AGENT SKILL

frontend-design

Guide for creating distinctive UI designs that avoid generic templates. Use when designing new UI components, screens, or evaluating designs for uniqueness and purpose. DO NOT USE FOR: architecture decisions or SOLID evaluation (use software-architecture), open-ended exploration (use brainstorming), or React test strategies (use ui-testing).

License 许可
MIT
最近更新
2026-08-16
Stars
★ 3
Forks
0

01 前言 Front Matter

name
frontend-design
description
Guide for creating distinctive UI designs that avoid generic templates. Use when designing new UI components, screens, or evaluating designs for uniqueness and purpose. DO NOT USE FOR: architecture decisions or SOLID evaluation (use software-architecture), open-ended exploration (use brainstorming), or React test strategies (use ui-testing).

03 SKILL.md 正文

Frontend Design Skill

Guide for creating distinctive, purposeful UI designs that avoid cookie-cutter patterns.

When to Use

  • Designing new UI components or screens
  • Evaluating existing designs for uniqueness
  • Reviewing designs that feel "generic"
  • Creating brand-aligned interfaces
  • Building memorable user experiences

Core Principles

1. Purpose Over Pattern

Every design decision should answer: "Why this, not something else?"

  • Bad: Using a card grid because it's common
  • Good: Using a card grid because content is comparable and scannable

2. Distinctive Identity

Your UI should be recognizable without the logo.

Questions to ask:

  • Would users recognize this as our product?
  • What makes this different from competitors?
  • Does this reflect our brand personality?

3. Intentional Defaults

Don't accept framework defaults blindly.

[CUSTOMIZE] Review these common defaults in your stack:
- Border radius values
- Shadow depths
- Spacing scales
- Color applications
- Typography scales

Design Review Checklist

Visual Distinction

  • [ ] Color palette goes beyond primary/secondary/neutral
  • [ ] Typography creates clear hierarchy (not just size changes)
  • [ ] Spacing creates intentional rhythm (not uniform gaps)
  • [ ] Icons have consistent style/weight/meaning
  • [ ] Micro-interactions add personality

Purposeful Patterns

  • [ ] Each component solves a specific user problem
  • [ ] Layout serves content structure (not vice versa)
  • [ ] Navigation reflects user mental models
  • [ ] Empty states guide users (not just "No data")
  • [ ] Loading states reduce perceived wait time

Avoiding Generic Traps

  • [ ] Not using component library defaults unchanged
  • [ ] Headers aren't just logo-left, nav-right
  • [ ] Forms have personality beyond labels + inputs
  • [ ] Buttons vary by importance (not just color)
  • [ ] Data displays fit the data (not just tables)

Breaking Generic Patterns

Instead of Generic Cards

Consider:

  • Asymmetric layouts for visual interest
  • Inline expansion vs. navigation
  • Progressive disclosure of details
  • Content-specific shapes (not all rectangles)

Instead of Generic Forms

Consider:

  • Conversational flows for complex inputs
  • Smart defaults that reduce input
  • Inline validation with helpful context
  • Progress indication for multi-step

Instead of Generic Tables

Consider:

  • Is a table the right pattern at all?
  • Grouped/nested rows for hierarchy
  • Inline actions vs. row selection
  • Responsive transformations (not just scroll)

Instead of Generic Dashboards

Consider:

  • User goals, not data availability
  • Actionable metrics, not vanity metrics
  • Contextual insights, not just numbers
  • Personalization based on role/usage

Design Language Documentation

[CUSTOMIZE] Document your design language:

## Our Design Personality

- [Define 3-5 adjectives: e.g., "Professional but approachable"]

## Signature Elements

- [Unique visual elements that define your brand]

## Intentional Constraints

- [Self-imposed rules that create consistency]

Review Questions

Before shipping any design:

  1. Is this recognizable? Would users know it's from us?
  2. Is this purposeful? Can we justify every choice?
  3. Is this necessary? Does it solve a real problem?
  4. Is this accessible? Can all users interact with it?
  5. Is this maintainable? Can we scale this pattern?

Resources

[CUSTOMIZE] Add your project's design resources:

  • Design system documentation
  • Brand guidelines
  • Component library
  • Design tokens
  • Approved patterns and templates

Supplement Skills

A supplement skill is a project-specific skill that layers additional constraints, themes, or identity guidance on top of this hub skill. When a project has one, load both together — the hub skill provides the universal design principles and the supplement narrows them for the project.

Naming convention: {project}-{hub-skill-name} — for example, windgust-frontend-design supplements frontend-design.

When to create one: When your project has a unique visual identity, brand-specific design tokens, or theme customizations that go beyond what the [CUSTOMIZE] markers in this skill cover. If you find yourself adding the same project-specific guidance to every session, extract it into a supplement.

Supplement ≠ replacement: A supplement adds to the hub skill; it does not replace it. Load both together. Do not contradict hub skill defaults — extend or constrain them instead.

Worked Example

windgust-frontend-design in Grimblaz-and-Friends/Windgust-Questbook supplements this skill with the Windgust brand personality, color palette, and component conventions specific to that project.

Supplement SKILL.md Template

Note: This template is pre-filled for frontend-design supplements. When creating a supplement for a different hub skill, replace every occurrence of frontend-design with your hub-skill name.

---
name: {project}-frontend-design
description: Supplements `frontend-design` with {project} brand identity, design tokens, and visual conventions. Use when designing {project} UI components or screens alongside the `frontend-design` hub skill. DO NOT USE FOR: standalone sessions without `frontend-design` loaded (this is a supplement skill; always load `frontend-design` alongside).
---

# {Project} Frontend Design Supplement

Project-specific design constraints that layer on top of the `frontend-design` hub skill.

## Brand Identity

[CUSTOMIZE] Document brand personality, color palette, and typography rules.

## Design Tokens

[CUSTOMIZE] List token overrides that go beyond `frontend-design` defaults.

## Component Conventions

[CUSTOMIZE] List component conventions that extend `frontend-design` hub skill guidance.

## When to Use

- [CUSTOMIZE] List the conditions when this supplement should be loaded (alongside `frontend-design`).

## Gotchas

| Trigger                          | Gotcha                      | Fix                       |
| -------------------------------- | --------------------------- | ------------------------- |
| [CUSTOMIZE] Observable condition | [CUSTOMIZE] What goes wrong | [CUSTOMIZE] How to fix it |

Gotchas

<!-- [CUSTOMIZE] Add project-specific anti-patterns below -->

Trigger Gotcha Fix
Keeping every component library default (border-radius, shadow, spacing) unchanged Design feels generic — indistinguishable from any other app using the same framework Audit defaults; make ≥3 intentional overrides per component type
Header layout is logo-left, nav-right without questioning it The invisible default — identical to every SaaS app Evaluate navigation mental models; consider sidebar, bottom nav, or contextual nav
"It's common" or "everyone does it" as design justification Common ≠ purposeful; pattern chosen without intent Force "why this, not something else?" using §1 Purpose Over Pattern
Reaching for a table when asked to "show data" Tables rarely fit mobile; rarely surface hierarchy Ask "Is a table the right pattern?" before building; consider cards, timelines, or grouped lists
Shipping without answering the 5 review questions UI may be polished but not recognizable, purposeful, or accessible Answer all 5 review questions before declaring design done

04 同仓库更多 Skills

Grimblaz
Grimblaz/agent-orchestra

webapp-testing

Playwright end-to-end testing guidance for web apps, with practical patterns and setup steps. Use when creating or improving browser-based E2E coverage, test stability, and CI execution. DO NOT USE FOR: React component tests (use ui-testing), canvas game interaction (use browser-canvas-testing), TDD workflow (use test-driven-development), debugging failures (use systematic-debugging), or randomized property tests (use property-based-testing).

测试与质量前端开发
★ 3
Grimblaz
Grimblaz/agent-orchestra

verification-before-completion

Evidence-based verification checklist before marking work complete. Use before PRs, releases, marking tickets done, or any "I'm finished" declaration; also when naming a baseline commit for a differential suite claim, when designing a mutation campaign or red-run evidence, when making an absence claim, a universal claim, or a one-time demonstration offered as a standing guarantee, when attributing a measurement or claiming a sweep or verification loop is complete, and when stating what a check or a CI suite will do about a change. DO NOT USE FOR: post-merge cleanup or archival (use post-pr-review) or processing GitHub review comments (use code-review-intake).

★ 3
Grimblaz
Grimblaz/agent-orchestra

validation-methodology

Reusable validation and review methodology for staged validation, failure triage, and prosecution-depth setup. Use when running validation ladders, triaging failures, or executing adversarial review passes. DO NOT USE FOR: CE Gate orchestration, specialist dispatch ownership, or step execution flow (keep those in Code-Conductor).

★ 3
Grimblaz
Grimblaz/agent-orchestra

upstream-onboarding

Shared opening-phase protocol for upstream agents (Experience-Owner, Solution-Designer, Issue-Planner) and Code-Conductor when invoked on an existing GitHub issue. Renders a scaled context brief and runs a standards check on inherited work at each phase boundary. Use when a user-invocable agent receives a request referencing an existing GitHub issue and must load solution-authoring and upstream-onboarding at the opening phase. DO NOT USE FOR: subagent dispatches (which already operate within an assessed session context); post-merge review (use post-pr-review); research or non-tree subagents.

人力资源Skill与智能体开发
★ 3
Grimblaz
Grimblaz/agent-orchestra

ui-testing

Resilient React component testing strategies focusing on user behavior. Use when writing or reviewing component-level React tests, fixing flaky component tests, or establishing React testing patterns. DO NOT USE FOR: Playwright E2E tests (use webapp-testing), canvas game interaction (use browser-canvas-testing), TDD workflow (use test-driven-development), debugging failures (use systematic-debugging), UI component design (use frontend-design), or randomized property tests (use property-based-testing).

设计师测试与质量前端开发
★ 3
Grimblaz
Grimblaz/agent-orchestra

ui-iteration

Reusable screenshot-driven UI polish workflow for iterative visual refinement. Use when improving layout, hierarchy, spacing, feedback, or Tailwind-based presentation through repeated review-and-adjust passes. DO NOT USE FOR: functional bug fixing, accessibility-only audits, or major redesign strategy work (use Code-Smith or frontend-design).

设计师前端开发
★ 3