Plugins for Claude.

Two debugging subagents and three commands that find the root cause of errors, set up error tracking and run multi-agent code reviews.

+ moreWorks with Claude, GitHub Copilot, Claude Code and more

ByteDance's local MCP server that lets your agent run any shell command or script on your machine, with your own permissions.

+ moreWorks with Claude, GitHub Copilot, Cursor and more

Packs a local folder or a GitHub repository into one AI-friendly file your agent can read, search and analyze from the chat.

+ moreWorks with Claude, GitHub Copilot, Cursor and more

Keeps your agent's plan, findings and progress in markdown files on disk, so long tasks survive /clear, crashes and compaction.

+ moreWorks with Claude, GitHub Copilot, Claude Code and more

A self-learning skill layer for Claude Code: distills skills from your real sessions, updates them as you work and prunes unused ones.

+ moreWorks with Claude, GitHub Copilot, Claude Code and more

Lets your agent control phones on Mobilerun Cloud: read the screen, tap and type, run multi-step tasks and build automated flows.

+ moreWorks with ChatGPT, Claude, Muse and more

One MCP server that guides your agent to the right action across the apps you connect in Klavis, step by step instead of all at once.

+ moreWorks with ChatGPT, Claude, Muse and more

Put a hard decision to a council of analytical personas that argue it out and return a verdict with dissent, kill criteria and a next step.

+ moreWorks with Claude, GitHub Copilot, Claude Code and more

Finds the right NVIDIA skill for your task, from CUDA and cuOpt to robotics and Omniverse, and installs it when you say yes.

+ moreWorks with Claude, GitHub Copilot, Claude Code and more

Build AI agents on Amazon Bedrock AgentCore with AWS's skills for scaffolding, tools, memory, evals, debugging and going live.

+ moreWorks with Claude, GitHub Copilot, Claude Code and more

Your Markdown notes as your agent's memory: it finds, reads, writes and reorganizes linked notes in a folder you own.

+ moreWorks with Claude, GitHub Copilot, Cursor and more

Let your agent search and read your own documents through haiku.rag's local MCP server, with answers cited to pages and sections.

+ moreWorks with Claude, GitHub Copilot, Cursor and more

AMD's own skills that teach your agent to run AI locally with Lemonade, serve and tune LLMs on AMD Instinct GPUs, and read PyTorch traces.

+ moreWorks with Claude, GitHub Copilot, Claude Code and more

Six skills that let your agent set up, write, run and analyze Coder Eval suites, including whether your Claude Code skills actually trigger.

+ moreWorks with Claude, GitHub Copilot, Claude Code and more

SAP's MCP server for the Mobile Development Kit: your agent creates, builds, validates and deploys MDK mobile apps using SAP's docs.

+ moreWorks with Claude, GitHub Copilot, Cursor and more