Build Amazon Machine Images (AMIs) with Packer using the amazon-ebs builder. Use when creating custom AMIs for EC2 instances.
80
70%
Does it follow best practices?
Impact
100%
1.23xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./packer/builders/skills/aws-ami-builder/SKILL.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is well-structured with a clear 'Use when' clause and targets a distinct niche (Packer AMI building). However, it could benefit from listing more specific actions beyond just 'Build' and including additional trigger terms that users might naturally use when requesting this type of work.
Suggestions
Add more specific actions such as 'validate Packer templates, configure provisioners, define build variables, troubleshoot build failures'.
Expand trigger terms to include natural variations like 'machine image', 'golden image', 'HCL template', 'packer build', '.pkr.hcl'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AMIs, Packer, amazon-ebs builder) and one action ('Build'), but doesn't list multiple concrete actions like validating templates, configuring provisioners, managing build variables, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (Build AMIs 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 good keywords like 'AMI', 'Packer', 'amazon-ebs', and 'EC2', but misses common variations users might say such as 'machine image', 'HCL template', 'packer build', 'golden image', or 'bake image'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche combining Packer + AMI + amazon-ebs builder, making it highly unlikely to conflict with other skills. The technology stack is distinct and well-defined. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with complete, executable Packer HCL templates and useful AMI filter examples. Its main weaknesses are some redundancy (duplicated AMI filter blocks), missing explicit validation feedback loops before costly build operations, and a slightly monolithic structure that could benefit from splitting reference material into separate files.
Suggestions
Remove the duplicated Ubuntu 22.04 source_ami_filter block—show it once in the basic template and reference it from the 'Common Source AMI Filters' section.
Add an explicit validation workflow with a feedback loop: 'Run packer validate → if errors, fix template → re-validate → only when valid, run packer build' to prevent costly failed builds.
Trim or remove the Authentication section's credential resolution order explanation, as Claude already knows standard AWS credential chain behavior.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some redundancy—the Ubuntu 22.04 source_ami_filter is shown in full twice (once in the basic template and once in the 'Common Source AMI Filters' section). The authentication section explains standard AWS credential resolution which Claude already knows. The cost note is marginally useful but adds tokens. | 2 / 3 |
Actionability | The skill provides fully executable HCL templates that are copy-paste ready, concrete build commands, specific AMI filter configurations with owner IDs, and practical variable usage. All code examples are complete and runnable. | 3 / 3 |
Workflow Clarity | Build commands include init, validate, and build steps in sequence, which is good. However, there's no explicit validation feedback loop—e.g., 'if validate fails, fix and re-validate before building.' For an operation that incurs AWS costs and takes 10-30 minutes, a clearer workflow with checkpoints (validate → fix → only then build) would be expected. | 2 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections, but it's somewhat monolithic at ~130 lines. The common source AMI filters and multi-region example could be split into separate reference files. External links are provided but there are no bundle files to offload detailed content. | 2 / 3 |
Total | 9 / 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.
339a113
Table of Contents
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.