By leeroo-ai
Supercharge AI coding agents for ML engineering: diagnose failures like OOM/NaN/crashes, verify code/configs against Hugging Face/PyTorch docs pre-training, generate grounded fine-tuning plans and next steps, maintain persistent experiment journals, deep-dive frameworks like vLLM/DeepSpeed, and optimize inference pipelines.
npx claudepluginhub leeroo-ai/superml --plugin supermlUse when something is failing in ML/AI work — OOM, NaN, divergence, crashes, bad throughput, wrong outputs, dependency conflicts
Use when starting, logging, or reviewing ML experiments — maintains a persistent experiment journal with hypotheses, results, and learnings across sessions
Use when the user is stuck, needs ranked next steps, or wants alternatives after initial experiments — "I tried X and got Y, what next?"
Use when the user wants an implementation plan, architecture design, or multi-step ML pipeline — "build X", "implement X", "design X", "set up X"
Use when the user wants to understand an ML/AI topic, compare approaches, or survey framework capabilities — "how does X work?", "compare X vs Y"
Use when the user wants to verify code, config, or math before running — or proactively before any expensive training job or deployment
Use when starting any conversation involving ML/AI — establishes how to use Leeroopedia KB tools and workflow skills
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
External network access
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Complete developer toolkit for Claude Code
AI-supervised issue tracker for coding workflows. Manage tasks, discover work, and maintain context with simple CLI commands.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams