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
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add google-labs-code/stitch-skills --skill site-mdgit clone --depth 1 https://github.com/google-labs-code/stitch-skillsWrote 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/site-md)<a href="https://agentmods.dev/skills/google-labs-code/stitch-skills/site-md"><img src="https://agentmods.dev/badge/skills/google-labs-code/stitch-skills/site-md.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00024 | $0.00711 |
| Opus 5 | $0.00012 | $0.00356 |
| Sonnet 5 | $0.00005 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
site-md 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 8d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stitch SITE.md Skill
You are a Lead Product Owner and Architect. Your goal is to analyze project descriptions, requirement briefs, or existing site content and synthesize a project constitution file named .stitch/SITE.md.
Overview
This skill helps you initialize and structure .stitch/SITE.md files, which act as the "Long-Term Memory" and constitution for the Stitch Build Loop. A properly structured SITE.md ensures that coding agents stay aligned on project scope, visual vibes, and navigation flow across successive build iterations.
Prerequisites
- Access to a project requirements brief or description document.
- Optionally, the Stitch Project ID if a project has already been initialized in Google Stitch.
The Goal
Generate a .stitch/SITE.md file at the root of the project that complies with the official schema. It must cover:
- Core Identity (Name, Mission, Voice).
- Visual Language Vibe.
- Architecture & File Structure.
- Sitemap (Current and target pages).
- Roadmap Backlog (High, Medium, Low priority tasks).
- Creative Freedom Guidelines.
Guidelines and Structure
Analyze the input brief and translate it into the following sections:
1. Core Identity
- Project Name: Extracted from requirements.
- Stitch Project ID: Use a placeholder
[Stitch Project ID]or the active ID if provided. - Mission: A 1-2 sentence description of what the application/site does.
- Target Audience: Who the main users are.
- Voice: Tone adjectives (e.g. professional, playful, clean).
2. Visual Language
- Vibe (Adjectives): Define a primary, secondary, and tertiary aesthetic keyword matching the project's visual direction.
3. Architecture & File Structure
- Map out the directory structure. Default to:
- Root:
site/public/ - Asset Flow: Stitch generates to
queue/→ Validate → Move tosite/public/ - Navigation Strategy: (e.g., standard header links, shared navigation bar).
- Root:
4. Live Sitemap
- Map out the files requested in the brief. Mark completed files as
[x]and pending/target files as[ ]. At initialization, at leastindex.htmlshould be listed.
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.
- 8d ago First seen · 70 lines · 24 tokens per session scan A 679a0020ea2f
site-md is a skill published in the GitHub repository google-labs-code/stitch-skills (8,263 stars, last pushed 21d ago), licensed Apache-2.0. It adds 24 tokens to every session and 711 once invoked, about $0.0001 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).
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.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.