AI & agents.Sorted by weekly installs
18 results
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.
Keeps your agent's plan, findings and progress in markdown files on disk, so long tasks survive /clear, crashes and compaction.
Has your agent write a tight, ready-to-paste prompt for the AI tool you name, from Claude Code and Cursor to Midjourney and Sora.
A self-learning skill layer for Claude Code: distills skills from your real sessions, updates them as you work and prunes unused ones.
Turns a task into a copy-ready /goal command for Claude Code or Codex, with a checkable finish line and a stop bound.
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.
The .NET team's skill for picking the right AI or ML stack in .NET 8+ apps, from ML.NET to Microsoft.Extensions.AI and Agent Framework.
Finds the right NVIDIA skill for your task, from CUDA and cuOpt to robotics and Omniverse, and installs it when you say yes.
Build AI agents on Amazon Bedrock AgentCore with AWS's skills for scaffolding, tools, memory, evals, debugging and going live.
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.
Six skills that let your agent set up, write, run and analyze Coder Eval suites, including whether your Claude Code skills actually trigger.
SAP's MCP server for the Mobile Development Kit: your agent creates, builds, validates and deploys MDK mobile apps using SAP's docs.
Has your agent move code and prompts from Sonnet 4.x or Opus 4.1 to Claude Opus 4.5, from model strings to prompt fixes.
Has your agent write and run evals for Power Apps Code Apps and Generative Pages: feature checks, unit tests and a static security scan.