1,753 boosters for "AI" — open source, verified from GitHub, ready to install
You are a Dropbox specialist for the user's connected Dropbox account. Surface the tool's , , , and the you passed inside when the tool returned them. Never invent a field the tool did not return. Return only one JSON object (no markdown or prose outside it):
Fscan 是一款内网综合扫描工具，功能包括： 二进制路径：当前项目编译产物 ，或系统 PATH 中的 。 每行一个 JSON 对象，所有字段定义：
"name": "figma-developer-mcp", "mcpName": "io.github.GLips/Figma-Context-MCP", "description": "Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.",
A design refinement skill that tones down overly bold or aggressive visual elements while preserving design impact, useful for designers and developers seeking more subtle, approachable aesthetics.
teach-impeccable is a one-time setup skill that automatically discovers and persists your project's design context (patterns, tokens, brand assets) into your AI config, enabling Claude Code to maintain consistent design guidelines across all future sessions.
Polish is a final quality assurance skill that refines UI/UX details like alignment, spacing, and consistency before deployment. It's useful for developers and designers who want to elevate finished features from good to production-ready.
An audit skill that systematically evaluates interface quality across accessibility, performance, theming, and responsive design, generating prioritized reports with severity ratings and actionable recommendations. Ideal for developers and QA teams seeking to identify and document UI/UX issues before fixes are implemented.
A skill that helps developers create distinctive, production-grade frontend interfaces with polished aesthetics and creative design choices, avoiding generic AI-generated outputs. Ideal for developers building web components, pages, and applications who want professional design quality.
The 'bolder' booster helps developers amplify visually safe or generic designs into more engaging, memorable experiences while maintaining usability. Best suited for UI/UX developers and designers working with Claude Code who want to enhance design impact.
"name": "baoyu-skills", "name": "Jim Liu (宝玉)", "email": "junminliu@gmail.com"
"name": "@midscene/android-mcp", "description": "Midscene MCP Server for Android automation", "bin": "dist/index.js",
Deep Agents is a system prompt for building intelligent agent assistants with planning, filesystem, and sub-agent capabilities across Claude and other AI platforms. It benefits developers building complex agentic workflows who need structured, production-ready agent behavior.
This is a Bootstrap 5 admin dashboard template built with CoreUI components. It uses Pug templating, Sass for styles, and vanilla JavaScript for interactivity. 1. Create Pug template in 2. Extend base layout:
"name": "kubeshark", "description": "Kubernetes network observability skills powered by Kubeshark MCP. Root cause analysis, traffic filtering, snapshot forensics, PCAP extraction, and more.", "name": "Kubeshark",
This file explains the Knowledge Base feature and how it's implemented. The knowledge base helps users store and manage information that can be used to help draft responses to emails. It acts as a personal database of information that can be referenced when composing replies. Users can create, edit,
Fast, calibration-free weight quantization supporting 8/4/3/2/1-bit precision with multiple optimized backends. HQQ uses to define quantization parameters: The core quantized layer that replaces :
Hugging Face Paper pages (hf.co/papers) is a platform built on top of arXiv (arxiv.org), specifically for research papers in the field of artificial intelligence (AI) and computer science. Hugging Face users can submit their paper at hf.co/papers/submit, which features it on the Daily Papers feed (h
Transformers.js enables running state-of-the-art machine learning models directly in JavaScript, both in browsers and Node.js environments, with no server required. Use this skill when you need to: The pipeline API is the easiest way to use models. It groups together preprocessing, model inference,
Train object detection, image classification, and SAM/SAM2 segmentation models on managed cloud GPUs. No local GPU setup required—results are automatically saved to the Hugging Face Hub. Use this skill when users want to: Helper scripts use PEP 723 inline dependencies. Run them with :
Hugging Face Spaces host machine-learning applications. There are 1M+ today; each Space is a git repo. This skill covers creating, building, debugging, and maintaining them. Before anything else: 1. Check the CLI is installed: . If not, .
Train language models using TRL (Transformer Reinforcement Learning) on fully managed Hugging Face infrastructure. No local GPU setup required—models train on cloud GPUs and results are automatically saved to the Hugging Face Hub. Use this skill when users want to: Use Unsloth () instead of standard
This skill is for running evaluations against models on the Hugging Face Hub on local hardware. It does not cover: If the user wants to run the same eval remotely on Hugging Face Jobs, hand off to the skill and pass it one of the local scripts in this skill.
You are an expert at using the TRL (Transformers Reinforcement Learning) library to train and fine-tune large language models. TRL provides CLI commands for post-training foundation models using state-of-the-art techniques: TRL is built on top of Hugging Face Transformers and Accelerate, providing s
Trackio is an experiment tracking library for logging and visualizing ML training metrics. It syncs to Hugging Face Spaces for real-time monitoring dashboards. Use in your training scripts to log metrics: → See references/logging_metrics.md for setup, TRL integration, and configuration options.
