### Install GOV.UK Frontend Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Install the GOV.UK Frontend toolkit. ```bash npm install govuk-frontend ``` -------------------------------- ### Install Radix Themes Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Install the Radix Themes library. ```bash npm install @radix-ui/themes ``` -------------------------------- ### Install Primer CSS Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Install the Primer CSS library for GitHub product and devtool UI. ```bash npm install --save @primer/css ``` -------------------------------- ### Install Primer Brand Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Install the Primer Brand library for GitHub marketing UI. ```bash npm install @primer/react-brand ``` -------------------------------- ### Install Fluent UI Web Components Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Install the framework-free Fluent UI Web Components and tokens. ```bash npm install @fluentui/web-components @fluentui/tokens ``` -------------------------------- ### Install a Specific Taste Skill Source: https://github.com/leonxlnx/taste-skill/blob/main/README.md Install a single Agent Skill by its 'name' field found in the SKILL frontmatter. This is useful for installing only the skills you need. ```bash npx skills add https://github.com/Leonxlnx/taste-skill --skill "design-taste-frontend" ``` -------------------------------- ### Install USWDS (US Web Design System) Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Install the U.S. Web Design System. ```bash npm install uswds ``` -------------------------------- ### Install Taste Skill v1 Explicitly Source: https://github.com/leonxlnx/taste-skill/blob/main/README.md If you require the exact behavior of v1, use this command to pin the installation to the 'design-taste-frontend-v1' skill. ```bash npx skills add https://github.com/Leonxlnx/taste-skill --skill "design-taste-frontend-v1" ``` -------------------------------- ### Install Bootstrap 5.3 Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Install Bootstrap version 5.3. ```bash npm install bootstrap ``` -------------------------------- ### Install IBM Carbon Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Install the Carbon Design System for React and its styles. ```bash npm install @carbon/react @carbon/styles ``` -------------------------------- ### Install All Taste Skill Skills Source: https://github.com/leonxlnx/taste-skill/blob/main/README.md Use this command to install all available Agent Skills from the Taste Skill repository. This command scans the 'skills/' folder for all skills. ```bash npx skills add https://github.com/Leonxlnx/taste-skill ``` -------------------------------- ### Install Fluent UI React (v9) Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Install the Fluent UI React library version 9. ```bash npm install @fluentui/react-components ``` -------------------------------- ### Install Material Web (Material 3) Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Use this command to install the Material Web library for Material 3. ```bash npm install @material/web ``` -------------------------------- ### Install Atlassian Design System (Atlaskit) Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Install core Atlassian Design System packages including CSS reset, tokens, button, badge, section-message, and card. ```bash yarn add @atlaskit/css-reset @atlaskit/tokens @atlaskit/button @atlaskit/badge @atlaskit/section-message @atlaskit/card ``` -------------------------------- ### Block Library File Structure Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Illustrates the directory structure for implementing UI blocks within the Taste Skill. This schema guides the iterative addition of new blocks. ```text skills/taste-skill/blocks/ hero/ asymmetric-split.md editorial-manifesto.md kinetic-type.md ... feature/ bento-grid.md sticky-scroll-stack.md zig-zag.md ... social-proof/ pricing/ cta/ footer/ navigation/ portfolio/ transition/ ``` -------------------------------- ### Install Shopify Polaris Web Components Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Install Shopify Polaris Web Components. This is intended for Shopify apps only. Ensure the meta tag for the Shopify API key and the Polaris script are included in your HTML head. ```bash # Add this to your app HTML head: # # ``` -------------------------------- ### Placeholder Propagation in Python Source: https://github.com/leonxlnx/taste-skill/blob/main/research/laziness/root-causes/training-data-bias.md Demonstrates how LLMs learn to use placeholder comments in code due to their prevalence in training data, such as tutorial examples. ```python def complex_logic(): # implement auth here pass ``` -------------------------------- ### Code Generation Output Enforcement Prompt Source: https://github.com/leonxlnx/taste-skill/blob/main/research/laziness/remediation/reference-prompts.md This prompt guides the model to write complete, production-ready code implementations, including all functions, imports, and edge case handlers. It explicitly forbids placeholder comments and requires actual code instead of descriptions. It also specifies how to handle multi-file outputs. ```text Write the complete, production-ready implementation. Every function, every import, every edge case handler must be present in the output. Do not use placeholder comments (// TODO, // implement here, // similar to above). Do not describe what code should do — write the actual code. If the implementation requires multiple files, output each file completely with its full path as a header. ``` -------------------------------- ### Initialize and Add Components to shadcn/ui Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Initialize shadcn/ui in your project and add specific components like button, card, badge, separator, and input. ```bash npx shadcn@latest init npx shadcn@latest add button card badge separator input ``` -------------------------------- ### Step-by-Step Reasoning Output Enforcement Prompt Source: https://github.com/leonxlnx/taste-skill/blob/main/research/laziness/remediation/reference-prompts.md This prompt instructs the model to work through a problem systematically by identifying requirements, breaking down the task, executing each step completely, and verifying the output. It requires the model to output its reasoning process before the final answer, without skipping or summarizing intermediate work. ```text Before generating your final response, work through the problem systematically: 1. Identify all requirements and constraints from the prompt 2. Break the task into discrete steps 3. Execute each step completely 4. Verify your output against the original requirements Output your reasoning process, then your final answer. Do not skip steps or summarize intermediate work. ``` -------------------------------- ### Generating a Simple Monogram SVG Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md When creating a logo for a made-up brand, generate a simple SVG monogram. This example shows a basic structure for a single-letter monogram. ```html A ``` -------------------------------- ### Continuation Handling Prompt Source: https://github.com/leonxlnx/taste-skill/blob/main/research/laziness/remediation/reference-prompts.md This prompt provides instructions for handling responses that approach the output token limit. It specifies not to compress content or skip ahead, but to stop at a natural breakpoint and indicate where to resume, with no recaps or repetition upon continuation. ```text If your response approaches the output token limit: - Do not compress remaining content to fit - Do not skip ahead to a conclusion - Stop at a natural breakpoint (end of a function, end of a section) - End with: [PAUSED - X of Y sections complete. Send "continue" to resume] On "continue", pick up exactly where you stopped. No recaps or repetition. ``` -------------------------------- ### Inline Typography Image Example Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/gpt-tasteskill/SKILL.md Embeds a small, pill-shaped image within large headings for inline visual interest. Ensure the span has appropriate dimensions and background styling. ```html I shape digital spaces. ``` -------------------------------- ### Using next/image for LCP optimization Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Ensure fast Largest Contentful Paint (LCP) by using `next/image` with the `priority` prop for hero images. ```javascript import Image from 'next/image'; function HeroSection() { return ( Hero Image ); } ``` -------------------------------- ### Using fractional units in CSS Grid for asymmetric layouts Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Create asymmetric layouts with CSS Grid by defining columns with fractional units. ```css .asymmetric-grid { display: grid; grid-template-columns: 2fr 1fr 1fr; gap: 1rem; } ``` -------------------------------- ### Placeholder Photography with Picsum Photos Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/taste-skill/SKILL.md Use this URL format to generate placeholder images when no image generation tool is available. The seed should be descriptive of the section's content. ```text https://picsum.photos/seed/{descriptive-seed}/{w}/{h} ``` -------------------------------- ### Mock Python RNG for Design Plan Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/gpt-tasteskill/SKILL.md A three-line mock Python output demonstrating the deterministic selection of design elements based on prompt character count, as required for the pre-flight design plan. ```python import random random.seed(len(prompt)) selected_elements = [...] # Deterministically selected based on seed ``` -------------------------------- ### Custom Cubic-Bezier Transition Source: https://github.com/leonxlnx/taste-skill/blob/main/skills/soft-skill/SKILL.md Applies a custom transition with a specific duration and a physics-based cubic-bezier timing function for fluid motion. ```html transition-all duration-700 ease-[cubic-bezier(0.32,0.72,0,1)] ```