408 boosters for "orm" — open source, verified from GitHub, ready to install
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
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 :
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.
A system prompt for Claude Code that enforces defensive security practices and provides CLI guidance, designed to help developers safely use Claude for software engineering tasks while preventing misuse.
This skill enables AI assistants to create, configure, and manage datasets on Hugging Face Hub with SQL-based querying and transformation capabilities. It's valuable for developers building data workflows and ML projects that require programmatic dataset management.
This skill automates the process of adding, extracting, and managing evaluation results in Hugging Face model cards, supporting multiple data sources including Artificial Analysis API and custom evaluations with vLLM/lighteval. It's valuable for ML practitioners and model maintainers who need to track and display model performance metrics.
A skill for fine-tuning and training language models on Hugging Face's cloud GPU infrastructure using TRL, supporting SFT, DPO, GRPO methods and GGUF conversion for local deployment. Developers and ML engineers working with cloud-based model training benefit from this comprehensive guidance.
Generates per-category catalog JSON files from the npm package's public API. Each catalog lists all UseCase and EventHandler abstractions in a category with their resolved source file paths. LLMs read source files on demand for exact, up-to-date types — no enrichment phase needed. 1. Discovers all
"name": "understand-anything", "description": "AI-powered codebase understanding — analyze, visualize, and explain any project", "homepage": "https://github.com/Lum1104/Understand-Anything",
Do NOT check or review pull requests. Do NOT call commands. Run CodeRabbit locally against the working repository only. From the output, extract for each finding:
❶ One is a new React framework - target web and native with a single Vite plugin and fully shared code, so you can ship cross-platform nearly as easy as single-platform.
MIRIX is a Multi-Agent Personal Assistant with an Advanced Memory System. It features a six-agent memory architecture (Core, Episodic, Semantic, Procedural, Resource, Knowledge Vault) with screen activity tracking and privacy-first design. 1. Follow PEP 8 strictly 3. Documentation
Real-time monocular depth estimation using Depth Anything v2. Transforms camera feeds with colorized depth maps — near objects appear warm, far objects appear cool. When used for privacy mode, the blend mode fully anonymizes the scene while preserving spatial layout and activity, enabling security
A Cursor IDE rules file providing comprehensive UI/styling guidelines for building responsive React components with HeroUI, Tailwind CSS, and accessibility best practices. Developers building social media automation tools in Cursor will benefit from these standardized component patterns and design specifications.
Implementation patterns for Runway prod checklist — AI video generation platform. See related Runway skills for more workflows.
A physics tutoring booster that adapts explanations from intuitive reasoning to formal derivations based on learner level. Ideal for students, educators, and researchers seeking physics help across all difficulty tiers.
Agent Identity provides cryptographic on-chain identity registration and verification for AI agents, enabling them to prove authenticity across platforms by staking USDC. Useful for AI developers building multi-platform agents who need trustless identity verification.
Validate load balancer behavior including traffic distribution algorithms, health check mechanisms, failover scenarios, session persistence, and SSL termination. Supports testing for NGINX, HAProxy, AWS ALB/NLB, GCP Load Balancers, and Kubernetes Ingress controllers. 1. Verify basic load balancer co
Mudlet is a cross-platform MUD client built with Qt6 and C++20, providing scripting capabilities in Lua 5.1. The project emphasizes "powerful simplicity" - clean interface with deep customization options. All files should end with a newline character at the end of the file. In general: write modern
AGENTS.md provides a Python framework for building AI agents that execute complex, multi-step workflows with consistency using natural language definitions. Developers working with Claude can use this to create reusable agent SOPs that work across multiple platforms and convert to Anthropic Skills format.
"description": "Agentic SOC Platform Claude Plugin", "description": "A comprehensive toolkit for operating the ASP platform, including features such as case management,SIEM Query.", "source": "./PLUGINS/ClaudeCode",
Automates GitHub pull request reviews by analyzing code for bugs, security issues, performance problems, and test coverage gaps, then posts findings directly to GitHub. Essential for engineering teams using Claude in their development workflow.
Multi-pattern search/replace tool for bulk refactoring with simultaneous replacements, file/directory renaming, and case-preserving transformations. Then execute if output looks correct:
A CLI skill for interacting with Obsidian vaults—read, create, search, and manage notes, tasks, and properties directly from the command line, plus plugin/theme development support. Useful for developers and power users who want to automate vault operations and debug Obsidian extensions.
