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 (Packer, WinRM, PowerShell), concrete outputs (AMIs, Azure images, VMware templates), and explicit trigger conditions. It uses proper third-person voice and occupies a clear, distinct niche that minimizes conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and technologies: 'Build Windows images with Packer', 'WinRM communicator', 'PowerShell provisioners', and specifies output formats like AMIs, Azure images, and 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', 'Windows AMIs', 'Azure images', 'VMware templates'. These cover the main terms a user working in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining Windows + Packer + WinRM + PowerShell provisioners. This is unlikely to conflict with general infrastructure, Linux Packer builds, or other image-building skills due to the specific Windows/WinRM/PowerShell focus. | 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 real, executable HCL and PowerShell examples covering multiple cloud platforms. Its main weaknesses are the lack of an explicit build workflow with validation checkpoints (especially important given the cost/time warnings) and some verbosity from including full platform-specific examples inline rather than using progressive disclosure. The troubleshooting section is practical but partially redundant with inline comments.
Suggestions
Add an explicit numbered workflow sequence (e.g., 1. Configure WinRM → 2. Validate connectivity → 3. Provision → 4. Cleanup → 5. Verify image → 6. Confirm resource teardown) with validation checkpoints at each critical step.
Consider moving platform-specific full examples (AWS, Azure) into separate referenced files (e.g., AWS_EXAMPLE.md, AZURE_EXAMPLE.md) and keeping only the common WinRM pattern and one concise example inline.
Add a post-build verification step (e.g., launch test instance, verify WinRM is disabled, check installed software) to address the stated risk of failed builds leaving resources running.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient with concrete HCL and PowerShell examples, but includes some redundancy (e.g., the Azure example is largely duplicative of the AWS example for WinRM config, and the note about Windows builds being costly is useful but the common issues section restates things already shown in the examples). Could be tightened by consolidating platform-specific differences into a table. | 2 / 3 |
Actionability | All code blocks are fully executable HCL and PowerShell — copy-paste ready for AWS and Azure builders. The WinRM setup script, provisioner blocks, cleanup steps, and troubleshooting guidance are all concrete and specific with real commands. | 3 / 3 |
Workflow Clarity | The implicit workflow (configure WinRM → provision software → run updates → cleanup) is discernible from the section ordering, but there's no explicit numbered sequence or validation checkpoints. Given the warning about failed builds leaving resources running and the destructive/costly nature of Windows image builds, the lack of explicit verification steps (e.g., validate WinRM connectivity, verify cleanup, confirm resource teardown) caps this at 2. | 2 / 3 |
Progressive Disclosure | The content is well-sectioned with clear headers and external reference links at the bottom, but at ~150 lines it includes substantial inline content (full Azure and AWS examples) that could be split into separate files. No bundle files exist to offload platform-specific examples, and the references section is just external links rather than structured navigation to companion files. | 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
339a113
- 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.