fix(evals): --case list mode and name precheck; case-shard qa-callers; refresh batching and design-with-ui seeds

scripts/paid-test-durations.json

@@ -32,7 +32,7 @@
       "test/skill-e2e-plan-ceo-finding-floor.test.ts": 297738,
       "test/skill-e2e-plan-ceo-plan-mode.test.ts": 36812,
       "test/skill-e2e-plan-decision-classification.test.ts": 1000,
-      "test/skill-e2e-plan-design-with-ui.test.ts": 595151,
+      "test/skill-e2e-plan-design-with-ui.test.ts": 240000,
       "test/skill-e2e-plan-devex-finding-floor.test.ts": 207635,
       "test/skill-e2e-plan-devex-peer-comparison-classification.test.ts": 1000,
       "test/skill-e2e-plan-devex-plan-mode.test.ts": 115679,
@@ -50,6 +50,11 @@
       "test/skill-e2e-plan.test.ts#plan-review-report": 76406,
       "test/skill-e2e-qa-bugs.test.ts": 1000,
       "test/skill-e2e-qa-callers.test.ts": 737164,
+      "test/skill-e2e-qa-callers.test.ts#review-exploratory-small-cli": 294865,
+      "test/skill-e2e-qa-callers.test.ts#ship-exploratory-late-input": 294865,
+      "test/skill-e2e-qa-callers.test.ts#ship-exploratory-plan-checks": 294865,
+      "test/skill-e2e-qa-callers.test.ts#ship-exploratory-small-cli": 294865,
+      "test/skill-e2e-qa-callers.test.ts#ship-exploratory-unavailable": 294865,
       "test/skill-e2e-qa-functional-fix.test.ts": 235133,
       "test/skill-e2e-qa-functional.test.ts": 356641,
       "test/skill-e2e-qa-workflow.test.ts": 427303,
@@ -162,7 +167,7 @@
       "test/skill-e2e-plan-design-plan-mode.test.ts": 106608,
       "test/skill-e2e-plan-devex-peer-comparison-classification.test.ts": 79786,
       "test/skill-e2e-plan-eng-finding-floor.test.ts": 388666,
-      "test/skill-e2e-plan-eng-multi-finding-batching.test.ts": 1318488,
+      "test/skill-e2e-plan-eng-multi-finding-batching.test.ts": 597500,
       "test/skill-e2e-plan-eng-plan-mode.test.ts": 229226,
       "test/skill-e2e-plan-format.test.ts": 219670,
       "test/skill-e2e-plan-prosons.test.ts": 163659,