Patterns for OrbStack Linux VMs and Docker on macOS. Covers orbctl/orb commands, machine lifecycle, cloud-init, networking, file sharing, and SSH access. Must use when working with OrbStack, orbctl commands, or Linux VMs on macOS.
93
89%
Does it follow best practices?
Impact
99%
2.10xAverage 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 skill description that clearly identifies a specific tool (OrbStack), lists concrete capabilities, includes natural trigger terms, and provides explicit 'when to use' guidance. The description is concise yet comprehensive, covering the key domains without unnecessary verbosity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and domains: orbctl/orb commands, machine lifecycle, cloud-init, networking, file sharing, and SSH access. These are concrete, identifiable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (patterns for OrbStack Linux VMs and Docker, covering orbctl commands, machine lifecycle, cloud-init, networking, file sharing, SSH) and 'when' ('Must use when working with OrbStack, orbctl commands, or Linux VMs on macOS'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'OrbStack', 'orbctl', 'orb commands', 'Linux VMs', 'macOS', 'Docker', 'cloud-init', 'SSH access'. Good coverage of terms a user working with OrbStack would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — OrbStack is a specific tool for macOS, and the description clearly scopes to orbctl commands, Linux VMs on macOS, and OrbStack-specific features. Unlikely to conflict with generic Docker or VM skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
79%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 reference skill that excels in conciseness and actionability, providing comprehensive, copy-paste ready OrbStack commands and configurations. Its main weaknesses are the lack of explicit validation/feedback loops in multi-step workflows and the monolithic structure that could benefit from splitting detailed subsections into separate files for better progressive disclosure.
Suggestions
Add validation checkpoints to multi-step workflows, e.g., after cloud-init creation: 'Verify: orb -m myvm cloud-init status --long → if not done, check logs → retry if needed'
Split detailed sections (Docker Integration, Kubernetes, Cloud-Init) into separate reference files and link from the main SKILL.md overview to reduce document size and improve progressive disclosure
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. It avoids explaining what OrbStack is beyond a single introductory sentence, uses tables for reference data, and presents commands without unnecessary commentary. Every section delivers information density without padding. | 3 / 3 |
Actionability | Nearly every section contains copy-paste ready commands and concrete examples. Cloud-init includes a complete YAML example, SSH shows exact connection strings, Docker integration covers specific use cases with executable commands, and troubleshooting provides specific fix commands. | 3 / 3 |
Workflow Clarity | While individual commands are clear, multi-step workflows lack explicit validation checkpoints. For example, cloud-init creation doesn't sequence 'create → verify status → check logs if failed.' The troubleshooting section helps but is separate from the workflows. Machine lifecycle steps are listed but without feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and tables, but it's a monolithic document (~250 lines) that could benefit from splitting detailed sections (Docker integration, Kubernetes, cloud-init) into separate reference files. No external file references are used despite the breadth of topics covered. | 2 / 3 |
Total | 10 / 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.
f772de4
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.