infrastructure-maintainer
Configures and maintains cloud infrastructure, monitoring systems, and automated operations. Sets up Prometheus/Grafana alerting, writes Terraform IaC for AWS/GCP/Azure resources, manages auto-scaling groups, load balancers, VPCs, and databases, and implements encrypted backup pipelines with S3 offload. Troubleshoots deployment failures, optimizes resource right-sizing, enforces security hardening (SOC2/ISO27001), and produces capacity planning and cost analysis reports. Use when the user asks about server setup, infrastructure provisioning, monitoring and alerting configuration, Terraform or CloudFormation, CI/CD pipeline issues, Kubernetes or container orchestration, cloud cost optimization, backup and disaster recovery, or database performance and scaling.
98
100%
Does it follow best practices?
Impact
98%
1.42xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that thoroughly covers specific capabilities, includes a comprehensive set of natural trigger terms, and explicitly states both what the skill does and when to use it. The description is well-structured with a clear separation between capability listing and trigger guidance. It uses proper third-person voice throughout and avoids vague language or buzzwords.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists numerous specific concrete actions: sets up Prometheus/Grafana alerting, writes Terraform IaC, manages auto-scaling groups/load balancers/VPCs/databases, implements encrypted backup pipelines with S3 offload, troubleshoots deployment failures, optimizes resource right-sizing, enforces security hardening, and produces capacity planning reports. | 3 / 3 |
Completeness | Clearly answers both 'what does this do' (configures cloud infrastructure, monitoring, Terraform IaC, backup pipelines, security hardening, etc.) AND 'when should Claude use it' with an explicit 'Use when...' clause listing nine distinct trigger scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: Terraform, CloudFormation, Kubernetes, CI/CD pipeline, cloud cost optimization, backup and disaster recovery, database performance, server setup, infrastructure provisioning, monitoring and alerting, Prometheus, Grafana, AWS/GCP/Azure, SOC2/ISO27001, container orchestration. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear DevOps/infrastructure niche with highly specific triggers like Terraform, Prometheus/Grafana, auto-scaling groups, VPCs, SOC2/ISO27001, and S3 backup pipelines, making it very unlikely to conflict with non-infrastructure skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality infrastructure skill that excels across all dimensions. It provides a clear, executable workflow with proper validation checkpoints and rollback procedures, maintains excellent token efficiency by assuming Claude's infrastructure knowledge, and uses progressive disclosure effectively by offloading detailed configurations to reference files while keeping the main skill focused on process and defaults.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It avoids explaining what Terraform, Prometheus, or AWS services are, assumes Claude's competence with these tools, and every section delivers actionable information without padding. | 3 / 3 |
Actionability | The workflow provides fully executable bash commands for each step — terraform plan/apply, health checks via curl, AWS CLI commands, and jq filters with expected outputs. The reference file descriptions are specific enough to be actionable (exact cipher algorithms, retention periods, metric thresholds). | 3 / 3 |
Workflow Clarity | The 5-step infrastructure change procedure is clearly sequenced with explicit validation checkpoints (health_check.sh after staging, target health verification, Prometheus up-check, error rate baseline comparison), a staged rollout pattern (staging before production), and a dedicated rollback procedure with concrete commands. | 3 / 3 |
Progressive Disclosure | The skill cleanly separates concerns: the main file provides the workflow and default requirements while pointing to four well-described reference files (prometheus-config.yml, terraform-aws.tf, backup.sh, infra-report.md) with clear summaries of what each contains. References are one level deep and clearly signaled. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- OpenRoster-ai/awesome-agents
- Commit
010799b
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.