diff --git a/.changeset/fn-6891-ce-review-skill.md b/.changeset/fn-6891-ce-review-skill.md
new file mode 100644
index 0000000000..8a08e8eaf3
--- /dev/null
+++ b/.changeset/fn-6891-ce-review-skill.md
@@ -0,0 +1,5 @@
+---
+"@runfusion/fusion": patch
+---
+
+Update the built-in compound-engineering workflow so its Review stage runs the `compound-engineering:ce-code-review` skill directly. The redundant generic reviewer seam node was removed, leaving the CE code-review gate as the sole review stage.
diff --git a/packages/core/src/__tests__/builtin-workflows.test.ts b/packages/core/src/__tests__/builtin-workflows.test.ts
index 8ded12ff1d..8abb7684b3 100644
--- a/packages/core/src/__tests__/builtin-workflows.test.ts
+++ b/packages/core/src/__tests__/builtin-workflows.test.ts
@@ -354,13 +354,15 @@ describe("built-in workflows", () => {
     }
   });
 
-  it("compound-engineering compiles its skill nodes to steps", () => {
+  it("compound-engineering compiles exactly one ce-code-review step and no generic review seam", () => {
     const ce = getBuiltinWorkflow("builtin:compound-engineering")!;
     const steps = compileWorkflowToSteps(ce.ir);
-    // plan + execute (ce-work) + code-review (pre-merge) + document (post-merge)
-    // — review/merge seams are skipped.
-    expect(steps.length).toBeGreaterThanOrEqual(4);
+    // plan + execute (ce-work) + code-review (pre-merge) + commit-pr +
+    // resolve-feedback + document (post-merge) — merge seams are skipped.
+    expect(steps.length).toBeGreaterThanOrEqual(6);
     expect(steps.some((s) => s.name === "Plan")).toBe(true);
+    expect(steps.filter((s) => s.skillName === "compound-engineering:ce-code-review")).toHaveLength(1);
+    expect(steps.some((s) => s.name === "Review" && !s.skillName)).toBe(false);
   });
 
   it("compound-engineering runs ce-work for the execute step in coding mode", () => {
@@ -393,6 +395,44 @@ describe("built-in workflows", () => {
     expect(ids.indexOf("merge")).toBeLessThan(ids.indexOf("document"));
   });
 
+  it("compound-engineering review stage is ce-code-review, with graph ordering and layout intact", () => {
+    const ce = getBuiltinWorkflow("builtin:compound-engineering")!;
+    const byId = (id: string) => ce.ir.nodes.find((n) => n.id === id);
+    const authoredNodeIds = ce.ir.nodes.filter((node) => node.id !== "start" && node.id !== "end").map((node) => node.id);
+    expect(authoredNodeIds).toEqual([
+      "plan",
+      "execute",
+      "code-review",
+      "commit-pr",
+      "resolve-feedback",
+      "merge",
+      "document",
+    ]);
+    expect(ce.ir.nodes.some((node) => node.config?.seam === "review")).toBe(false);
+
+    const codeReview = byId("code-review");
+    expect(codeReview?.kind).toBe("gate");
+    expect(codeReview?.config?.skillName).toBe("compound-engineering:ce-code-review");
+    expect(codeReview?.config?.gateMode).toBe("gate");
+    expect(codeReview?.config?.toolMode).toBe("coding");
+
+    const layout = ce.layout ?? {};
+    expect(Object.keys(layout).sort()).toEqual(ce.ir.nodes.map((node) => node.id).sort());
+    for (let i = 1; i < ce.ir.nodes.length; i += 1) {
+      expect(layout[ce.ir.nodes[i].id].x - layout[ce.ir.nodes[i - 1].id].x).toBe(170);
+    }
+    expect(ce.ir.edges.some((edge) => edge.from === "execute" && edge.to === "code-review")).toBe(true);
+    expect(ce.ir.edges.some((edge) => edge.from === "code-review" && edge.to === "commit-pr")).toBe(true);
+  });
+
+  it("other built-in workflows retain their generic review nodes", () => {
+    const coding = getBuiltinWorkflow("builtin:coding")!;
+    const reviewHeavy = getBuiltinWorkflow("builtin:review-heavy")!;
+
+    expect(coding.ir.nodes.some((node) => node.id === "review" && node.config?.seam === "review")).toBe(true);
+    expect(reviewHeavy.ir.nodes.some((node) => node.id === "review" && node.config?.seam === "review")).toBe(true);
+  });
+
   it("compound-engineering runs plan/code-review/document in coding mode and carries skillName onto compiled steps (U1/U4)", () => {
     const ce = getBuiltinWorkflow("builtin:compound-engineering")!;
     const byId = (id: string) => ce.ir.nodes.find((n) => n.id === id);
@@ -407,8 +447,10 @@ describe("built-in workflows", () => {
     const plan = steps.find((s) => s.name === "Plan");
     expect(plan?.skillName).toBe("compound-engineering:ce-plan");
     expect(plan?.toolMode).toBe("coding");
-    const codeReview = steps.find((s) => s.skillName === "compound-engineering:ce-code-review");
-    expect(codeReview?.toolMode).toBe("coding");
+    const codeReviewSteps = steps.filter((s) => s.skillName === "compound-engineering:ce-code-review");
+    expect(codeReviewSteps).toHaveLength(1);
+    expect(codeReviewSteps[0].gateMode).toBe("gate");
+    expect(codeReviewSteps[0].toolMode).toBe("coding");
     const document = steps.find((s) => s.skillName === "compound-engineering:ce-compound");
     expect(document?.toolMode).toBe("coding");
   });
diff --git a/packages/core/src/builtin-workflows.ts b/packages/core/src/builtin-workflows.ts
index 936c33f403..b9382f4ee0 100644
--- a/packages/core/src/builtin-workflows.ts
+++ b/packages/core/src/builtin-workflows.ts
@@ -208,7 +208,6 @@ export const BUILTIN_WORKFLOWS: WorkflowDefinition[] = [
           prompt: "Execute the plan for this task, following existing patterns and maintaining quality throughout.",
         },
       },
-      { id: "review", kind: "prompt", config: builtinPromptConfig("review", "Review") },
       {
         id: "code-review",
         kind: "gate",
@@ -217,6 +216,10 @@ export const BUILTIN_WORKFLOWS: WorkflowDefinition[] = [
           executor: "skill",
           skillName: "compound-engineering:ce-code-review",
           gateMode: "gate",
+          /*
+           * FNXC:Workflows 2026-06-21-00:00:
+           * FN-6891 requires the compound-engineering Review stage to invoke compound-engineering:ce-code-review directly. The prior generic reviewer seam was removed so CE review runs through the CE skill and still blocks merge as a gate.
+           */
           // Coding mode so ce-code-review can fan out to its reviewer-persona
           // subagents via fn_spawn_agent. As a gate step it still emits the
           // verdict JSON (KTD-6); it is not meant to write the tree (Risk-1).