AgentHubAgentHub

ml-engineering Skill Install & Guide

SkillSkillsMP

skillsmp.stas00-ml-engineering-skill-md

Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference performance and memory; debugging multi-node/ multi-GPU hangs; and writing/running tests. Use when the user is training or fine-tuning large models, hits low TFLOPS/MFU, OOM, slow dataloading, a loss spike/divergence, a NCCL/InfiniBand or multi-node hang, node/GPU failures, checkpoint or preemption problems, storage/network bottlenecks, or needs to pick GPUs/cloud/file-systems or size inference latency/throughput. Distilled from "Machine Learning Engineering", the latest version of which can be found at https://github.com/stas00/ml-engineering The latest SKILL.md version can be found at https://github.com/st

View on SkillsMP ↗

Copy the install config on this page first, then verify docs and permissions upstream.

Popularity

Repo stars19.1k

Overview

Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference performance and memory; debugging multi-node/ multi-GPU hangs; and writing/running tests. Use when the user is training or fine-tuning large models, hits low TFLOPS/MFU, OOM, slow dataloading, a loss spike/divergence, a NCCL/InfiniBand or multi-node hang, node/GPU failures, checkpoint or preemption problems, storage/network bottlenecks, or needs to pick GPUs/cloud/file-systems or size inference latency/throughput. Distilled from "Machine Learning Engineering", the latest version of which can be found at https://github.com/stas00/ml-engineering The latest SKILL.md version can be found at https://github.com/st ml-engineering is a Agent Skill listed from SkillsMP. This page includes an overview, setup tutorial, install commands, and use cases for Trae, Tongyi Lingma, Cursor, Claude Code, and VS Code.

AgentHub Verified AvailabilityTested & Ready

Automated pipeline validated install commands, protocol & client compatibility

Verified At2026-10-01
Install Snippets TestedCLI & JSON config syntax verified
Protocol Handshake ReadyComplies with JSON-RPC 2.0 specifications
Origin Registry ActiveSourced from skillsmp
Verified ClientsClaude Code、Claude Desktop、Cursor 等
Security Tier: A 级 · 标准受控运行 (A)·Scanned for high-risk vulnerabilities. Recommended to run with project-scoped permissions.
No auto-generated install guide — see the source repository README.

Troubleshooting & Common ErrorsFAQ

Common connection errors and verified fixes for ml-engineering

Getting 'connection closed' or exit code 1 in Cursor / Claude Code for ml-engineering?

Usually caused by missing runtime paths or IDE environment inheritance. Fix steps: 1. Verify Node.js 18+ (npx) or Python 3.10+ (uvx) is installed; 2. Run 'which npx' or 'which uvx' in terminal, and replace 'command' with absolute path; 3. Reload or restart the client window after modifying config.

Fix Snippet
# Check binary path in terminal:
which npx
node -v
Getting 'spawn npx ENOENT' or 'command not found'?

The editor background process does not inherit your full terminal PATH. Solution: Globally install the package, or set the absolute binary path (e.g. C:\Program Files\nodejs\npx.cmd on Windows, or /usr/local/bin/npx on macOS).

Tool calls timing out or failing to download packages?

First-time package downloading might be slow or timeout due to network limits. Configure a reliable mirror or check outbound proxy settings.

Agent does not match or apply ml-engineering during conversations?

Verify SKILL.md is located at .cursor/skills/ml-engineering/SKILL.md (Cursor) or ~/.claude/skills/ml-engineering/SKILL.md (Claude Code). You can explicitly mention the skill name in your prompt to boost match confidence.

Still not connecting? Read the MCP troubleshooting guide →

Tool Mock Playground

Sandbox

ml-engineering Rule Injection & Agent Behavior Simulation · Preview tool schema & outputs without local runtime

Sandbox Ready
fn: agent_skill_runtimeInject system prompt guidelines & workflow constraints from ml-engineering
Request ArgumentsJSON Schema
{
  "skill": "ml-engineering",
  "rulePath": ".cursor/skills/ml-engineering/SKILL.md",
  "userGoal": "请使用 ml-engineering 的方法与标准帮我完成当前任务",
  "client": "Cursor / Claude Code"
}
💡Parameters generated dynamically by Agent runtime
Agent Tool Output

Click 'Run Mock' above

to preview the raw response returned to the LLM

Env: AgentHub Virtual SandboxJSON-RPC 2.0

Decision Guide: Why & When to Use

Assess suitability before installing to save trial-and-error time

Best Suited For
  • When your AI Agent needs tool calling capabilities in this domain
  • Automating repetitive workflows in your IDE or terminal
  • Pairing with modern clients supporting MCP/Skill standards
When NOT to Use
  • When missing required API secrets or local runtime prerequisites
  • Pure conversational requests that don't need external system access
Recommended Workflow Pairing:

ml-engineering + Scenario Prompt → Complete Agent Automation

Skill hands-on: install to visible results

Follow the full lab (expected UI/output + contrast checks). After installing this item, verify with the tutorial prompts.

Open tutorial →

An Agent Skill is a folder with SKILL.md instructions. After install, the AI loads it automatically when your task matches its description.

Related resources

腾讯云 CloudBase · Tencent CloudBase

v1.92.120

SkillClawHub9k

io.clawhub.binggg/cloudbase

Use this skill when you develop, design, build, deploy, debug, migrate, or troubleshoot CloudBase (腾讯云开发, 云开发, TCB, 微信云开发) projects — Web, 微信小程序, 小程序, uni-app, mobile (iOS, Android, Flutter, React Native). Covers UI (页面, 界面, 表单, dashboard, prototype, 原型); auth (登录, 注册, OAuth, publishable key); databases (NoSQL 文档数据库, MySQL 关系型数据库, PostgreSQL/CloudBase PG, app.rdb(), queryPgDatabase/managePgDatabase, CRUD, security rules); 云函数/cloud functions (serverless, scf_bootstrap); CloudRun (云托管, Dockerfile); 云存储; built-in AI (内置大模型, AI 对话, streaming, 流式输出, 图片生成, generateText, streamText, createModel, generateImage, TokenHub, Hunyuan, DeepSeek, GLM, Kimi, Token Credits 资源包, 小程序成长计划); third-party/custom model onboarding (第三方大模型接入, 大模型调用, LLM API); AI agent (智能体, AG-UI, LangGraph); ops troubleshooting (巡检, 诊断, 日志); spec workflow (需求文档, 技术方案, requirements, tasks.md). Do NOT use for non-CloudBase projects, pure frontend without CloudBase, or self-hosted backends without CloudBase.

source
View on ClawHub

ai-insurance-advisor

v2.0.125

SkillClawHub7.9k

io.clawhub.mnetfairy/ai-insurance-advisor

中国大陆保险顾问。本 skill 仅覆盖 6 项实际实现的能力：保险需求分析（needs_analyzer.py）、产品对比（premium_calculator.py + 本地 products.json）、保费计算（premium_calculator.py）、方案设计（plan_designer.py）、保险知识问答（insurance-knowledge.md）、合规要点提示（compliance.md）。不提供核保预审、理赔代办、朋友圈/营销文案生成、培训话术、代理人展业工具等能力——这些场景请转人工或调用专业服务。

source
View on ClawHub

Often paired with

Keep exploring AgentHub

Most people compare similar tools or check scenario guides before installing—start here.

Browse more like thisSearch similarPick by scenarioPrompt playbooksSkill hands-onReviews & comparisons

Listing badge: put AgentHub on your site

Copy either snippet into your project homepage, docs, or GitHub README. The badge is a hotlinked SVG — nothing to host — and it links back to this page so visitors can find the install steps.

PreviewListed on AgentHub: ml-engineering
HTML
<a href="https://myagenthub.cn/p/skillsmp.stas00-ml-engineering-skill-md" title="Listed on AgentHub: ml-engineering" target="_blank" rel="noopener">
  <img src="https://myagenthub.cn/badge/skillsmp.stas00-ml-engineering-skill-md?lang=en" alt="Listed on AgentHub: ml-engineering" height="20" style="border:0"/>
</a>
Markdown (GitHub README)
[![Listed on AgentHub: ml-engineering](https://myagenthub.cn/badge/skillsmp.stas00-ml-engineering-skill-md?lang=en)](https://myagenthub.cn/p/skillsmp.stas00-ml-engineering-skill-md)

Badges are generated on the fly from /badge/<package-id>, so name and listing changes propagate automatically. Keep the link target unchanged — it is what counts as the referral.

Unified Manifest

{
  "id": "skillsmp.stas00-ml-engineering-skill-md",
  "type": "skill",
  "version": "0.0.0",
  "displayName": "ml-engineering",
  "description": "Field-tested methodology and concrete recipes for training and operating large-scale LLM/VLM/multi-modal models end to end - choosing and benchmarking accelerators, storage and network; SLURM/Kubernetes orchestration; maximizing training throughput and fitting models in memory; diagnosing and surviving training instabilities, NaN/Inf, and hardware/job failures; checkpointing and fault tolerance; inference performance and memory; debugging multi-node/ multi-GPU hangs; and writing/running tests. Use when the user is training or fine-tuning large models, hits low TFLOPS/MFU, OOM, slow dataloading, a loss spike/divergence, a NCCL/InfiniBand or multi-node hang, node/GPU failures, checkpoint or preemption problems, storage/network bottlenecks, or needs to pick GPUs/cloud/file-systems or size inference latency/throughput. Distilled from \"Machine Learning Engineering\", the latest version of which can be found at https://github.com/stas00/ml-engineering\nThe latest SKILL.md version can be found at https://github.com/st",
  "author": {
    "name": "stas00"
  },
  "homepage": "https://skillsmp.com/creators/stas00/ml-engineering/skill",
  "distribution": {
    "packages": [
      {
        "registryType": "source",
        "identifier": "stas00-ml-engineering-skill-md",
        "version": "main",
        "runtimeHint": "npx skills add"
      }
    ],
    "remotes": []
  },
  "dependencies": [],
  "installTargets": [
    "claude-code",
    "claude-desktop",
    "cursor",
    "codex",
    "vscode"
  ],
  "keywords": [
    "repo_stars:19062"
  ],
  "provenance": {
    "origin": "skillsmp",
    "originalId": "stas00-ml-engineering-skill-md",
    "originalUrl": "https://skillsmp.com/creators/stas00/ml-engineering/skill",
    "isOfficial": false,
    "status": "active"
  }
}