AWS DevOps Agent Tools skill
Forty-five skills, custom agents and CloudFormation templates for AWS DevOps Agent: incident analysis and operations reviews
- 137 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- The skills read AWS account state through the IAM permissions of the agent role, and the CloudFormation template grants those permissions
- The materials are labeled sample code and are not meant for production without testing in a non-production environment
Install
- Works in
Manual install
npx skills add aws/tools-for-devops-agentA generic Skills CLI route for other agents. The author does not describe installation itself, and the skills are meant for AWS DevOps Agent.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skills read AWS account state through the IAM permissions of the agent role, and the CloudFormation template grants those permissions
- The materials are labeled sample code and are not meant for production without testing in a non-production environment
This is third-party code. Review the repository files before installing.
What it does
The aws repository gathers extensions for AWS DevOps Agent, a managed agent for incident investigation. The `skills/` folder holds 45 skills in the Agent Skills format: runbooks and decision trees the agent follows when working through problems. They include `aws-health-events` for AWS Health events, `aws-vpc-dns-investigation`, `eks-upgrade-readiness`, `rds-operation-review`, `service-quota-check`, cost skills for CloudTrail, Config and GuardDuty, and sets for Honeycomb and Sumo Logic. `custom-agents/` holds nine ready agents with system prompts: an AWS health report, an EKS operations review, a service quota monitor, a support cases report, a security and cost optimizer and others. `cloudformation/` has templates that grant the agent role the needed IAM permissions and forward CloudWatch alarms into investigations. Each skill documents its permissions in the Prerequisites section.
Who it is for. SRE and DevOps engineers who already use AWS DevOps Agent and want to plug in ready incident runbooks instead of writing their own.
Good fit when
- An incident starts with the question of whether AWS itself is at fault and symptoms have to be matched to AWS Health events
- Before an EKS upgrade you want a cluster readiness check and an operations report
- You want a regular report on service quotas or support cases from a custom agent on a schedule
- You want to take a ready skill as a template and write your own runbooks from it
Not a fit when
- There is no AWS account with a Business support plan or higher: the AWS Health skill requires such a plan
- Investigations run without AWS DevOps Agent: the sets are written for it and do not suit a general chat agent
- You need a ready production configuration without tests: the authors ask to try everything in a non-production environment first
Example request
Check AWS Health events for the last day in eu-west-1 and say whether they could explain the rise in errors in our APILimitations
The materials are labeled sample code: before production the authors ask you to test them in a non-production environment and review IAM permissions against organization policy. The sets are built for AWS DevOps Agent and uploaded to an Agent Space following the AWS documentation, and the README has no direct instructions for Claude Code. Some skills need extra IAM permissions beyond the managed `AIDevOpsAgentAccessPolicy`, and the AWS Health skill works through us-east-1, requires a Business or higher support plan and covers 90 days of data. The author does not describe Skills CLI installation itself, so `npx skills add aws/tools-for-devops-agent` is a generic command.
How to disable. Delete the skill or custom agent in the AWS DevOps Agent Agent Space console. Remove the permissions granted by the CloudFormation template by deleting the `devops-agent-skill-policies` stack.
FAQ
How do I install the AWS DevOps Agent Tools skills?
Upload the skill you need from the `skills/` folder to your Agent Space following the guide at aws.github.io/tools-for-devops-agent. Check the agent role permissions against the Prerequisites section in the skill README.
What is in the repository besides skills?
Custom agents with system prompts, MCP servers tailored to these skills and CloudFormation templates. The templates grant the agent role the needed permissions and forward CloudWatch alarms into investigations.
How do I grant IAM permissions for the skills?
Most permissions are already in the managed `AIDevOpsAgentAccessPolicy`. For the rest deploy `devops-agent-skill-policies.yaml` with `aws cloudformation deploy` and the `ExistingRoleName` parameter.
Will these skills work in Claude Code?
The skills follow the open Agent Skills standard but are written for AWS DevOps Agent and call its tools. In Claude Code you can use them as runbook templates; the authors claim no direct support.
Which custom agents does the repository include?
Nine: an AWS health report, an EKS operations review, an AWS operations review, a Confluence memory sync, a DevOps Agent cost dashboard, a Redshift support specialist, a service quotas monitor, a support cases report and a unified security and cost optimizer.
Discussion
No questions or reviews yet.
Related
SkillsA set of skills for agent work with AWS: common cloud service tasks packaged as ready instructions for a coding agent
AWS's official set of MCP servers, skills and plugins so an agent can build, deploy and operate on AWS
A large base of DevOps, security, infrastructure and compliance skills for AI agents
An AWS marketplace of plugins that give the agent skills to architect, deploy and operate AWS services
Microsoft Agent Skills
Agent Skills
Official Microsoft skills that ground coding agents in Azure SDKs and Foundry for Python, .NET, TypeScript, Java and Rust
Official Datadog skills: monitors, logs, APM, cloud integrations, RUM and LLM observability from inside the agent
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| AWS DevOps Agent Tools (this card) | yes | 137 | |
| AWS Agent Skills | no | 1,174 | a set of skills for AWS services in development, without incident investigation runbooks |
| AWS Skills for Claude Code | no | 373 | a plugin with AWS recipes for Claude Code |
README in short
The README lists the four parts of the repository, explains the difference between skills, custom agents and MCP servers, carries a warning about sample code and describes permissions. At the bottom it collects AWS documentation links and five articles about DevOps Agent.
README badge
Original SKILL.md
--- name: aws-health-events description: ALWAYS use this skill in the beginning of any incident investigation, root cause analysis, or operational troubleshooting. This skill retrieves and analyzes AWS Health events (service issues, scheduled changes, and account notifications) to identify AWS-side events that may explain or correlate with observed operational issues. Activate this skill when investigating an issue and you observe service degradation, elevated error rates, latency spikes, connection failures, throttling, capacity issues, deployment-related failures, alarms, or any operational event or issue. This skill searches AWS Health events by service, time window, region, and status to surface active or recent service disruptions, scheduled maintenance, and account-specific notifications that inform the current investigation. Also activate when a user requests a health event summary or report for their account over a specified time period. metadata: author: udid-aws version: "1.0.1" aws-devops-agent-skills.agent-types: "CHAT, INCIDENT_RCA" aws-devops-agent-skills.aws-services: "AWS Health" aws-devops-agent-skills.technical-domains: "Operations" --- # AWS Health Event Review Use this skill when investigating an incident and you need to check for AWS-side service events that may be causing or contributing to the observed issue. Also use this skill when a user requests a summary report of AWS Health events over a configurable time period. ## When to Use This Skill **Incident Investigation (automatic activation):** - An active incident may be caused by an AWS service disruption or degradation. - You observe service degradation, elevated error rates, latency spikes, connection failures, throttling, or capacity issues. - You need to determine whether an AWS-side event is the root cause or a contributing factor to the current incident. - You want to correlate observed symptoms with known AWS Health events. **Chat Reporting (on-demand activation):** - A user requests a health event summary or report for their account. - A user wants to review the health posture of their AWS environment over a specific time period.