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 code-to-designgit 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/code-to-design)<a href="https://agentmods.dev/skills/google-labs-code/stitch-skills/code-to-design"><img src="https://agentmods.dev/badge/skills/google-labs-code/stitch-skills/code-to-design/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/code-to-design"><img src="https://agentmods.dev/badge/skills/google-labs-code/stitch-skills/code-to-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 37 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 53 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 63 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 71 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00115 | $0.00876 |
| Opus 5.5 | $0.00046 | $0.00350 |
| Sonnet 5.5 | $0.00023 | $0.00175 |
| Haiku 4.5 | $0.00012 | $0.00088 |
Grade A, and why
stitch::code-to-design 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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code to Design
Transform your existing frontend code (React + Vite, Next.js, Angular, Vue, etc.) into a Stitch Design so you can iterate and improve it using Stitch.
This skill orchestrates three other skills in sequence:
extract-static-html: Extract a single self-contained HTML file from your build output or running dev server (e.g., Vite dev server or Angular CLIng serve).extract-design-md: Analyze the source code (including Angularangular.json, external.htmltemplates, theme files, and components) to create a design system (DESIGN.md).upload-to-stitch: Upload that HTML file and the design system to your Stitch project.
Workflow
Follow these steps to convert your existing code.
Prerequisites
- A running local dev server (e.g.
npm run dev,ng serve) OR a built web application directory containingindex.htmland assets. - Target Stitch
projectId(uselist_projectsif unknown).
Steps
1. Extract Self-Contained HTML
Delegate to the extract-static-html skill to generate a standalone HTML file.
Read skills/extract-static-html/SKILL.md for detailed instructions and script usage.
Expected output: A single file like /path/to/extracted/standalone.html.
2. Verify HTML (Optional — User-Driven)
After extraction, inform the user of the output file path so they can manually verify in a browser if desired. Do not block on verification — proceed directly to Step 3.
If the user reports issues after reviewing, fix them before continuing.
3. Extract Design System (File)
Delegate to the extract-design-md skill to analyze the project's source files
(components, stylesheets, theme configs) and produce a design system. Read
skills/extract-design-md/SKILL.md for the
full analysis workflow.
Write .stitch/DESIGN.md following the extract-design-md skill's output
structure.
4. Upload DESIGN.md and Create Design System in Stitch
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.
- 1mo ago First seen · 78 lines · 115 tokens per session scan A 1daafb1d89d6
stitch::code-to-design is a skill published in the GitHub repository google-labs-code/stitch-skills (8,543 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 115 tokens to every session and 876 once invoked, about $0.0005 per session on Opus 5.5. 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 $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
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.