agentleFS
frontier-ai-nextfrontier-ai-next/mgarlbot/skills/aws_ops/SKILL.md

aws_ops

Skill17 starsChanged 4 months agoMITView on GitHub

AWS EC2 — инстансы, VPC, subnets через aws_api tool

The file

Files
SKILL.md

AWS EC2 (aws_api tool)

Креды в настройках бота: AWS_PROFILE или AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY, плюс AWS_REGION. Не передавай ключи в аргументах и не выводи их в ответ.

Когда использовать

  • «покажи EC2 / инстансы в AWS»
  • «подними t3.micro в eu-central-1»
  • «останови / запусти инстанс i-…»
  • «какие VPC / subnets / security groups»

Безопасность (обязательно)

  • Не вызывай terminate_instance без явного запроса пользователя на удаление.
  • Для terminate_instance нужен params.confirm: true.
  • По умолчанию предпочитай t3.micro / t3.small; не запускай дорогие типы без запроса.
  • Перед run_instance: list_vpcs → list_subnets → list_security_groups → list_amis (Ubuntu/Amazon Linux).
  • После run_instance — краткий отчёт: InstanceId, IP, тип, регион.

Типовые вызовы

Инстансы:

{"action": "list_instances", "params": {"region": "eu-central-1"}}
{"action": "get_instance", "params": {"instance_id": "i-0123456789abcdef0", "region": "eu-central-1"}}

Запуск (минимальный):

{
  "action": "run_instance",
  "params": {
    "region": "eu-central-1",
    "ami_id": "ami-xxxxxxxx",
    "instance_type": "t3.micro",
    "name": "mgarlbot-test",
    "key_name": "my-key",
    "subnet_id": "subnet-xxx",
    "security_group_ids": ["sg-xxx"]
  }
}

Stop / start:

{"action": "stop_instance", "params": {"instance_id": "i-xxx", "region": "eu-central-1"}}
{"action": "start_instance", "params": {"instance_id": "i-xxx", "region": "eu-central-1"}}

Terminate (только по явной просьбе):

{"action": "terminate_instance", "params": {"instance_id": "i-xxx", "region": "eu-central-1", "confirm": true}}

Сеть и образы:

{"action": "list_vpcs", "params": {"region": "eu-central-1"}}
{"action": "list_subnets", "params": {"region": "eu-central-1", "vpc_id": "vpc-xxx"}}
{"action": "list_security_groups", "params": {"region": "eu-central-1"}}
{"action": "list_amis", "params": {"region": "eu-central-1", "owners": ["amazon"], "name_filter": "ubuntu-noble", "max_results": 10}}

Ошибки

  • «AWS не настроен» → ⚙ Настройки → AWS (профиль или ключи + регион).
  • UnauthorizedOperation → у IAM не хватило прав (EC2 read/run).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.