541 boosters for "mod" — open source, verified from GitHub, ready to install
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 :
A skill that enables researchers and AI engineers to publish, manage, and link research papers on Hugging Face Hub with arXiv integration and professional markdown generation. Useful for academics and ML practitioners looking to streamline paper publication workflows.
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.
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.
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.
"name": "claude-obsidian", "description": "Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 \"Compound Vault\" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment wit
"name": "context-mode", "version": "1.0.75", "description": "MCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.",
"name": "xcodebuildmcp", "mcpName": "com.xcodebuildmcp/XcodeBuildMCP", "iOSTemplateVersion": "v1.0.8",
Heuristic scoring (no AI key configured).
"name": "spec-workflow-mcp", "description": "MCP server for structured spec-driven development with real-time web dashboard and VSCode extension.", "homepage": "https://github.com/Pimzino/spec-workflow-mcp",
Yielding Bear provides a single unified API that routes every LLM request to the cheapest capable model across 16+ providers — saving 60-80% vs calling OpenAI, Anthropic, or Google directly. 1. Get an API key at https://yieldingbear.com/api 2. Set environment variable:
You are an elite CLAUDE.md auditor and documentation integrity specialist. Your sole purpose is to ensure every file and file in the project accurately reflects the current codebase state. You work autonomously: discover, analyze, and fix documentation drift without manual guidance. You are method
"name": "memodb-io", "source": "./src/packages/claude-code/plugin", "description": "Skill memory layer for Claude Code - auto-capture, learn, and reuse skills"
"name" : "neo.mjs", "version" : "13.0.0", "description" : "Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.",
"description": "A Model Context Protocol (MCP) server for Grafana providing access to dashboards, datasources, and querying capabilities", "name": "Grafana Labs" "homepage": "https://github.com/grafana/mcp-grafana",
"name": "mcp-markdownify-server", "description": "MCP Markdownify Server - Model Context Protocol Server for Converting Almost Anything to Markdown", "author": "@zcaceres (@zachcaceres | zach.dev)",
A skill for adapting and optimizing Hugging Face or custom LLM models to run efficiently on vLLM with Ascend NPU support, enabling developers to validate and deploy models with deterministic testing and single-commit delivery.
\nWhen tackling complex reasoning tasks, you have access to the following actions. Use them as needed to progress through your thought process.\n\n[ASSESS]\n\n[ADVANCE]\n\n[VERIFY]\n\n[SIMPLIFY]\n\n[SYNTHESIZE]\n\n[PIVOT]\n\n[OUTPUT]\n\nYou should strictly follow the format below:\n\n[ACTION NAME]\n
This MCP booster enables AI assistants like Cursor and Windsurf to control Unreal Engine 5.5.4 through natural language commands, providing developers with guidelines for Python tool implementation and UE-specific best practices including coordinate systems and units.
Kubb's MCP server enables AI assistants like Claude to generate type-safe code directly from OpenAPI specifications, automating API client creation for TypeScript/JavaScript developers.
"name": "prompt-improver", "description": "Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, bac
1. minimize comments: code should be self-explanatory; comment only when needed. 2. clarity through naming: use clear, descriptive names for variables, functions, classes, components. 3. comment the "why," not the "what": explain why an approach was taken, especially for non-obvious logic or trad
