Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add int2t05/engineering-skills/plugin install engineering-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/int2t05/engineering-skills/frontend-design)<a href="https://agentmods.dev/skills/int2t05/engineering-skills/frontend-design"><img src="https://agentmods.dev/badge/skills/int2t05/engineering-skills/frontend-design.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00066 | $0.02985 |
| Opus 5 | $0.00033 | $0.01492 |
| Sonnet 5 | $0.00013 | $0.00597 |
| Haiku 4.5 | $0.00007 | $0.00298 |
Grade A, and why
frontend-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 4d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend Design
Build distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. The method: pick a bold aesthetic direction, apply a color formula, pair typography deliberately, specify interaction states, and execute with precision. Bold maximalism and refined minimalism both work — the key is intentionality, not intensity.
When to use
- Building web components, pages, or applications (HTML/CSS/JS, React, Vue, Svelte, etc.)
- Choosing a design direction, color palette, or typography system for a project
- Reviewing UI for visual quality, accessibility, or interaction polish
- Implementing responsive layouts, dark mode, or platform-specific conventions (Apple HIG, Material)
- Triggers on "frontend", "UI design", "组件设计", "界面设计", "前端设计", "视觉风格"
Not for: pure data visualization (use dataviz); backend logic with no visual surface;
API contract design (use api-design). Visually important web work where image-first is preferred
(use image-to-code).
Steps
1. Define the element and project context
Before coding, commit to a bold aesthetic direction. Answer:
- Element: What are you building? (button, card, modal, navbar, page, full app)
- Purpose: What problem does this interface solve? Who uses it?
- Tone: Pick an extreme — brutally minimal, maximalist, retro-futuristic, organic, luxury, playful, editorial, brutalist, art deco, industrial. Commit fully; never default to "safe."
- Differentiation: What makes this UNFORGETTABLE? The one thing someone will remember.
Match implementation complexity to the vision: maximalist designs need elaborate code; minimalist designs need restraint and precision. NEVER use generic AI aesthetics — overused fonts (Inter, Roboto, Arial), purple gradients on white, rounded-2xl everything, stock card grids, lorem ipsum.
- Load references/brief-inference.md for the design-read protocol (infer page kind, audience, vibe, constraints before coding) and the three dials (DESIGN_VARIANCE, MOTION_INTENSITY, VISUAL_DENSITY) that gate layout, motion, and density
- Load references/design-foundations.md §Perception & Gestalt and §Hierarchy & Layout for the visual-organization principles beneath layout — Gestalt laws, the four hierarchy techniques, F/Z reading patterns, the squint and 5-second tests, CRAP expanded
- Load references/design-foundations.md §Cognitive Laws for the psychology laws that constrain layout — Hick's, Fitts's, Miller's 7±2, Tesler, Von Restorff, cognitive load types, progressive disclosure
- Load references/ux-research.md when the user or context is unknown — interviews, personas, journey maps, empathy maps, usability testing (run discovery before visual design)
- Load references/design-foundations.md §Information Architecture when organizing content — the four IA elements, tree vs network, card sorting, navigation depth, labeling systems
What ships with it
18 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 161 B
- references/anti-tells.md 7.6 KB
- references/apple-hig.md 9.6 KB
- references/brief-inference.md 6.4 KB
- references/component-anatomy.md 6.0 KB
- references/design-foundations.md 32 KB
- references/design-system-audit.md 5.9 KB
- references/design-tokens.md 6.2 KB
- references/font-pairings.md 6.1 KB
- references/material-design.md 7.0 KB
- references/motion-system.md 7.2 KB
- references/palettes.md 6.4 KB
- references/state-design.md 6.2 KB
- references/state-management.md 6.4 KB
- references/styles.md 12 KB
- references/ux-guidelines.md 28 KB
- references/ux-research.md 8.5 KB
- references/visual-direction.md 8.2 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.
- 4d ago Changed · +1 lines 80f19277462b
- 8d ago First seen · 148 lines · 66 tokens per session scan A 738394eebdf4
frontend-design is a skill published in the GitHub repository int2t05/engineering-skills (3 stars, last pushed 7d ago), licensed MIT. It adds 66 tokens to every session and 2,985 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
figma-fetch
Extract frame/component structure and all visible text from a Figma design URL. Use whenever a prompt or a fetched issue contains a figma.com/design or figma.com/file link.
design
Intent-first UI design with conscious, traceable design decisions. Persists decisions in .interface-design/ for cross-session consistency. Includes domain exploration, design system generation (system.md + system.json), per-component construction with mandatory checkpoints, and craft validation tests. Modes: init…
ux
Forms, flows and screens. Structure, naming and clarity of user-facing interaction code: component boundaries, state ownership, and keeping presentation separable from the rules behind it.
fec-storybook-component-doc
A workflow for documenting interface components in Storybook, a tool that displays UI components and their states in isolation. It covers stories, reusable setup wrappers, written documentation, interaction checks, accessibility checks, and visual baselines.
Component Variants / States Documentation コンポーネント状態の文書化
A code review check for new reusable interface components and the variations and states they support, such as hover, focus, disabled, loading, and error states.
Design Source-of-Truth Conformance デザイン定義準拠
A code review check that compares new interface values—such as colors, spacing, font sizes, rounded corners, and shadows—with the project's documented design rules or token files. It only runs when those design definitions exist.