Catches when your project drifts from its own decisions. Local-first cross-agent memory MCP.

Academic research MCP server for paper search, citation checks, graphs, and deep research.

NVIDIA GPU metrics as MCP tools — utilization, memory, temperature, power. Supports MIG.

MCP server for the Krónan grocery store API (Iceland)

Sourcegraph code search, semantic search, go-to-definition, find-references, and diff search.

Mirror MCP: Introspection for LLMs

MCP server for IT Glue — organizations, configurations, passwords, flexible assets, and documents.

MCP server for iCloud (Apple) Calendar access via CalDAV

Production-ready Claude Code skills for server-side Swift (Vapor, Hummingbird) and Xcode Cloud CI/CD

Multi-agent orchestration plugin for Claude Code — 11 AI agents with intelligent model routing, 3-layer codebase indexing, and auto skill injection

A collection of skills focused on end-to-end automation for AI agents.

🔥🔥 A Claude Skill that teaches Claude Code how to write LLM features

Agent skill for Senzing entity resolution — data mapping, SDK code generation, documentation search, error troubleshooting, and sample data via the Senzing MCP server

Zero-human full-stack deployment skill bundle for AI agents — GitHub + Dokploy + Convex (self-hosted & Cloud) + Vercel + Hostinger DNS, via modular /sc-* slash commands.

A Claude Code plugin that packages Alfresco extension development as slash commands, skills, and agents

Readable agent skills with optional declarative YON protocols you can inspect and validate. A personal, field-used pack by Alexandru Mares.

Agentic loops and AI agent capabilities for the Laravel AI SDK

This skill accommodates Agent-to-Agent communitcation: e.g. Codex asking Claude for a review, treating it as a worker, teammate, thinking partner.

jup is a command-line tool for installing and managing agent skills across different ai agents, scopes, and projects.

Production-grade engineering skills for AI coding agents, built on Amazon Way of building services

AI skills for integrating the Unlayer drag-and-drop editor. Install with: npx skills add unlayer/unlayer-skills

A opinionated collection of agent skills organized by domain: dev, writing, productivity, and knowledge management

12 agent skills for AI-driven software development — a gated idea-to-ship pipeline: 7w3 design, build-ready specs, executable architecture, honest review loops, a parallel worker-fleet lane, QA, safe deploy. Works with Claude Code, Codex, Cursor and any skills-capable agent. No vibecode.

OpenClaw operations skill for AI agents — 1.5K installs on skills.sh

A curated collection of mostly handcrafted skills encoding our more than a decade worth of best practices, proven patterns and lessons learned for Angular / NgRx frontend development which scales from SaaS MVP to enterprise scale environments

Claude Agent SDK with a E2E testing tool

Official Agentcard skill — give your AI agent a virtual card: fund a wallet with Apple Pay/Google Pay, create single-use or multi-use cards, shop and check out. Works with Claude Code, Cursor, and 70+ agents.

Personal collection of Agent Skills for AI coding agents (Claude Code, Gemini CLI, Cursor, Codex, etc.)

A multi-agent context, rules, and hooks boilerplate generator. With a single command, it scaffolds conventions, namespaced skills, stack-appropriate settings, and interactive guardrails for seven major AI coding environments, matching each agent's native file formats and capability profiles.

Curated, auto-synced collection of 2,000+ Claude Code & Codex skills for AI4Protein, bioinformatics, AI development, and academic paper writing. One curl command installs them all.

Security audit skill for LLM agents - prompt injection scanner, attack catalog & defense checklist

Access Obsidian vaults via Local REST API - read, search, and interact with notes

Local memory engine for AI agents with knowledge graphs, forgetting, and semantic recall

Zero-Knowledge Context™ & Neural Handover™ for AI Agents. The Trust Layer for AI Memory.

Manage Proxmox VE clusters through AI assistants — VMs, containers, and more

Cashfree MCP server for cashfree docs and APIs

One MCP connection for all your tools — with discovery, namespacing, and execution policies.

Semantic code & doc search with keyword boost. AST code nav, auto HF mirror, local, privacy-first.

Model Context Protocol (MCP) server for DeployHQ API integration

Behavioral memory layer for AI tools. Learns preferences and context across Claude, Cursor, Codex.

Powerful tools for automating Google Sheets using Model Context Protocol (MCP)

MCP server for Cinema 4D — entity CRUD, parameter-level access, batched undo, security controls.

Local DevDocs MCP Server (Developer Docs with project specific context awareness)

Shared, project-aware memory for Claude Code, Codex, and other agents with human review.

MCP server aggregating developer infrastructure deals, free tiers, and startup programs

Sandboxed computer-use for AI agents: drive real browser + desktop apps in nested X11 windows

MCP server for the Semantic Scholar API: search 200M+ papers, citations, authors, recommendations.

AI-powered web scraping MCP. Distill pages to Markdown or extract structured data via JSON Schema.

AI-powered web scraping MCP. Distill pages to Markdown or extract structured data via JSON Schema.

MCP server for YADE — open-source DEM engine. Browse API docs, run simulations, manage tasks.

AI Agent plugin for Autoresearch with AI (Claude, OpenClaw, etc) to improve anything!

State-of-the-Art (2026) AI/LLM engineering skills/agents for building and auditing software — 40+ domain & language skills, BUILD/AUDIT modes, audit checklists.

Mirko Bozzetto's curated skills for AI coding agents (Claude Code, Codex, Cursor, ...)

Agent-Native CLI design & review skill — design CLIs that serve humans, AI agents, and orchestration systems simultaneously

🥋 Claude Code plugin that teaches programming while you vibecode — contextual explanations, micro-quizzes, and belt progression. Free & open source by Dojo Coding.

Claudikins Automatic Context Manager - seamless context handoff for Claude Code

Agent skill for task management in Obsidian reads and writes your TaskNotes directly as markdown files. Pairs with llm-wiki-claude-skills for an assisted knowledge + task workflow.

An AI agent that explores your AWS account and draws what it finds. Not a perfect map. A useful one.

Free Collaborative Dynamics Augment for risk-driven software verification, skeptical review, and isolated Agent behavioral evals.

Official AI Agent skills for building with Zvec vector database