Featured

affaan-m

prompt-optimizer is a skill that refines and optimizes user prompts for AI agents, ensuring effective communication and improved outcomes.

huggingface

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in Node.js and browsers (with WebGPU/WASM) using pre-trained models from Hugging Face Hub.

huggingface

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classifica

expo

Use Expo DOM components to run web code in a webview on native and as-is on web. Migrate web code to native incrementally.

expo

Set up Tailwind CSS v4 in Expo with react-native-css and NativeWind v5 for universal styling

n8n-io

create-skill is a workflow automation AI agent skill for Claude Code, designed to teach the agent focused workflows and integrate APIs for streamlined development.

langgenius

backend-code-review is a skill that analyzes Python code under the api/ directory, checking for quality, security, and best practices based on established checklist rules.

langgenius

component-refactoring is a skill that simplifies complex React components by applying refactoring patterns and workflows to improve code quality and reduce maintenance efforts.

obra

Use when creating new skills, editing existing skills, or verifying skills work before deployment

affaan-m

api-design is a skill for creating well-structured REST APIs, following best practices for resource naming, HTTP methods, and error handling.

affaan-m

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

affaan-m

click-path-audit is a behavioural flow audit skill that traces every interactive touchpoint to find bugs where functions individually work but cancel each other out.