Automate 21risk tasks via Rube MCP (Composio). Always search tools first for current schemas.
中文简介正在准备中。当前显示原文说明。
Create comprehensive palette with 8-10 greys, 5-10 primary, 5-10 accent shades
中文简介正在准备中。当前显示原文说明。
实测评分 未实测
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Create a comprehensive, systematic color palette with sufficient shades to build realistic interfaces (8-10 greys, 5-10 primary shades, 5-10 accent shades).
Generative + Evaluative
Maps functional needs to a comprehensive palette organized into three categories (greys, primary, accents), each with 5-10 distinct shades.
The majority of your UI is grey. You need more than you think.
White / Near-white: #FFFFFF, #F9FAFB
Gray 100: #F3F4F6 - Subtle backgrounds
Gray 200: #E5E7EB - Borders, dividers
Gray 300: #D1D5DB - Disabled states
Gray 400: #9CA3AF - Placeholder text
Gray 500: #6B7280 - Secondary text
Gray 600: #4B5563 - Body text
Gray 700: #374151 - Strong text
Gray 800: #1F2937 - Headings
Gray 900: #111827 - Near-black text
Start with dark grey (not true black) and work up to white in steady increments.
One or two colors that define the overall look of your site.
Primary 50: Ultra-light (alert backgrounds)
Primary 100: Very light (subtle backgrounds)
Primary 200-300: Light (hover states)
Primary 400-500: Base (buttons, links)
Primary 600-700: Dark (hover text, emphasis)
Primary 800-900: Very dark (text on light)
Used sparingly to grab attention or communicate meaning.
| Color | Use Case |
|---|---|
| Red | Destructive actions, errors, warnings |
| Yellow/Amber | New features, caution, highlights |
| Green | Success, positive trends, confirmation |
| Teal/Pink/Purple | Feature highlights, categorization, calendars |
Each accent needs 5-10 shades just like primary colors.
| Failure | Description | Fix |
|---|---|---|
| 5-Color Generator | Using only 5 hex codes for entire UI | Build comprehensive palette with 8-10 greys, 5-10 primary shades, 5-10 accent shades |
| Too Few Greys | 3-4 grey shades leading to compromises | Expand to 8-10 greys from near-white to near-black |
| Opacity for Shades | Using rgba() to create lighter/darker | Define explicit hex shades upfront for consistency |
| Missing Hover States | No lighter/darker variants for interactions | Each interactive color needs 5-10 shades |
| Missing Semantic Colors | Only brand colors, no red/yellow/green | Add accent colors for errors, warnings, success |
| Too Few Accent Shades | Only one shade of red/green/yellow | Each accent needs 5-10 shades for flexibility |
| True Black Text | Using #000000 (harsh) | Start with #111827 or #1F2937 |
establish-visual-hierarchy (colors support hierarchy)manage-color-contrast (accessibility requirement)For each color, define shades by adjusting lightness in HSL:
Input: Palette with only: Brand Blue #0066FF, Light Blue #E6F2FF, White, Grey #999999, Black
Evaluation: FAIL
Recommendation: Build comprehensive palette:
Greys (10): #F9FAFB, #F3F4F6, #E5E7EB, #D1D5DB, #9CA3AF, #6B7280, #4B5563, #374151, #1F2937, #111827
Primary Blue (8): #EFF6FF, #DBEAFE, #BFDBFE, #93C5FD, #60A5FA, #3B82F6, #2563EB, #1D4ED8
Accents (7-8 each):
Total: 10 greys + 8 primary + 21 accents = 39 shades organized systematically
还没有评价。欢迎分享你的使用感受。
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。
Automate 21risk tasks via Rube MCP (Composio). Always search tools first for current schemas.
中文简介正在准备中。当前显示原文说明。
Automate 2chat tasks via Rube MCP (Composio). Always search tools first for current schemas.
中文简介正在准备中。当前显示原文说明。
Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.
中文简介正在准备中。当前显示原文说明。
Build integrated IS/BS/CF financial workbooks in Excel.
中文简介正在准备中。当前显示原文说明。
Entry point for 9Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 9Router, NINEROUTER_URL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability SKILL.md from the URLs below when needed.
中文简介正在准备中。当前显示原文说明。
Chat / code generation via 9Router using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through 9Router.
中文简介正在准备中。当前显示原文说明。