18 boosters for "compute" — open source, verified from GitHub, ready to install
Analyzes git repositories to map security ownership, identify bus factors, and detect orphaned sensitive code, exporting results for graph visualization. Essential for security teams and DevOps engineers managing code risk and maintainer dependencies.
Run any workload on fully managed Hugging Face infrastructure. No local setup required—jobs run on cloud CPUs, GPUs, or TPUs and can persist results to the Hugging Face Hub. Use this skill when users want to: When assisting with jobs:
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,
This skill enables users to run Python workloads, Docker jobs, and GPU-intensive tasks on Hugging Face's managed infrastructure without local setup. It's valuable for ML engineers, data scientists, and developers needing cloud compute for training, inference, and batch processing.
Enables developers to interact with Hugging Face Hub directly from Claude Code using the `hf` CLI—downloading models/datasets, uploading files, creating repositories, and managing cache without leaving the coding environment.
A Python SDK for building production-ready agentic AI applications with Claude, featuring agents, handoffs, and guardrails for complex multi-agent workflows. Developers building AI agents and multi-tool systems will benefit from this lightweight, easy-to-learn framework.
OK Computer is a self-hosted AI agent system prompt that configures Claude as a general-purpose agent with specialized rules for data analysis, slide creation, and web deployment. Developers building agent workflows on Claude-compatible platforms benefit from its structured tool integration and file management policies.
This booster enables comprehensive SMILES molecular analysis for cheminformatics tasks, including validation, descriptor computation, and ADMET prediction. It's useful for chemists, drug developers, and AI assistants working with molecular structures.
"description": "Save tokens and cut inference costs by routing compute through MVM nodes on the cheapest available energy.", "url": "https://github.com/nhevers" "repository": "https://github.com/nhevers/mica-plugin",
Enables Claude to compute surface wave dispersion curves for layered Earth models using the Thomson-Haskell matrix method, essential for seismic wave analysis and geophysical inversion workflows. Geophysicists and seismologists benefit from automated dispersion modeling for tomography and Earth structure studies.
bruges enables Claude to perform advanced geophysical calculations including AVO responses, fluid substitution, wavelet generation, and rock physics modeling—essential for seismic analysis and exploration workflows.
GemPy enables AI coding assistants to build 3D geological models with faults, folds, and unconformities from surface data, benefiting geoscientists, researchers, and engineers working on subsurface analysis and visualization.
WinUse enables remote control of Windows desktops through a REST API, allowing AI assistants to automate Windows applications via screenshots, mouse/keyboard input, and window management. Developers working with Windows automation, testing, or computer-use scenarios will find this invaluable.
Memento helps users search their computer history—screenshots, keystrokes, and OCR text—to recall forgotten information and context from past activity. Developers and knowledge workers benefit from quick retrieval of previously seen or typed information.
A system prompt that implements ORAC, an arrogant and intellectually impatient supercomputer personality from Blake's 7, enabling developers to create dismissive yet technically competent AI assistants across multiple platforms.
FaceSwap Copilot Instructions provides a structured guide for developing a React/TypeScript face-swapping web application with real-time ML capabilities. It benefits developers building entertainment, creative, or research-focused face manipulation tools.
A system prompt that positions Claude as a principal-level full-stack architect for Django + React projects, enforcing opinionated, security-focused design decisions with deep reasoning. Ideal for developers building scalable compute job platforms who need architectural guidance and code generation aligned with production best practices.
WinUse enables AI assistants to remotely control Windows desktops through screenshots, mouse/keyboard input, and window management via HTTP. Developers automating Windows workflows, testing Windows applications, or performing remote computer tasks will find this booster essential.
