diff --git a/apps/skills/plannotator-setup-goal/SKILL.md b/apps/skills/plannotator-setup-goal/SKILL.md
index 303c3b77..3e1d9aaf 100644
--- a/apps/skills/plannotator-setup-goal/SKILL.md
+++ b/apps/skills/plannotator-setup-goal/SKILL.md
@@ -23,6 +23,17 @@ Use `goals/<slug>/` for both working JSON files and final docs. The JSON files a
 
 **Browser session patience rule:** Plannotator goal setup is a user-driven browser session. After launching an interview or facts command, be absolutely patient and keep waiting on the user until they submit, dismiss, or explicitly ask you to stop. Do not close, kill, restart, refresh, or open a second copy just because the UI is idle or the user is taking time. Never close and reopen the session as a way to update state; if a rerun is needed after the prior session ends, update the working JSON file and launch a new command from that file.
 
+**Optional: grill first (deep, one-at-a-time interview).** Before building the compact interview bundle, *suggest* a grilling pass whenever the goal is vague or carries many interdependent decisions — and run one whenever the user asks for it ("grill me first"). This is opt-in: for a clear, well-scoped goal, skip it and go straight to the bundle, so grilling never fights the bundle's "fewer, higher-leverage questions" philosophy. When you grill, run the protocol below verbatim, then fold the resolved decisions forward into a higher-quality interview bundle (Phase 2) — or, if grilling fully resolves scope, straight into the fact sheet (Phase 3).
+
+<!-- Grilling protocol below adapted verbatim from the /grill-me skill by Matt Pocock (MIT-licensed):
+     https://github.com/mattpocock/skills/blob/main/skills/productivity/grill-me/SKILL.md -->
+
+> Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
+>
+> Ask the questions one at a time.
+>
+> If a question can be answered by exploring the codebase, explore the codebase instead.
+
 ### 2. Interview Bundle
 
 Build a compact bundle of questions that can derive every "fact" this goal should produce. Package the questions together so the user can answer them quickly in the Plannotator goal setup UI. For each question, include your recommended answer and use options when they make answering faster.
diff --git a/apps/skills/plannotator-setup-goal/SKILL.test.ts b/apps/skills/plannotator-setup-goal/SKILL.test.ts
index 595d241f..83c91459 100644
--- a/apps/skills/plannotator-setup-goal/SKILL.test.ts
+++ b/apps/skills/plannotator-setup-goal/SKILL.test.ts
@@ -5,7 +5,7 @@ import { join } from "node:path";
 const skill = readFileSync(join(import.meta.dir, "SKILL.md"), "utf-8");
 
 describe("plannotator-setup-goal skill", () => {
-  test("uses bundled goal setup UI instead of serial chat questions", () => {
+  test("uses bundled goal setup UI as the default interview path", () => {
     expect(skill).toContain("Build a compact bundle of questions");
     expect(skill).toContain("plannotator setup-goal interview");
     expect(skill).toContain("goals/<slug>/interview.json");
@@ -15,7 +15,18 @@ describe("plannotator-setup-goal skill", () => {
     expect(skill).toContain("be absolutely patient and keep waiting on the user");
     expect(skill).toContain("Do not close, kill, restart, refresh, or open a second copy");
     expect(skill).not.toContain("setup-goal interview -");
-    expect(skill).not.toContain("one at a time");
+  });
+
+  test("allows opt-in grill-first questions before the bundled interview", () => {
+    const grillStart = skill.indexOf("**Optional: grill first");
+    const bundleStart = skill.indexOf("### 2. Interview Bundle");
+    expect(grillStart).toBeGreaterThan(-1);
+    expect(bundleStart).toBeGreaterThan(grillStart);
+
+    const grillSection = skill.slice(grillStart, bundleStart);
+    expect(grillSection).toContain("This is opt-in");
+    expect(grillSection).toContain("Ask the questions one at a time.");
+    expect(grillSection).toContain("If a question can be answered by exploring the codebase");
   });
 
   test("facts phase captures automated verification selections", () => {