diff --git a/src/bmm-skills/4-implementation/bmad-quick-dev/render.py b/src/bmm-skills/4-implementation/bmad-quick-dev/render.py
index b5faed752..267ae8ef9 100644
--- a/src/bmm-skills/4-implementation/bmad-quick-dev/render.py
+++ b/src/bmm-skills/4-implementation/bmad-quick-dev/render.py
@@ -215,12 +215,59 @@ def _scalar_str(value):
     return str(value)
 
 
-def _render_workflow_value(value):
-    """Format a resolved [workflow] value for inline substitution. Lists render
-    as markdown bullets (empty -> '_None._'); scalars render verbatim. Each list
-    item uses the same scalar formatting so booleans stay consistent. Entries are
-    emitted as-is so runtime placeholders like {project-root} survive for the LLM
-    to resolve."""
+# [workflow] keys holding review layers ([[workflow.review_layers]] tables with
+# id/name/instruction/when fields). This renderer knows this skill's
+# customization schema outright — layer semantics are materialized here, not
+# interpreted by the LLM at run time.
+_REVIEW_LAYER_KEYS = ("review_layers", "oneshot_review_layers")
+
+
+def _render_review_layers(layers):
+    """Materialize review layers into direct invocation blocks. A layer with an
+    empty or missing instruction is disabled (that is how an override turns off
+    a default layer) and drops out entirely. A `when` condition is the one part
+    that stays with the LLM: it renders as a run-time guard line. No active
+    layers renders as the HALT instruction the workflow would otherwise have to
+    derive from an empty list."""
+    active = [
+        layer
+        for layer in layers
+        if isinstance(layer, dict) and _scalar_str(layer.get("instruction")).strip()
+    ]
+    if not active:
+        return (
+            "No review layers are active. HALT with status `blocked` and "
+            "blocking condition `no active review layers`."
+        )
+    blocks = []
+    for layer in active:
+        title = (
+            _scalar_str(layer.get("name")).strip()
+            or _scalar_str(layer.get("id")).strip()
+            or "Review layer"
+        )
+        lines = [f"#### {title}", ""]
+        when = _scalar_str(layer.get("when")).strip()
+        if when:
+            lines.append(
+                "Run this layer only if the following holds in the "
+                f"current context: `{when}`"
+            )
+            lines.append("")
+        lines.append(_scalar_str(layer.get("instruction")).strip("\n"))
+        blocks.append("\n".join(lines))
+    return "\n\n".join(blocks)
+
+
+def _render_workflow_value(key, value):
+    """Format a resolved [workflow] value for inline substitution. Review-layer
+    keys materialize as invocation blocks; other lists render as markdown
+    bullets (empty -> '_None._'); scalars render verbatim. Each list item uses
+    the same scalar formatting so booleans stay consistent. Entries are emitted
+    as-is so runtime placeholders like {project-root} or {diff_output} survive
+    for the LLM to resolve."""
+    if key in _REVIEW_LAYER_KEYS and isinstance(value, list):
+        return _render_review_layers(value)
     if isinstance(value, list):
         if not value:
             return "_None._"
@@ -235,7 +282,7 @@ def render_workflow(content, workflow):
     elsewhere are untouched."""
     return re.sub(
         r"\{workflow\.(\w+)\}",
-        lambda m: _render_workflow_value(workflow.get(m.group(1))),
+        lambda m: _render_workflow_value(m.group(1), workflow.get(m.group(1))),
         content,
     )
 
diff --git a/src/bmm-skills/4-implementation/bmad-quick-dev/step-04-review.md b/src/bmm-skills/4-implementation/bmad-quick-dev/step-04-review.md
index c49ae8c3c..3a735cd83 100644
--- a/src/bmm-skills/4-implementation/bmad-quick-dev/step-04-review.md
+++ b/src/bmm-skills/4-implementation/bmad-quick-dev/step-04-review.md
@@ -18,11 +18,9 @@ Do NOT `git add` anything — this is read-only inspection.
 
 ### Review
 
-The review layers are `{workflow.review_layers}`, resolved during activation.
+Execute these review layers in parallel wherever their execution methods allow: substitute the runtime placeholders (e.g. `{diff_output}`) into each layer's instruction, then follow it verbatim.
 
-Skip every layer whose `instruction` is empty or missing — that is how an override disables a default layer — and every layer whose `when` condition (if present) does not hold in the current context. If no layers remain, HALT with status `blocked` and blocking condition `no active review layers`.
-
-Execute all remaining layers in parallel wherever their execution methods allow: substitute the runtime placeholders (e.g. `{diff_output}`) into each layer's `instruction`, then follow it verbatim.
+{workflow.review_layers}
 
 If a layer's instruction requires subagents and none are available, generate one review prompt file per such layer in `{{.implementation_artifacts}}` and HALT. Ask the human to run each in a separate session (ideally a different LLM) and paste back the findings.
 
diff --git a/src/bmm-skills/4-implementation/bmad-quick-dev/step-oneshot.md b/src/bmm-skills/4-implementation/bmad-quick-dev/step-oneshot.md
index 21bbc1bdd..eb078796c 100644
--- a/src/bmm-skills/4-implementation/bmad-quick-dev/step-oneshot.md
+++ b/src/bmm-skills/4-implementation/bmad-quick-dev/step-oneshot.md
@@ -17,9 +17,9 @@ Implement the clarified intent directly.
 
 ### Review
 
-The review layers for this route are `{workflow.oneshot_review_layers}`, resolved during activation.
+Execute these review layers in parallel wherever their execution methods allow, following each layer's instruction verbatim after substituting any runtime placeholders:
 
-Skip every layer whose `instruction` is empty or missing, and every layer whose `when` condition (if present) does not hold. If no layers remain, HALT with status `blocked` and blocking condition `no active review layers`. Execute all remaining layers in parallel wherever their execution methods allow, following each layer's `instruction` verbatim after substituting any runtime placeholders.
+{workflow.oneshot_review_layers}
 
 If a layer's instruction requires subagents and none are available, generate one review prompt file per such layer in `{{.implementation_artifacts}}` and HALT. Ask the human to run each in a separate session and paste back the findings.
 
diff --git a/test/test-quick-dev-renderer.js b/test/test-quick-dev-renderer.js
index 22746fc70..89452ec90 100644
--- a/test/test-quick-dev-renderer.js
+++ b/test/test-quick-dev-renderer.js
@@ -9,7 +9,12 @@
  *   3. [workflow] customization is self-resolved and inlined: prepend bullet,
  *      persistent_facts append (base kept), empty list -> _None._, on_complete
  *      scalar baked into step-05/step-oneshot.
- *   4. No {workflow.*} placeholder or resolve_customization.py call survives
+ *   4. Review layers materialize as direct invocation blocks: default layers
+ *      become #### sections in step-04, an override replacing a layer by id
+ *      wins, an empty-instruction override drops its layer, a `when` renders
+ *      as a run-time guard, runtime placeholders like {diff_output} survive,
+ *      and disabling every layer renders the HALT instruction.
+ *   5. No {workflow.*} placeholder or resolve_customization.py call survives
  *      in any rendered file.
  *
  * Usage: node test/test-quick-dev-renderer.js
@@ -114,6 +119,16 @@ try {
       'activation_steps_prepend = ["TEST_PREPEND_STEP"]',
       'persistent_facts = ["TEST_EXTRA_FACT"]',
       'on_complete = "TEST_ON_COMPLETE_INSTRUCTION"',
+      '',
+      '[[workflow.review_layers]]',
+      'id = "edge-case-hunter"',
+      'name = "Replaced Layer"',
+      'when = "TEST_WHEN_CONDITION"',
+      'instruction = "TEST_REPLACED_LAYER_INSTRUCTION"',
+      '',
+      '[[workflow.review_layers]]',
+      'id = "verification-gap"',
+      'instruction = ""',
     ].join('\n'),
     'utf-8',
   );
@@ -195,6 +210,72 @@ try {
     }
   });
 
+  test('review layers materialize as invocation blocks in step-04', () => {
+    const content = readRendered('step-04-review.md');
+    assert(content.includes('#### Blind Hunter'), 'default review layer not rendered as a #### invocation block');
+    assert(!content.includes('- id:'), 'layer table data leaked into the rendered output');
+    assert(content.includes('{diff_output}'), 'runtime {diff_output} placeholder did not survive rendering');
+  });
+
+  test('review layer override replaces the matching default by id', () => {
+    const content = readRendered('step-04-review.md');
+    assert(content.includes('#### Replaced Layer'), 'override layer name not used as block title');
+    assert(content.includes('TEST_REPLACED_LAYER_INSTRUCTION'), 'override layer instruction not inlined');
+    assert(!content.includes('bmad-review-edge-case-hunter'), 'replaced default layer instruction still present');
+    assert(content.includes('bmad-review-adversarial-general'), 'untouched default layer dropped by keyed merge');
+  });
+
+  test('empty-instruction override drops its layer entirely', () => {
+    const content = readRendered('step-04-review.md');
+    assert(!content.includes('verification-gap'), 'disabled layer id still present in rendered output');
+    assert(!content.includes('Verification Gap Reviewer'), 'disabled layer name still present in rendered output');
+  });
+
+  test('when condition renders as a run-time guard line', () => {
+    const content = readRendered('step-04-review.md');
+    assert(
+      content.includes('Run this layer only if the following holds in the current context: `TEST_WHEN_CONDITION`'),
+      'when condition not rendered as a guard line',
+    );
+  });
+
+  test('disabling every layer renders the HALT instruction', () => {
+    // Second render pass: replace the override file so every default layer
+    // (and the oneshot route's only layer) is disabled, then re-render.
+    fs.writeFileSync(
+      path.join(tmpDir, '_bmad', 'custom', 'bmad-quick-dev.user.toml'),
+      [
+        '[workflow]',
+        '',
+        '[[workflow.review_layers]]',
+        'id = "blind-hunter"',
+        'instruction = ""',
+        '',
+        '[[workflow.review_layers]]',
+        'id = "edge-case-hunter"',
+        'instruction = ""',
+        '',
+        '[[workflow.review_layers]]',
+        'id = "verification-gap"',
+        'instruction = ""',
+        '',
+        '[[workflow.oneshot_review_layers]]',
+        'id = "blind-hunter"',
+        'instruction = ""',
+      ].join('\n'),
+      'utf-8',
+    );
+    const rerun = spawnSync('python3', [path.join(skillDst, 'render.py')], {
+      cwd: skillDst,
+      encoding: 'utf-8',
+    });
+    assert(rerun.status === 0, `re-render exit code ${rerun.status}\nstderr: ${rerun.stderr}`);
+    const halt = 'No review layers are active. HALT with status `blocked` and blocking condition `no active review layers`.';
+    for (const file of ['step-04-review.md', 'step-oneshot.md']) {
+      assert(readRendered(file).includes(halt), `HALT instruction missing from ${file}`);
+    }
+  });
+
   test('no {workflow.*} placeholder survives in any rendered file', () => {
     const leaks = renderedMdFiles().filter((f) => readRendered(f).includes('{workflow.'));
     assert(leaks.length === 0, `{workflow.*} leaked in: ${leaks.join(', ')}`);