跳到正文
cccskills
免费在 GitHub 公开

design-style-installer

Install a complete design-token theme into any project in one pass -- pulls a style from the Open Agent Stack design-styles collection (aurora-mesh, cirrus, liquid-glass, mono-brutalist, neo-terminal, sand-terra, tidal) or a local tokens.json, wires it into Tailwind/CSS, and repaints existing components to match.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md3.7 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Design Style Installer

Apply a full design system to a project the way a brand refresh actually works: tokens first, wiring second, components last, and nothing hardcoded that the tokens already define. Sources: the seven production themes in Open Agent Stack design-styles/ -- each ships tokens.json (W3C design-tokens), theme.css, tailwind.tokens.js, and a WCAG contrast worksheet -- or any local W3C-format tokens file.

Workflow

  1. Pick the style. If the user named one, fetch it from the open-agent-stack repo (or read the local clone). If not, show the seven options with their one-line personalities -- aurora-mesh (soft futuristic dark, gradient mesh), cirrus (light cloud/sky, frosted), liquid-glass (translucent layered), mono-brutalist (stark, type-led), neo-terminal (CRT green-on-black), sand-terra (warm editorial neutrals), tidal (deep ocean blues) -- and ask which fits the product.
  2. Read the project. Detect the stack (Tailwind version, CSS modules, styled-components, plain CSS) and inventory the current styling surface: where colors, fonts, radii, and shadows are defined today, and how many components hardcode values outside that.
  3. Install the tokens. Wire the theme by stack: Tailwind -- merge tailwind.tokens.js into theme.extend (v4: emit @theme CSS variables); otherwise -- add theme.css custom properties at :root/[data-theme]. Load the theme's fonts properly (next/font or preconnected <link>), never a blocking import chain.
  4. Repaint. Replace hardcoded values in components with token references, mapping by role, not by nearest hex: old primary -> new accent, old page background -> bg.base, old card -> surface. Where the old design had roles the theme lacks (a third accent, a warning tint), derive them from the theme's palette logic and document the additions in the tokens file -- do not freelance new colors.
  5. Verify. Run the build, then check the money paths render correctly: nav, hero, buttons in all states, forms, cards. Confirm text/background pairs still meet the contrast worksheet's AA levels after any derivations. Output design-install-report.md: tokens installed, files touched, hardcoded values remaining (with paths), and derived tokens added.

Rules

  • Tokens are the only source of truth after installation. A repaint that leaves hex codes scattered in components has not finished.
  • Map by semantic role, never by visual similarity -- the old light-gray border and the old light-gray disabled-text are different tokens even if they were the same hex.
  • Never mix themes. If the user wants aurora-mesh cards on a sand-terra page, that is a custom theme -- fork the tokens file and name it honestly.
  • Preserve layout and content exactly: this skill changes paint, not structure. Structural itches go in the report as suggestions.
  • Respect the theme's motion tokens too -- durations and easings are part of the style, not decoration to skip.
  • Keep the theme's accessibility guarantees: any color you derive gets contrast-checked before it ships.

Quick Commands

  • "Install [style] into this project" -- full workflow
  • "Show me the styles" -- step 1 gallery with personalities
  • "Just the tokens, no repaint" -- steps 1-3
  • "What's still hardcoded?" -- the drift audit from step 5

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Audit websites for accessibility issues and WCAG compliance. Use when checking accessibility, fixing a11y issues, or ensuring WCAG compliance.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3662026年10月20日 更新

Deploy a 2-layer parallel agent hierarchy for large, parallelizable work — big refactors, multi-file migrations, codebase-wide audits, bulk generation. A top-tier commander (Fable or Opus) orchestrates the swarms; the user picks a power level (Max Power / Heavy / Balanced / Economy) that sets the Opus/Sonnet/Haiku model mix per layer. Layer 1 is 3-50+ specialist agents, each with its own full context window; Layer 2 is 2+ sub-agents per member. Includes git safety, tiered sizing, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3662026年10月20日 更新

Use to test whether an AI agent, prompt, or skill actually works before or after it ships — build a small eval set, score runs, and catch regressions when the prompt or model changes. Trigger when the user asks whether a prompt is good, wants to compare models or versions, sees inconsistent agent output, or is about to put an agent in front of customers.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3662026年10月20日 更新

Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3662026年10月20日 更新

Designs and deploys custom agent teams for specific business workflows. Interactive discovery of business processes, then generates complete team configurations with specialized agent roles, tool access, communication protocols, and handoff rules.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3662026年10月20日 更新

Agent-to-Agent (A2A) communication protocol. Connect two or more Claude agents that pass messages, share context, delegate tasks, and collaborate. Implements structured handoffs, shared memory, and multi-agent conversations.

中文简介正在准备中。当前显示原文说明。

OneWave-AI/claude-skills3662026年10月20日 更新

查看 OneWave-AI 的全部技能

报告此技能的问题