Garden Skills is an open-source collection of reusable instructions for AI coding agents such as Claude Code, Cursor, and Codex, covering tasks including web design, image generation, and turning source material into articles or presentations. Developers use the skills to guide agents through these 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 ConardLi/garden-skills --skill web-design-engineergit clone --depth 1 https://github.com/ConardLi/garden-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/conardli/garden-skills/web-design-engineer)<a href="https://agentmods.dev/skills/conardli/garden-skills/web-design-engineer"><img src="https://agentmods.dev/badge/skills/conardli/garden-skills/web-design-engineer/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/conardli/garden-skills/web-design-engineer"><img src="https://agentmods.dev/badge/skills/conardli/garden-skills/web-design-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 204 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00096 | $0.07849 |
| Opus 5 | $0.00048 | $0.03925 |
| Sonnet 5 | $0.00019 | $0.01570 |
| Haiku 4.5 | $0.00010 | $0.00785 |
Grade A, and why
web-design-engineer 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 11d 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 — 493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Design Engineer
This skill positions the Agent as a top-tier design engineer who crafts elegant, refined Web artifacts using HTML/CSS/JavaScript/React. The output medium is always HTML, but the professional identity shifts with each task: UX designer, motion designer, slide designer, prototype engineer, data-visualization specialist.
Core philosophy: The bar is "stunning," not "functional." Every pixel is intentional, every interaction is deliberate. Respect design systems and brand consistency while daring to innovate.
Scope
✅ Applicable: Visual front-end deliverables and redesigns (pages / dashboards / prototypes / slide decks / visualizations / animations / UI mockups / design systems)
❌ Not applicable: Back-end APIs, CLI tools, data-processing scripts, pure logic development, source material → long-form HTML article conversion, or narration-beat → recordable web-video presentation. Route the last two to their dedicated skills when available.
Workflow
Step 0: Verify Facts Before Anything Else
Highest priority — runs before clarifying questions.
When the request mentions a specific product, brand, technology, SDK, or event you're not sure about, verify the current facts from authoritative sources before designing around them. Never assert unstable facts from memory.
Trigger conditions (any one):
- The request names a specific product / SDK / library you're unsure about (e.g., a new device, a recently announced model)
- Any time-sensitive release timeline / version / specification
- You catch yourself thinking "I think it's…" / "should still be…" / "probably not released yet" / "I don't think that exists"
- The user asks you to design materials for a specific company or product
If search returns nothing or is ambiguous → ask the user. Don't guess. Forbidden phrases without prior search: "I think X hasn't released yet" / "X is currently version N" / "X probably doesn't exist" / "As I recall, X's specs are…"
What ships with it
38 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.
- agents/openai.yaml 288 B
- manifest.json 609 B
- README.md 28 KB
- README.zh-CN.md 27 KB
- references/advanced-patterns.md 14 KB
- references/block-library.md 1.7 KB
- references/browser-acceptance.md 4.5 KB
- references/critique-guide.md 10 KB
- references/design-calibration.md 6.0 KB
- references/design-directions.md 14 KB
- references/failure-patterns.md 7.0 KB
- references/redesign-protocol.md 4.1 KB
- references/style-recipes/active-theory.md 2.5 KB
- references/style-recipes/aesop.md 2.7 KB
- references/style-recipes/apple-hig.md 3.0 KB
- references/style-recipes/are-na.md 2.2 KB
- references/style-recipes/balenciaga-post-2017.md 2.3 KB
- references/style-recipes/bloomberg-businessweek-turley.md 2.5 KB
- references/style-recipes/bloomberg-terminal.md 2.7 KB
- references/style-recipes/dieter-rams-braun.md 2.5 KB
- references/style-recipes/field-io.md 2.9 KB
- references/style-recipes/headspace-meditation.md 2.6 KB
- references/style-recipes/INDEX.md 12 KB
- references/style-recipes/linear.md 3.1 KB
- references/style-recipes/mailchimp-freddie.md 2.5 KB
- references/style-recipes/mid-century-modern.md 2.7 KB
- references/style-recipes/monocle-magazine.md 2.6 KB
- references/style-recipes/muji-kenya-hara.md 2.6 KB
- references/style-recipes/notion-pre-ai.md 2.8 KB
- references/style-recipes/nyt-the-daily.md 2.6 KB
- references/style-recipes/pentagram.md 2.8 KB
- references/style-recipes/raycast.md 3.2 KB
- references/style-recipes/resn-storytelling.md 2.4 KB
- references/style-recipes/stripe-press.md 2.8 KB
- references/style-recipes/tufte-dataink.md 2.5 KB
- references/style-recipes/vercel-mesh.md 2.9 KB
- references/style-recipes/vignelli-swiss-helvetica.md 2.5 KB
- references/style-recipes/y2k-retrofuturism.md 2.7 KB
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.
- 11d ago First seen · 493 lines · 96 tokens per session scan A 00633aa43028
web-design-engineer is a skill published in the GitHub repository ConardLi/garden-skills (12,324 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 7,849 once invoked, about $0.0005 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
agentos-ui-ux
Design, review, or implement AgentOS UI and UX work using the project’s operator-console visual system. Use for React/Tailwind pages, cards, dialogs, mobile layouts, theme work, navigation, forms, empty/loading/error states, and UI consistency reviews in AgentOS.
webflow-mcp:interactions
Create, update, list, and delete Webflow IX3 interactions (GSAP animations) through Webflow MCP. Use when the user wants click/hover/load/scroll/mouse-move animations, interaction timelines, or datainteractionstool / createinteraction payloads. Requires beta MCP + ff-ix3-interaction-apis during dogfood.
webflow-mcp:flowkit-naming
Apply Flowkit CSS naming system in Webflow. Use when creating classes, auditing existing naming, or building new components following Flowkit conventions. Flowkit is Webflow's official CSS framework with utility-first approach. Runs headlessly against a page ID — no Designer connection required, except for the…
ardot-style-guide
A design-system workflow for choosing and applying colors, fonts, spacing, and page layouts in Ardot projects.
webflow-cli:designer-extension
Build Designer Extensions for custom Webflow Designer functionality. Lists available templates, initializes extension projects from templates (default/react/typescript-alt), bundles extensions for upload, and serves locally for development.
figma
Fetch Figma design context, variables, screenshots, and assets through MCP when working from Figma URLs or node IDs, or diagnosing its integration.