diff --git a/experiments/claude-code-sonnet-5-no-skills.ts b/experiments/claude-code-sonnet-5-no-skills.ts
index 5452fe38..5a266f92 100644
--- a/experiments/claude-code-sonnet-5-no-skills.ts
+++ b/experiments/claude-code-sonnet-5-no-skills.ts
@@ -8,7 +8,7 @@ import { localStackRuntime } from '@supabase-evals/sandbox';
 
 // Same as claude-code-sonnet-5 but with no skills, to measure skills' impact.
 export default defineExperiment({
-  suite: ['no-skills', 'regression'],
+  suite: ['no-skills'],
   agent: claudeCodeAgent({
     model: 'claude-sonnet-5',
     reasoningEffort: 'high',
@@ -18,6 +18,4 @@ export default defineExperiment({
   }),
   localStack: localStackRuntime(),
   skills: [],
-  // Evals that override `skills: []` already run under the baseline experiment. Skip them from running again here.
-  skipEval: (ev) => ev.metadata.skills?.length === 0,
 });
diff --git a/experiments/claude-code-sonnet-5.ts b/experiments/claude-code-sonnet-5.ts
index 1572000e..e2b01a50 100644
--- a/experiments/claude-code-sonnet-5.ts
+++ b/experiments/claude-code-sonnet-5.ts
@@ -7,7 +7,7 @@ import {
 import { localStackRuntime } from '@supabase-evals/sandbox';
 
 export default defineExperiment({
-  suite: ['benchmark', 'regression'],
+  suite: ['benchmark'],
   agent: claudeCodeAgent({
     model: 'claude-sonnet-5',
     reasoningEffort: 'high',
diff --git a/experiments/codex-gpt-5.6-luna-no-skills.ts b/experiments/codex-gpt-5.6-luna-no-skills.ts
index 40ccfbaf..34abfe99 100644
--- a/experiments/codex-gpt-5.6-luna-no-skills.ts
+++ b/experiments/codex-gpt-5.6-luna-no-skills.ts
@@ -7,7 +7,7 @@ import {
 import { localStackRuntime } from '@supabase-evals/sandbox';
 
 export default defineExperiment({
-  suite: ['no-skills'],
+  suite: ['no-skills', 'regression'],
   agent: codexAgent({
     model: 'gpt-5.6-luna',
     reasoningEffort: 'medium',
@@ -17,4 +17,6 @@ export default defineExperiment({
   }),
   localStack: localStackRuntime(),
   skills: [],
+  // Evals that override `skills: []` already run under the baseline experiment. Skip them from running again here.
+  skipEval: (ev) => ev.metadata.skills?.length === 0,
 });
diff --git a/experiments/codex-gpt-5.6-luna.ts b/experiments/codex-gpt-5.6-luna.ts
index 141b1459..d4e18052 100644
--- a/experiments/codex-gpt-5.6-luna.ts
+++ b/experiments/codex-gpt-5.6-luna.ts
@@ -7,7 +7,7 @@ import {
 import { localStackRuntime } from '@supabase-evals/sandbox';
 
 export default defineExperiment({
-  suite: ['benchmark'],
+  suite: ['benchmark', 'regression'],
   agent: codexAgent({
     model: 'gpt-5.6-luna',
     reasoningEffort: 'medium',