Enable evals on 20 more agentic workflows

.github/workflows/daily-awf-spec-compiler-surfacing.md

@@ -40,6 +40,11 @@ imports:
   - shared/otlp.md
 features:
   gh-aw-detection: true
+evals:
+  - id: spec_updates_reviewed
+    question: Did the agent review AWF specification and compiler updates for features that should be surfaced in gh-aw?
+  - id: finding_reported_or_noop
+    question: Did the agent create an issue for an actionable surfacing gap, or report that no issue was needed?
 ---
 
 {{#runtime-import? .github/shared-instructions.md}}

.github/workflows/daily-github-docs-seo-optimizer.md

@@ -35,6 +35,11 @@ safe-outputs:
     max: 1
 features:
   gh-aw-detection: false
+evals:
+  - id: seo_opportunities_analyzed
+    question: Did the agent analyze GitHub Docs for opportunities to improve Agentic Workflows recommendations in Copilot CLI?
+  - id: recommendation_reported
+    question: Did the agent report an actionable documentation recommendation or explain why no update was needed?
 ---
 
 # Daily GitHub Docs SEO Optimizer

.github/workflows/daily-go-test-parallelizer.md

@@ -38,6 +38,11 @@ safe-outputs:
     max-patch-files: 1
     max-patch-size: 2048
   noop:
+evals:
+  - id: tests_analyzed
+    question: Did the agent analyze Go tests to identify a safe candidate for t.Parallel?
+  - id: pr_created_or_noop
+    question: Did the agent create a pull request for a safe test change, or use noop when no safe change was available?
 ---
 
 # Daily Go Test Parallelizer

.github/workflows/daily-multi-device-docs-tester.md

@@ -130,6 +130,11 @@ pre-agent-steps:
       npm run build
 features:
   gh-aw-detection: true
+evals:
+  - id: device_tests_completed
+    question: Did the agent test the documentation site across the requested device form factors?
+  - id: results_reported
+    question: Did the agent report the multi-device test results and any responsive design or functionality findings?
 ---
 
 {{#runtime-import? .github/shared-instructions.md}}

.github/workflows/daily-safeoutputs-git-simulator.md

@@ -63,6 +63,11 @@ models:
   default-ai-credits-pricing:
     input: 5.0
     output: 25.0
+evals:
+  - id: git_scenarios_simulated
+    question: Did the agent simulate git configurations for create-pull-request and push-to-pull-request-branch safe outputs?
+  - id: simulator_findings_reported
+    question: Did the agent report the simulator results and any systematic safe-output issues it found?
 ---
 
 # Daily Safe Outputs Git Simulator

.github/workflows/daily-spdd-spec-planner.md

@@ -76,6 +76,11 @@ safe-outputs:
   max-bot-mentions: 1
 
 timeout-minutes: 20
+evals:
+  - id: specifications_analyzed
+    question: Did the agent analyze repository specifications using the SPDD planning process?
+  - id: prioritized_plan_reported
+    question: Did the agent report a prioritized plan with actionable specification work items?
 ---
 
 {{#runtime-import? .github/shared-instructions.md}}

.github/workflows/daily-spending-forecast.md

@@ -99,6 +99,11 @@ timeout-minutes: 45
 sandbox:
   agent:
     sudo: false
+evals:
+  - id: spending_forecast_analyzed
+    question: Did the agent analyze the agentic workflow spending forecast and its data quality?
+  - id: forecast_report_created
+    question: Did the agent create a report with spending projections and supporting evidence?
 ---
 
 # Daily Spending Forecast

.github/workflows/daily-squid-image-scan.md

@@ -61,6 +61,11 @@ sandbox:
   agent:
     sudo: false
 timeout-minutes: 90
+evals:
+  - id: container_images_scanned
+    question: Did the agent analyze container images for vulnerabilities, updates, and rejected licenses?
+  - id: findings_reported_or_noop
+    question: Did the agent report actionable image findings, or use noop when no findings required action?
 ---
 
 # Daily Container Image Security Scan

.github/workflows/daily-token-consumption-report.md

@@ -39,6 +39,11 @@ imports:
   - shared/otlp.md
 features:
   gh-aw-detection: true
+evals:
+  - id: token_consumption_analyzed
+    question: Did the agent analyze AI Credit consumption across agentic workflows using available telemetry?
+  - id: consumption_report_created
+    question: Did the agent create a report with token consumption trends and actionable observations?
 ---
 
 {{#runtime-import? .github/shared-instructions.md}}

.github/workflows/daily-windows-terminal-integration-builder.md

@@ -27,6 +27,11 @@ safe-outputs:
     title-prefix: "[windows-integration] "
     labels: [workflow, windows]
   noop:
+evals:
+  - id: windows_integration_checked
+    question: Did the agent assess the Windows CLI integration build and test workflow?
+  - id: failure_reported_or_noop
+    question: Did the agent create an issue for an actionable integration failure, or use noop when no action was required?
 ---
 
 ### Daily Windows Terminal Integration Builder

.github/workflows/daily-workflow-updater.md

@@ -51,6 +51,11 @@ timeout-minutes: 15
 
 imports:
   - shared/otlp.md
+evals:
+  - id: action_versions_checked
+    question: Did the agent check GitHub Actions versions for available updates?
+  - id: update_pr_created_or_noop
+    question: Did the agent create a pull request for required updates, or report that no changes were needed?
 ---
 
 {{#runtime-import? .github/shared-instructions.md}}

.github/workflows/dependabot-burner.md

@@ -282,6 +282,11 @@ steps:
         fs.mkdirSync(path.dirname(outPath), { recursive: true });
         fs.writeFileSync(outPath, JSON.stringify(payload, null, 2) + '\n', 'utf8');
         console.log(JSON.stringify(payload, null, 2));
+evals:
+  - id: dependabot_batch_analyzed
+    question: Did the agent analyze the selected grouped Dependabot remediation batch?
+  - id: remediation_reported
+    question: Did the agent create a remediation pull request or clearly report why no remediation was needed?
 ---
 
 # Dependabot Burner

.github/workflows/detection-analysis-report.md

@@ -35,6 +35,11 @@ features:
 sandbox:
   agent:
     sudo: false
+evals:
+  - id: detection_runs_analyzed
+    question: Did the agent analyze detection jobs for workflow misconfiguration and performance differences?
+  - id: detection_report_created
+    question: Did the agent create a report with evidence-backed detection findings or recommendations?
 ---
 
 # Detection Analysis Report