Enhance microsoft-foundry quota skill with explicit calculation language

plugin/skills/microsoft-foundry/SKILL.md

@@ -4,7 +4,7 @@ description: "Deploy, evaluate, and manage Foundry agents end-to-end: Docker bui
 license: MIT
 metadata:
   author: Microsoft
-  version: "1.0.7"
+  version: "1.0.8"
 ---
 
 # Microsoft Foundry Skill

plugin/skills/microsoft-foundry/quota/quota.md

@@ -145,7 +145,7 @@ Quota freed **immediately**. Re-run Workflow #1 to verify.
 ```
 Production [workload type] using [model] in [region].
 Expected traffic: [X requests/day] with [Y tokens/request].
-Requires [Z TPM] capacity. Current [N TPM] insufficient.
+Calculated required TPM: [Z TPM]. Current [N TPM] insufficient.
 Request increase to [M TPM]. Deployment target: [date].
 ```
 

plugin/skills/microsoft-foundry/quota/references/capacity-planning.md

@@ -56,7 +56,7 @@ Scenario: 1M requests/day, average 1,000 tokens per request
 
 ## Production Workload Examples
 
-Real-world production scenarios with capacity calculations for gpt-4, version 0613 (from Azure Foundry Portal calculator):
+To estimate quota requirements, use real-world production scenarios with capacity calculations for gpt-4, version 0613 (from Azure Foundry Portal calculator):
 
 | Workload Type | Calls/Min | Prompt Tokens | Response Tokens | Cache Hit % | Total Tokens/Min | PTU Required | TPM Equivalent |
 |---------------|-----------|---------------|-----------------|-------------|------------------|--------------|----------------|
@@ -65,7 +65,9 @@ Real-world production scenarios with capacity calculations for gpt-4, version 06
 | **Summarization** | 10 | 5,000 | 300 | 20% | 53,000 | 100 | 53K TPM |
 | **Classification** | 10 | 3,800 | 10 | 20% | 38,100 | 100 | 38K TPM |
 
-**How to Calculate Your Needs:**
+**How to Estimate Your Production Quota Requirements:**
+
+To calculate your quota needs for production deployments, follow these steps:
 
 1. **Determine your peak calls per minute**: Monitor or estimate maximum concurrent requests
 2. **Measure token usage**: Average prompt size + response size
@@ -117,7 +119,9 @@ For the combined workload (40 calls/min, 135K tokens/min total), use **200 PTU**
 
 **Capacity Planning Approach** (from [PTU onboarding guide](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/provisioned-throughput-onboarding)):
 
-1. **Understand your TPM requirements**: Calculate expected tokens per minute based on workload
+To calculate and estimate your capacity requirements:
+
+1. **Calculate your TPM requirements**: Determine required tokens per minute based on your expected workload
 2. **Use the built-in capacity planner**: Available in Azure AI Foundry portal (Microsoft Foundry → Operate → Quota → Provisioned Throughput Unit tab)
 3. **Input your metrics**: Enter input TPM and output TPM based on your workload characteristics
 4. **Get PTU recommendation**: The calculator provides PTU allocation recommendation

tests/microsoft-foundry/quota/integration.test.ts

@@ -92,7 +92,8 @@ describeIntegration(`${SKILL_NAME}_quota - Integration Tests`, () => {
         prompt: "How much quota do I need for a production Foundry deployment?"
       });
 
-      const hasCapacityGuidance = doesAssistantMessageIncludeKeyword(
+      // Require at least one quota-specific term
+      const hasQuotaTerm = doesAssistantMessageIncludeKeyword(
         agentMetadata,
         "TPM"
       ) || doesAssistantMessageIncludeKeyword(
@@ -101,8 +102,27 @@ describeIntegration(`${SKILL_NAME}_quota - Integration Tests`, () => {
       ) || doesAssistantMessageIncludeKeyword(
         agentMetadata,
         "capacity"
+      ) || doesAssistantMessageIncludeKeyword(
+        agentMetadata,
+        "tokens per minute"
+      );
+
+      // Require at least one calculation verb
+      const hasCalculationVerb = doesAssistantMessageIncludeKeyword(
+        agentMetadata,
+        "calculate"
+      ) || doesAssistantMessageIncludeKeyword(
+        agentMetadata,
+        "estimate"
+      ) || doesAssistantMessageIncludeKeyword(
+        agentMetadata,
+        "calculation"
+      ) || doesAssistantMessageIncludeKeyword(
+        agentMetadata,
+        "quantify"
       );
-      expect(hasCapacityGuidance).toBe(true);
+
+      expect(hasQuotaTerm && hasCalculationVerb).toBe(true);
     }));
   });
 
@@ -253,14 +273,37 @@ describeIntegration(`${SKILL_NAME}_quota - Integration Tests`, () => {
       const isSkillUsed = isSkillInvoked(agentMetadata, SKILL_NAME);
       expect(isSkillUsed).toBe(true);
 
-      const hasPlanning = doesAssistantMessageIncludeKeyword(
+      // Require at least one quota-specific term
+      const hasQuotaTerm = doesAssistantMessageIncludeKeyword(
+        agentMetadata,
+        "TPM"
+      ) || doesAssistantMessageIncludeKeyword(
+        agentMetadata,
+        "PTU"
+      ) || doesAssistantMessageIncludeKeyword(
+        agentMetadata,
+        "capacity"
+      ) || doesAssistantMessageIncludeKeyword(
+        agentMetadata,
+        "tokens per minute"
+      );
+
+      // Require at least one calculation verb
+      const hasCalculationVerb = doesAssistantMessageIncludeKeyword(
         agentMetadata,
         "calculate"
       ) || doesAssistantMessageIncludeKeyword(
         agentMetadata,
-        "TPM"
+        "estimate"
+      ) || doesAssistantMessageIncludeKeyword(
+        agentMetadata,
+        "calculation"
+      ) || doesAssistantMessageIncludeKeyword(
+        agentMetadata,
+        "quantify"
       );
-      expect(hasPlanning).toBe(true);
+
+      expect(hasQuotaTerm && hasCalculationVerb).toBe(true);
     }));
 
     test("provides best practices", () => withTestResult(async () => {