aws-ami-builder
Build Amazon Machine Images (AMIs) with Packer using the amazon-ebs builder. Use when creating custom AMIs for EC2 instances.
Install with Tessl CLI
npx tessl i github:hashicorp/agent-skills --skill aws-ami-builder90
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
89%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 a solid skill description with excellent trigger terms and clear when/what guidance. The main weakness is limited specificity in capabilities - it only mentions building AMIs without detailing other actions like template validation, provisioner configuration, or multi-region builds. The description effectively carves out a distinct niche.
Suggestions
Expand the capabilities list to include additional concrete actions like 'validate templates, configure provisioners, manage build variables' to improve specificity
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AMIs, Packer, amazon-ebs builder) and one action (build/create), but doesn't list multiple concrete actions like configuring provisioners, validating templates, or managing build artifacts. | 2 / 3 |
Completeness | Clearly answers both what ('Build Amazon Machine Images with Packer using the amazon-ebs builder') and when ('Use when creating custom AMIs for EC2 instances') with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'AMI', 'AMIs', 'Packer', 'amazon-ebs', 'EC2 instances', 'custom AMIs'. These are terms users would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific technology stack (Packer + amazon-ebs + AMI). Unlikely to conflict with other skills due to the narrow, well-defined niche of AWS image building with Packer specifically. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
87%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 skill that provides concrete, executable Packer templates for building AMIs. It's concise, assumes appropriate knowledge, and includes practical details like owner IDs and common filters. The main gap is the lack of explicit validation/verification steps in the workflow—users should verify AMI creation succeeded before relying on it.
Suggestions
Add a verification step after build commands, e.g., `aws ec2 describe-images --image-ids <ami-id>` to confirm AMI was created successfully
Include guidance on checking Packer build output for the AMI ID and how to handle build failures (cleanup of partial resources)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, providing only essential information. No unnecessary explanations of what AMIs or Packer are—it assumes Claude knows these concepts and jumps straight to actionable templates. | 3 / 3 |
Actionability | Provides complete, copy-paste ready HCL templates with all required blocks. Build commands are explicit and executable. Common AMI filters include specific owner IDs and filter patterns. | 3 / 3 |
Workflow Clarity | Build commands section shows the sequence (init → validate → build), but lacks explicit validation checkpoints or feedback loops. For AMI building which can fail in various ways, there's no guidance on verifying the build succeeded or troubleshooting failed builds beyond common issues. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from basic to advanced (multi-region). External references are clearly signaled at top and bottom. Content is appropriately sized for a single file without needing additional documents. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.