Leeroo-AI

17 mods across 2 repositories, 207 stars between them.

superml

01

Leeroo-AI/superml

Plugin Claude Code

ML engineering plugin for Claude Code.

193 5mo ago A tokens not measured original Apache-2.0

superml

02

Leeroo-AI/superml

Plugin Claude Code

ML engineering plugin: Give your AI coding agent ML engineering superpowers.

193 5mo ago A tokens not measured original Apache-2.0

leeroopedia

03

Leeroo-AI/superml

MCP server Claude CodeCodexCursor +2

MCP server "leeroopedia", hosted remotely at mcp.leeroopedia.com, as configured in Leeroo-AI/superml.

193 5mo ago A tokens not measured original Apache-2.0

ml-expert

04

Leeroo-AI/superml

Agent

Senior ML/AI engineer agent for heavy-lift tasks — training config reviews, serving/inference optimization, pipeline debugging, framework deep-dives, architecture decisions. Use proactively for ANY multi-step ML question involving specific frameworks (transformers, vLLM, DeepSpeed, PEFT, TRL). Maintains persistent…

193 5mo ago A 373 tokens original Apache-2.0

SessionStart

05

Leeroo-AI/superml

Hook

Runs when a session starts, executing run-hook.cmd. From Leeroo-AI/superml.

193 5mo ago A tokens not measured copy · 72% Apache-2.0

ml-debug

06

Leeroo-AI/superml

Skill Claude CodeCodex

Use when something is failing in ML/AI work — OOM, NaN, divergence, crashes, bad throughput, wrong outputs, dependency conflicts.

193 5mo ago A 32 tokens original Apache-2.0

ml-experiment

07

Leeroo-AI/superml

Skill Claude CodeCodex

Use when starting, logging, or reviewing ML experiments — maintains a persistent experiment journal with hypotheses, results, and learnings across sessions.

193 5mo ago A 30 tokens original Apache-2.0

ml-iterate

08

Leeroo-AI/superml

Skill Claude CodeCodex

Use when the user is stuck, needs ranked next steps, or wants alternatives after initial experiments — "I tried X and got Y, what next?".

193 5mo ago A 34 tokens original Apache-2.0

ml-plan

09

Leeroo-AI/superml

Skill Claude CodeCodex

Use when the user wants an implementation plan, architecture design, or multi-step ML pipeline — "build X", "implement X", "design X", "set up X".

193 5mo ago A 38 tokens original Apache-2.0

ml-research

10

Leeroo-AI/superml

Skill Claude CodeCodex

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".

193 5mo ago A 37 tokens original Apache-2.0

ml-verify

11

Leeroo-AI/superml

Skill Claude CodeCodex

Use when the user wants to verify code, config, or math before running — or proactively before any expensive training job or deployment.

193 5mo ago A 29 tokens original Apache-2.0

using-superml

12

Leeroo-AI/superml

Skill Claude CodeCodex

Use when starting any conversation involving ML/AI — establishes how to use Leeroopedia KB tools and workflow skills.

193 5mo ago A 26 tokens original Apache-2.0

leeroopedia-mcp

13

Leeroo-AI/leeroopedia-mcp

Skill Claude CodeCodex

Use Leeroopedia MCP to fetch grounded ML/AI best practices, build and review ML plans, debug failures, verify code/math correctness, and expand KB citations via getpage.

14 6mo ago A 42 tokens original MIT

Leeroo-AI/leeroopedia-mcp

Skill Claude CodeCodex

You have access to Leeroopedia, a curated ML/AI knowledge base, via MCP tools. These are real MCP tools registered in your environment -- call them directly like any other tool. They contain framework-specific docs, code examples, API references, and best practices.

14 6mo ago A 0 tokens original MIT

llm_post_training

15

Leeroo-AI/leeroopedia-mcp

Skill Claude CodeCodex

You have access to the Leeroopedia MCP tools. Use them throughout this pipeline to make informed decisions. Specifically.

14 6mo ago A 0 tokens original MIT

Leeroo-AI/leeroopedia-mcp

Skill Claude CodeCodex

This document describes the Leeroopedia MCP tools available during the with-KB benchmark run. It is a standalone reference and is not fed to the agents automatically.

14 6mo ago A 0 tokens original MIT

self_evolve_rag

17

Leeroo-AI/leeroopedia-mcp

Skill Claude CodeCodex

This document describes how to use the Leeroopedia MCP tools for the Self-Evolving RAG task. It is kept as a reference and is NOT included in the agent prompt.

14 6mo ago A 0 tokens original MIT