Skill registry
Agent infrastructurePublic skills

Cloud Infrastructure

Cloud operations for AI agents — deploy services, scale replicas, manage DNS, rotate secrets, promote between environments, monitor costs, and rollback on failure.

What this skill teaches

A reusable playbook for a specific kind of work.

An MCP server tells an agent which actions are available. A skill adds the judgment around those actions: how to recognize the job, which sequence to follow, what to avoid, and how to decide that the result is complete.

Orchestrate cloud infrastructure — deploy services, scale replicas, manage DNS, handle secrets, promote between environments, monitor costs, and rollback on failure. Use when deploying services, scaling applications, managing DNS records, rotating secrets, promoting to production, checking costs, or rolling back…

Architecture

How Cloud Infrastructure guides an ADK-Rust agent.

The skill stays readable and portable because it contains instructions rather than service credentials or business data. ADK-Rust supplies it to the agent, the agent chooses from its reviewed tool boundary, and the connected MCP server performs the authenticated operation.

01

User request

The agent receives a goal expressed in ordinary language.

02

Cloud Infrastructure skill

Matches intent, supplies the decision guide, and narrows the tool boundary.

03

ADK-Rust agent

Plans the workflow and streams each meaningful step through the runtime.

04

mcp-infrastructure

Executes authenticated operations against the system that owns the capability.

05

Verified result

The skill's completion rules shape the evidence returned to the user.

Portable instructions: SKILL.md · Capability boundary: mcp-infrastructure · Allowed tools: 24

Decision guide

How the agent turns a request into the right action.

These routes come directly from the skill instructions. They help the model recognize intent and select a focused tool or workflow instead of improvising across the entire capability surface.

01

"deploy", "ship", "release", "new version"?

WORKFLOW 1: Deploy

02

"scale", "replicas", "capacity"?

WORKFLOW 2: Scale

03

"rollback", "revert", "undo"?

WORKFLOW 3: Rollback

04

"DNS", "domain", "record"?

WORKFLOW 4: DNS Management

05

"secret", "env var", "API key", "rotate"?

WORKFLOW 5: Secrets

06

"promote", "staging to prod"?

WORKFLOW 6: Promotion

07

"costs", "spending", "bill"?

WORKFLOW 7: Cost Analysis

08

"health", "status", "services"?

list_services / get_cluster_health

Proven workflows

Repeatable sequences for useful outcomes.

A workflow joins several tool calls into a task the user actually recognizes. The skill explains the sequence and the intended result while ADK-Rust streams the agent's progress through the shared runtime.

013-4 calls

Deploy

Deploy → verify logs → check resources

022-3 calls

Scale

Check resources → check costs → scale

032 calls

Rollback

Revert → verify healthy

042 calls

DNS

List → set/update record

052-3 calls

Secrets

Set/rotate → restart service

063 calls

Promotion

Verify staging → promote → verify prod

Tool boundary

The skill may use 24 documented tools.

This allowlist is declared by the skill. It keeps the agent focused on the actions needed for this job while mcp-infrastructure retains responsibility for authentication, validation, and the connected system.

list_services
get_service
get_logs
get_resources
get_deploy_history
deploy
scale
rollback
restart
list_dns
set_dns
delete_dns
list_secrets
set_secret
delete_secret
rotate_secret
list_environments
get_environment
promote
list_containers
get_cluster_health
get_costs
list_domains
add_domain

Working rules

What the agent should do.

  • Follow the decision guide, use the declared tool boundary, and verify the result before responding.

Operating boundaries

What the agent should avoid.

  • Review the complete SKILL.md before enabling this skill for production work.

Install and connect

Add the skill beside the capability it expects.

Install the repository where your ADK-Rust skill loader can discover it, connect mcp-infrastructure, and confirm the declared tools are available before asking the agent to use the workflow.

Install the skill
git clone https://github.com/zavora-ai/skill-cloud-infrastructure.git \
  ~/.skills/skills/cloud-infrastructure
ADK-Rust loading shape
let skills = SkillLoader::from_dir("~/.skills/skills").await?;
let skill = skills.load("cloud-infrastructure").await?;

let agent = LlmAgentBuilder::new("agent")
    .instruction(skill.instructions())
    .tools(skill.allowed_tools(toolset)?)
    .build()?;

The repository's compatibility statement: Requires mcp-infrastructure server connected (supports any cloud platform via API).

Official documentation

Read the complete skill package.

The repository remains authoritative for its exact instructions, examples, helper scripts, assets, MCP requirements, license, and later updates.

Source record

Repository metadata for this skill entry.

View public repository ↗
License
Apache-2.0
Allowed tools
24
References
3
Revision
0f663c3ebdb8
Updated
May 31, 2026