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 thoroughly. It provides specific concrete actions, comprehensive natural trigger terms, explicit 'USE FOR' and 'DO NOT USE FOR' clauses, and a clearly defined niche within the Azure OpenAI ecosystem. The inclusion of negative boundaries is a notable strength that further reduces ambiguity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: discovers available capacity across regions/projects, analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. | 3 / 3 |
Completeness | Clearly answers both 'what' (discovers capacity, analyzes quotas, compares availability, recommends deployment locations) and 'when' (explicit USE FOR clause with trigger terms). Additionally includes a DO NOT USE FOR section which further clarifies boundaries. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'find capacity', 'check quota', 'where can I deploy', 'best region for capacity', 'multi-project capacity search', 'quota analysis', 'model availability', 'region comparison', 'check TPM availability'. These are highly natural phrases. | 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, quota increase requests, and listing existing deployments, 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-crafted skill with excellent workflow clarity and actionability — the phased approach with quota validation is particularly strong. The progressive disclosure is clean with appropriate cross-references to related skills. The main weakness is moderate verbosity: the Quick Reference table, use-case checklist, and some explanatory text could be trimmed without losing clarity.
Suggestions
Remove or condense the Quick Reference table and 'When to Use This Skill' section — these largely duplicate information Claude can infer from the skill description and workflow context.
Tighten Phase 3.5 by showing only one language variant (e.g., bash) with a note that PowerShell equivalents exist, rather than duplicating both inline.
| 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), the Quick Reference table that restates obvious information, and some verbose inline explanations. The Phase 3.5 section is quite lengthy with code that could be more tightly presented. | 2 / 3 |
Actionability | Provides fully executable commands at every step — specific script invocations with parameters, concrete Azure CLI commands, and inline code for quota validation with both PowerShell and bash variants. The example output table with specific values makes expected output crystal clear. | 3 / 3 |
Workflow Clarity | Excellent multi-phase workflow with clear sequencing (Phases 1-5), explicit validation checkpoints (Phase 3.5 validates subscription quota after discovery), feedback loops (re-run Phase 2 if checking another model), and a comprehensive error handling table with specific resolutions. The quota validation step catches a critical gap between platform capacity and user-level quota. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from quick reference to detailed workflow. External references are one level deep and clearly signaled (preset, customize, quota skills). Scripts abstract complexity appropriately, and the skill stays focused on discovery while pointing to related skills for deployment. | 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
a46a937
- 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.