checkpoint — User Confirmation Required. Before uploading, you MUST pause and ask the user for confirmation. Present a summary of the design system you are about to create (display name, key colors, fonts, and roundness) and wait for explicit approval before proceeding. Do NOT upload until the user confirms.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 133 lines · 35 tokens per session scan A 5ce0b8adb526
stitch::manage-design-system is a skill published in the GitHub repository google-labs-code/stitch-skills (8,270 stars, last pushed 22d ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,392 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.