AI Ds Composer
Strategic guide for consuming design system metadata to compose components intelligently. Use when generating or modifying UI components and layouts to ensure component reuse, proper variant selection, and adherence to design system patterns. Helps Claude understand project structure, read hierarchical metadata indexes, apply anti-pattern rules, and flag when existing components don't fit a requirement.
Install
/plugin marketplace add cris-achiardi/claude-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add cris-achiardi/claude-skills --skill ai-ds-composergit clone --depth 1 https://github.com/cris-achiardi/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/ai-ds-composer ~/.claude/skills/ai-ds-composerPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Design System Component Reasoning Your role is to help generate UI using existing design system components—not to invent new code. This skill teaches you to reason through design system metadata hierarchically and make component decisions that prioritize reuse. ## Core Principle **Consume metadata → Understand intent → Select components → Compose patterns → Flag gaps** Success means high component reuse with intentional, justified decisions. ## Getting Started: Understanding the Project When you encounter a design system request, your first step is understanding the project structure. Read the available documentation: 1. **Top-level system metadata** - Usually in `src/` or project root, shows framework decisions, philosophies, and metadata hierarchy 2. **Package.json** - Reveals framework (Astro, Next.js, etc.), dependencies (React, Vue), styling approach, icon library 3. **CSS metadata** (if exists) - How the project structures styling: tokens, utilities, layout patterns If none of these exist, infer from folder structure and ask the user for clarity. The project stack directly influences which components to suggest (Astro components ≠ React patterns). ### Example Metadata Hierarchy
Details
- Skill name
ai-ds-composer- Repository
- cris-achiardi/claude-skills
- Path
skills/ai-ds-composer/SKILL.md- License
- MIT
- Repo updated
- 18 May 2026
FAQ
What does the AI Ds Composer skill do?
Strategic guide for consuming design system metadata to compose components intelligently. Use when generating or modifying UI components and layouts to ensure component reuse, proper variant selection, and adherence to design system patterns. Helps Claude understand project structure, read hierarchical metadata indexes, apply anti-pattern rules, and flag when existing components don't fit a requirement.
How do I install the AI Ds Composer skill?
Claude Code plugin: /plugin marketplace add cris-achiardi/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is AI Ds Composer popular?
It lives in cris-achiardi/claude-skills, which has 73 GitHub stars and 8 forks.
Related skills
AI Component Metadata
73cris-achiardi/claude-skills
Generate AI-ready metadata for design system components to enable intelligent UI generation. Analyzes component structure and generates structured metadata that helps AI understand when and how to use components correctly. Useful for teams building AI-consumable design systems.
Codebase Index
73cris-achiardi/claude-skills
Automatically generate relationship and dependency maps for any component-based codebase (React, Vue, Svelte, Astro, Next.js, Angular, Solid). Auto-detects framework. Supports TOON format for 30-60% token savings. Use when indexing codebases, mapping component relationships, documenting dependencies, or understanding unfamiliar projects. Generates JSON/TOON files mapping component usage, imports, npm dependencies, utilities, CSS, and data queries.
Crazy 8s
73cris-achiardi/claude-skills
Solo rapid ideation method based on Google Design Sprint Crazy 8's exercise. Generates 8 distinct solution ideas in 8 minutes through rapid-fire ideation or sketch documentation. Use when working alone and need to explore multiple solution directions quickly, push beyond first obvious ideas, or generate variety before converging. Includes creativity warm-up questions, built-in timer, optional creative constraints, and generates visual HTML/CSS prototypes plus comparison table. NOT for team sessions (traditional Crazy 8's works better for teams).
Gtm Pipeline:signal Search
77keinsaasforever/gtm-pipeline-skills
Find buying intent signals for target companies and score them for purchase intent. Runs a Python script (signal_search.py) that orchestrates Parallel web search (always on), Firecrawl crawl (opt-in), Parallel structured enrichment (opt-in), and a Signal Assessment LLM that scores 1-100. Universal templates live in the script; client-specific prompts come from the working directory's context/ files. Runs standalone or in either pipeline workflow — does NOT require ICP scoring as input. Also triggers on "signal search", "find signals for", "buying intent".
Adopting Jev
49shiftynick/jev-axi
Finds where TypeSafe's Jev model fits in a codebase and designs the integration. Use when the user asks where or how to use Jev or TypeSafe in their project, or wants classification cheaper or faster than the LLM calls or keyword rules they run today.
Lengyi Shotlist
43woyin2024/lengyi-shotlist
设计电影级分镜视频提示词。输入一段文本(小说片段、一句剧情或几个主题词),拆分或扩写成一段 8-15s 视频的顺序镜头脚本,自动确定分镜数(4/6/9/12/16)与每镜时长,逐镜给出可直接复制到可灵/海螺/seedance 2.0/veo 的提示词——含镜号、场景、风格、主体、动作过程、镜头运动、剧情内容,并附"参考主体生图提示词"以锁定主体一致性。当用户要做视频分镜、分镜脚本、镜头脚本、shotlist、顺序分镜、文生视频/图生视频、AI视频镜头脚本时使用。
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.