windows-builder
Build Windows images with Packer using WinRM communicator and PowerShell provisioners. Use when creating Windows AMIs, Azure images, or VMware templates.
88
82%
Does it follow best practices?
Impact
100%
1.47xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
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 a strong, well-crafted skill description that concisely covers specific capabilities, includes natural trigger terms, and clearly delineates both what the skill does and when to use it. The technology-specific terms (Packer, WinRM, PowerShell, AMIs, Azure, VMware) make it highly distinctive and easy for Claude to match against user requests.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Build Windows images with Packer', 'WinRM communicator', 'PowerShell provisioners', and specifies output types like 'Windows AMIs, Azure images, or VMware templates'. | 3 / 3 |
Completeness | Clearly answers both what ('Build Windows images with Packer using WinRM communicator and PowerShell provisioners') and when ('Use when creating Windows AMIs, Azure images, or VMware templates') with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Windows images', 'Packer', 'WinRM', 'PowerShell', 'AMIs', 'Azure images', 'VMware templates'. These cover the main terms someone working in this domain would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining Windows + Packer + WinRM + PowerShell provisioners. Unlikely to conflict with general infrastructure, Linux Packer builds, or other image-building skills due to the specific technology stack mentioned. | 3 / 3 |
Total | 12 / 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 fully executable HCL and PowerShell examples covering multiple cloud providers. Its main weaknesses are the lack of explicit validation/verification steps for a process that's expensive and failure-prone, and the inline verbosity of including full examples for multiple platforms without a concise overview or progressive disclosure structure.
Suggestions
Add an explicit build verification workflow: e.g., 'After build completes: 1. Verify image exists with `packer inspect`, 2. Check cloud console for orphaned resources, 3. Launch test instance from new image'
Add a quick-start section at the top with a minimal complete example before diving into platform-specific details
Consider moving the Azure example to a separate AZURE.md file and keeping only the AWS example inline, with a cross-reference to the Azure guide
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with concrete HCL examples, but includes some redundancy (e.g., full Azure example when the AWS example already demonstrates the pattern, inline comments that state the obvious like '# Install Chocolatey'). The cost/time warning is useful but some sections could be tightened. | 2 / 3 |
Actionability | All code blocks are fully executable HCL and PowerShell — copy-paste ready with real resource types, specific AMI filters, concrete Chocolatey commands, and complete WinRM setup scripts. The troubleshooting section provides specific, actionable fixes. | 3 / 3 |
Workflow Clarity | The build sections show a logical sequence (WinRM setup → provisioners → cleanup), but there's no explicit validation workflow or feedback loop. The note about failed builds leaving resources running is mentioned but no verification step (e.g., 'check AWS console for running instances') is provided. For a process that can fail expensively, missing validation caps this at 2. | 2 / 3 |
Progressive Disclosure | References to external docs are provided at the bottom, and the content is organized into clear sections. However, the skill is quite long (~150 lines of content) with full Azure and AWS examples inline that could be split into separate files, and there's no quick-start summary before diving into full examples. | 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.
- Repository
- hashicorp/agent-skills
- Commit
b129bb5
- 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.