capacity
Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.
92
92%
Does it follow best practices?
Impact
88%
1.35xAverage score across 3 eval scenarios
Passed
No known issues
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 an excellent skill description that covers all key dimensions well. It provides specific concrete actions, comprehensive natural trigger terms, explicit use/don't-use guidance, and clear boundaries that distinguish it from related skills. The inclusion of a DO NOT USE FOR section is particularly effective for reducing false positive skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: discovers available capacity, analyzes quota limits, compares availability, recommends optimal deployment locations. Also specifies scope boundaries (what NOT to use it for). | 3 / 3 |
Completeness | Clearly answers both 'what' (discovers capacity, analyzes quotas, compares availability, recommends deployment locations) and 'when' (explicit USE FOR and DO NOT USE FOR clauses with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'find capacity', 'check quota', 'where can I deploy', 'best region for capacity', 'TPM availability', 'model availability', 'region comparison'. These are highly natural phrases a user would actually type. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (Azure OpenAI capacity discovery). The DO NOT USE FOR section explicitly delineates boundaries against related skills like deployment or quota increase requests, minimizing conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured capacity discovery skill with strong actionability and workflow clarity. The phased approach with explicit validation checkpoints (especially Phase 3.5 for quota validation) and clear hand-off points demonstrates thoughtful design. Minor conciseness improvements could be made by trimming the Quick Reference table and the 'When to Use' section, which partially duplicate information available in the frontmatter or are self-evident from context.
Suggestions
Remove or significantly trim the 'When to Use This Skill' section and Quick Reference table — these duplicate frontmatter metadata and add ~20 lines of low-value content.
Consider moving the Phase 3.5 inline quota validation code into a script (e.g., `scripts/validate_quota.ps1/.sh`) to match the pattern established by the other phases and reduce body length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary elements like the 'When to Use This Skill' section (which duplicates frontmatter intent) and the Quick Reference table that restates obvious information. The Phase 3.5 quota validation section is quite verbose with inline code that could be in a script. However, it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | Provides concrete, executable commands for every phase — specific az CLI commands, PowerShell and bash script invocations with clear parameter patterns, and jq-based JSON processing. The quota validation code is executable and the output table format is explicit. The hand-off options are clearly enumerated with specific routing targets. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced across 5 phases with explicit validation checkpoints (Phase 1 validates prerequisites, Phase 3.5 validates subscription quota after discovery). There's a clear feedback loop — if no quota is available, it hands off to the quota skill. The error handling table provides specific resolution steps for each failure mode. | 3 / 3 |
Progressive Disclosure | Content is well-structured with a clear overview, script reference table, phased workflow, and error handling. References to related skills (preset, customize, quota, parent router) are one level deep and clearly signaled with relative paths. Complex API logic is appropriately delegated to scripts rather than inlined. | 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.
- Repository
- microsoft/github-copilot-for-azure
- Commit
771a666
- 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.