Cloud.ru Skills for AI Agents
Cloud.ru Skills для AI-агентов
Official Cloud.ru skills: account setup, Foundation Models, ML Inference, virtual machines, RAG and Evolution AI Agents
High risk
We rate an entry high when the tool writes to external systems, handles money, production databases or secrets, or runs arbitrary commands. The CLI installs it only with your consent.
Why this level
- Creates and removes real virtual machines and ML deployments billed by usage
- Manages AI agents and MCP servers on the Evolution platform with your account's rights
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/cloud-ru-skills-dlya-ai-agentovDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Assembled automatically, review before installing.
Run in a terminal in the project folder
npx skills add cloud-ru/evo-aifactory-skills --skill cloudru-account-setup cloudru-ai-agents cloudru-foundation-models cloudru-managed-rag cloudru-ml-inference cloudru-vm -a claude-code -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 73fae63
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/cloud-ru/evo-aifactory-skills.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /cloudru-account-setup/ /cloudru-ai-agents/ /cloudru-foundation-models/ /cloudru-managed-rag/ /cloudru-ml-inference/ /cloudru-vm/
git -C "$tmp" checkout 73fae638899ccac371a2b29be80e11b77b962845
mkdir -p .claude/skills
cp -R "$tmp/cloudru-account-setup" .claude/skills/cloudru-account-setup
cp -R "$tmp/cloudru-ai-agents" .claude/skills/cloudru-ai-agents
cp -R "$tmp/cloudru-foundation-models" .claude/skills/cloudru-foundation-models
cp -R "$tmp/cloudru-managed-rag" .claude/skills/cloudru-managed-rag
cp -R "$tmp/cloudru-ml-inference" .claude/skills/cloudru-ml-inference
cp -R "$tmp/cloudru-vm" .claude/skills/cloudru-vmCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add cloud-ru/evo-aifactory-skills --skill cloudru-account-setup cloudru-ai-agents cloudru-foundation-models cloudru-managed-rag cloudru-ml-inference cloudru-vm -a cursor -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 73fae63
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/cloud-ru/evo-aifactory-skills.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /cloudru-account-setup/ /cloudru-ai-agents/ /cloudru-foundation-models/ /cloudru-managed-rag/ /cloudru-ml-inference/ /cloudru-vm/
git -C "$tmp" checkout 73fae638899ccac371a2b29be80e11b77b962845
mkdir -p .agents/skills
cp -R "$tmp/cloudru-account-setup" .agents/skills/cloudru-account-setup
cp -R "$tmp/cloudru-ai-agents" .agents/skills/cloudru-ai-agents
cp -R "$tmp/cloudru-foundation-models" .agents/skills/cloudru-foundation-models
cp -R "$tmp/cloudru-managed-rag" .agents/skills/cloudru-managed-rag
cp -R "$tmp/cloudru-ml-inference" .agents/skills/cloudru-ml-inference
cp -R "$tmp/cloudru-vm" .agents/skills/cloudru-vmCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add cloud-ru/evo-aifactory-skills --skill cloudru-account-setup cloudru-ai-agents cloudru-foundation-models cloudru-managed-rag cloudru-ml-inference cloudru-vm -a github-copilot -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 73fae63
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/cloud-ru/evo-aifactory-skills.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /cloudru-account-setup/ /cloudru-ai-agents/ /cloudru-foundation-models/ /cloudru-managed-rag/ /cloudru-ml-inference/ /cloudru-vm/
git -C "$tmp" checkout 73fae638899ccac371a2b29be80e11b77b962845
mkdir -p .github/skills
cp -R "$tmp/cloudru-account-setup" .github/skills/cloudru-account-setup
cp -R "$tmp/cloudru-ai-agents" .github/skills/cloudru-ai-agents
cp -R "$tmp/cloudru-foundation-models" .github/skills/cloudru-foundation-models
cp -R "$tmp/cloudru-managed-rag" .github/skills/cloudru-managed-rag
cp -R "$tmp/cloudru-ml-inference" .github/skills/cloudru-ml-inference
cp -R "$tmp/cloudru-vm" .github/skills/cloudru-vmCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add cloud-ru/evo-aifactory-skills --skill cloudru-account-setup cloudru-ai-agents cloudru-foundation-models cloudru-managed-rag cloudru-ml-inference cloudru-vm -a codex -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 73fae63
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/cloud-ru/evo-aifactory-skills.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /cloudru-account-setup/ /cloudru-ai-agents/ /cloudru-foundation-models/ /cloudru-managed-rag/ /cloudru-ml-inference/ /cloudru-vm/
git -C "$tmp" checkout 73fae638899ccac371a2b29be80e11b77b962845
mkdir -p .agents/skills
cp -R "$tmp/cloudru-account-setup" .agents/skills/cloudru-account-setup
cp -R "$tmp/cloudru-ai-agents" .agents/skills/cloudru-ai-agents
cp -R "$tmp/cloudru-foundation-models" .agents/skills/cloudru-foundation-models
cp -R "$tmp/cloudru-managed-rag" .agents/skills/cloudru-managed-rag
cp -R "$tmp/cloudru-ml-inference" .agents/skills/cloudru-ml-inference
cp -R "$tmp/cloudru-vm" .agents/skills/cloudru-vmCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add cloud-ru/evo-aifactory-skills --skill cloudru-account-setup cloudru-ai-agents cloudru-foundation-models cloudru-managed-rag cloudru-ml-inference cloudru-vm -a gemini-cli -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 73fae63
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/cloud-ru/evo-aifactory-skills.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /cloudru-account-setup/ /cloudru-ai-agents/ /cloudru-foundation-models/ /cloudru-managed-rag/ /cloudru-ml-inference/ /cloudru-vm/
git -C "$tmp" checkout 73fae638899ccac371a2b29be80e11b77b962845
mkdir -p .agents/skills
cp -R "$tmp/cloudru-account-setup" .agents/skills/cloudru-account-setup
cp -R "$tmp/cloudru-ai-agents" .agents/skills/cloudru-ai-agents
cp -R "$tmp/cloudru-foundation-models" .agents/skills/cloudru-foundation-models
cp -R "$tmp/cloudru-managed-rag" .agents/skills/cloudru-managed-rag
cp -R "$tmp/cloudru-ml-inference" .agents/skills/cloudru-ml-inference
cp -R "$tmp/cloudru-vm" .agents/skills/cloudru-vmCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/cloud-ru/evo-aifactory-skills.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /cloudru-account-setup/ /cloudru-ai-agents/ /cloudru-foundation-models/ /cloudru-managed-rag/ /cloudru-ml-inference/ /cloudru-vm/
git -C "$tmp" checkout 73fae638899ccac371a2b29be80e11b77b962845
mkdir -p .devin/skills
cp -R "$tmp/cloudru-account-setup" .devin/skills/cloudru-account-setup
cp -R "$tmp/cloudru-ai-agents" .devin/skills/cloudru-ai-agents
cp -R "$tmp/cloudru-foundation-models" .devin/skills/cloudru-foundation-models
cp -R "$tmp/cloudru-managed-rag" .devin/skills/cloudru-managed-rag
cp -R "$tmp/cloudru-ml-inference" .devin/skills/cloudru-ml-inference
cp -R "$tmp/cloudru-vm" .devin/skills/cloudru-vmCommands for macOS and Linux, on Windows run them in Git Bash.
Formerly Windsurf.
Run in a terminal in the project folder
npx skills add cloud-ru/evo-aifactory-skills --skill cloudru-account-setup cloudru-ai-agents cloudru-foundation-models cloudru-managed-rag cloudru-ml-inference cloudru-vm -a cline -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 73fae63
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/cloud-ru/evo-aifactory-skills.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /cloudru-account-setup/ /cloudru-ai-agents/ /cloudru-foundation-models/ /cloudru-managed-rag/ /cloudru-ml-inference/ /cloudru-vm/
git -C "$tmp" checkout 73fae638899ccac371a2b29be80e11b77b962845
mkdir -p .cline/skills
cp -R "$tmp/cloudru-account-setup" .cline/skills/cloudru-account-setup
cp -R "$tmp/cloudru-ai-agents" .cline/skills/cloudru-ai-agents
cp -R "$tmp/cloudru-foundation-models" .cline/skills/cloudru-foundation-models
cp -R "$tmp/cloudru-managed-rag" .cline/skills/cloudru-managed-rag
cp -R "$tmp/cloudru-ml-inference" .cline/skills/cloudru-ml-inference
cp -R "$tmp/cloudru-vm" .cline/skills/cloudru-vmCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add cloud-ru/evo-aifactory-skills --skill cloudru-account-setup cloudru-ai-agents cloudru-foundation-models cloudru-managed-rag cloudru-ml-inference cloudru-vm -a roo -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 73fae63
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/cloud-ru/evo-aifactory-skills.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /cloudru-account-setup/ /cloudru-ai-agents/ /cloudru-foundation-models/ /cloudru-managed-rag/ /cloudru-ml-inference/ /cloudru-vm/
git -C "$tmp" checkout 73fae638899ccac371a2b29be80e11b77b962845
mkdir -p .roo/skills
cp -R "$tmp/cloudru-account-setup" .roo/skills/cloudru-account-setup
cp -R "$tmp/cloudru-ai-agents" .roo/skills/cloudru-ai-agents
cp -R "$tmp/cloudru-foundation-models" .roo/skills/cloudru-foundation-models
cp -R "$tmp/cloudru-managed-rag" .roo/skills/cloudru-managed-rag
cp -R "$tmp/cloudru-ml-inference" .roo/skills/cloudru-ml-inference
cp -R "$tmp/cloudru-vm" .roo/skills/cloudru-vmCommands for macOS and Linux, on Windows run them in Git Bash.
A fork of Roo Code, same .roo folders.
Run in a terminal in the project folder
npx skills add cloud-ru/evo-aifactory-skills --skill cloudru-account-setup cloudru-ai-agents cloudru-foundation-models cloudru-managed-rag cloudru-ml-inference cloudru-vm -a opencode -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit 73fae63
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/cloud-ru/evo-aifactory-skills.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /cloudru-account-setup/ /cloudru-ai-agents/ /cloudru-foundation-models/ /cloudru-managed-rag/ /cloudru-ml-inference/ /cloudru-vm/
git -C "$tmp" checkout 73fae638899ccac371a2b29be80e11b77b962845
mkdir -p .agents/skills
cp -R "$tmp/cloudru-account-setup" .agents/skills/cloudru-account-setup
cp -R "$tmp/cloudru-ai-agents" .agents/skills/cloudru-ai-agents
cp -R "$tmp/cloudru-foundation-models" .agents/skills/cloudru-foundation-models
cp -R "$tmp/cloudru-managed-rag" .agents/skills/cloudru-managed-rag
cp -R "$tmp/cloudru-ml-inference" .agents/skills/cloudru-ml-inference
cp -R "$tmp/cloudru-vm" .agents/skills/cloudru-vmCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/cloud-ru/evo-aifactory-skills.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /cloudru-account-setup/ /cloudru-ai-agents/ /cloudru-foundation-models/ /cloudru-managed-rag/ /cloudru-ml-inference/ /cloudru-vm/
git -C "$tmp" checkout 73fae638899ccac371a2b29be80e11b77b962845
mkdir -p .agents/skills
cp -R "$tmp/cloudru-account-setup" .agents/skills/cloudru-account-setup
cp -R "$tmp/cloudru-ai-agents" .agents/skills/cloudru-ai-agents
cp -R "$tmp/cloudru-foundation-models" .agents/skills/cloudru-foundation-models
cp -R "$tmp/cloudru-managed-rag" .agents/skills/cloudru-managed-rag
cp -R "$tmp/cloudru-ml-inference" .agents/skills/cloudru-ml-inference
cp -R "$tmp/cloudru-vm" .agents/skills/cloudru-vmCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/cloud-ru/evo-aifactory-skills.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /cloudru-account-setup/ /cloudru-ai-agents/ /cloudru-foundation-models/ /cloudru-managed-rag/ /cloudru-ml-inference/ /cloudru-vm/
git -C "$tmp" checkout 73fae638899ccac371a2b29be80e11b77b962845
mkdir -p .agents/skills
cp -R "$tmp/cloudru-account-setup" .agents/skills/cloudru-account-setup
cp -R "$tmp/cloudru-ai-agents" .agents/skills/cloudru-ai-agents
cp -R "$tmp/cloudru-foundation-models" .agents/skills/cloudru-foundation-models
cp -R "$tmp/cloudru-managed-rag" .agents/skills/cloudru-managed-rag
cp -R "$tmp/cloudru-ml-inference" .agents/skills/cloudru-ml-inference
cp -R "$tmp/cloudru-vm" .agents/skills/cloudru-vmCommands for macOS and Linux, on Windows run them in Git Bash.
Clone cloud-ru/evo-aifactory-skills, set the CP_CONSOLE_KEY_ID, CP_CONSOLE_SECRET and PROJECT_ID environment variables, point your agent at the relevant SKILL.md, such as cloudru-vm/SKILL.md, and it will get all the instructions it needs.
Other ways from the author
git clone https://github.com/cloud-ru/evo-aifactory-skills.git
pip install httpxBase install for all skills; boto3 is needed for managed-rag and playwright for account-setup.
This is third-party code. Review the repository files before installing.
What it does
The project gives six skills for managing Cloud.ru from a development agent. cloudru-account-setup creates a service account and keys via browser login. cloudru-foundation-models calls ready LLMs through the Foundation Models API. cloudru-ml-inference deploys and manages your own GPU ML models. cloudru-vm creates and configures virtual machines. cloudru-managed-rag builds a RAG pipeline: knowledge bases, semantic search and LLM-backed Q&A. cloudru-ai-agents manages the Evolution AI Agents platform: agents, systems, MCP servers, triggers, workflows and the marketplace. Each skill is a folder with a SKILL.md and Python scripts, and the skills are agent-agnostic, working with Claude Code, Cursor, Windsurf, Cline, Aider and more.
Who it is for. For developers and ML engineers on Cloud.ru who want to deploy models, VMs and RAG pipelines right from a chat with an agent.
Good fit when
- You need to quickly call a Cloud.ru Foundation Models model from an agent
- You need to deploy a virtual machine or a GPU ML model without manual console work
- You need a RAG pipeline over documents with semantic search and LLM answers
Not a fit when
- You have no Cloud.ru account and creating one is out of scope
- You do not want to install the httpx, boto3 or playwright Python dependencies each skill needs
- You need a different cloud provider, not Cloud.ru
Example request
Deploy a Cloud.ru virtual machine with Ubuntu 22.04 and show me its floating IPLimitations
It needs real Cloud.ru credentials: CP_CONSOLE_KEY_ID, CP_CONSOLE_SECRET, PROJECT_ID and a separate Foundation Models API key. Different skills need different Python dependencies: httpx for all of them, boto3 for managed-rag, playwright for account-setup. The project is under active development by the Cloud.ru team itself.
How to disable. Delete the relevant skill folders (for example cloudru-vm or cloudru-managed-rag) from your agent install.
Security check
- Creates and removes real virtual machines and ML deployments billed by usage
- Manages AI agents and MCP servers on the Evolution platform with your account's rights
README in short
The Russian README from the Cloud.ru team lists six skills in a table with short descriptions, and gives a step-by-step quick start from credential setup to calling models, deploying ML inference, creating VMs and running RAG and Evolution AI Agents. A separate WORKFLOW.md file covers cross-skill scenarios and a decision matrix for Foundation Models API versus ML Inference.
FAQ
How do I get credentials?
Through the cloudru-account-setup skill with browser login (needs playwright), or by setting environment variables manually.
Can I use this outside Claude Code?
Yes, the skills are agent-agnostic and work with any agent that reads markdown and runs Python scripts.
Related
An MCP server built into the Netdata agent: metrics, logs, alerts and live process, service and container data for an AI assistant
GitHub's official MCP server: code, issues, pull requests, Actions and security alerts straight from the agent
Agent Skills for Google products
Agent Skills for Google products and technologies
Official Google skill collection for working with Google Cloud, BigQuery, GKE, ads and analytics from an agent
AWS's official MCP server suite: docs, IaC, containers, serverless, databases, cost and monitoring