fix(preamble): harden AskUserQuestion Format + Codex ELI10 carve-out

Follow-up to v1.6.2.0. Codex (GPT-5.4) under the gpt.md overlay
treated "No preamble / Prefer doing over listing" as license to skip
the Simplify paragraph and the RECOMMENDATION line on AskUserQuestion
calls. Users had to manually re-prompt "ELI10 and don't forget to
recommend" almost every time.

Two layers:

1. model-overlays/gpt.md — adds an explicit "AskUserQuestion is NOT
   preamble" carve-out. The "No preamble" rule applies to direct
   answers; AskUserQuestion content must emit the full format
   (Re-ground, Simplify/ELI10, Recommend, Options). Tells the model:
   if you find yourself about to skip any of these, back up and emit
   them — the user will ask anyway, so do it the first time.

2. scripts/resolvers/preamble/generate-ask-user-format.ts — step 2
   renamed to "Simplify (ELI10, ALWAYS)" with explicit "not optional
   verbosity, not preamble" framing. Step 3 "Recommend (ALWAYS)"
   hardened: "Never omit, never collapse into the options list."

All T2 skills regenerated across all hosts. Golden fixtures refreshed
(claude-ship, codex-ship, factory-ship). Updated the ELI10 assertion
in test/gen-skill-docs.test.ts to match the new wording.

Codex compliance to be verified empirically via test/codex-e2e-plan-format.test.ts.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

autoplan/SKILL.md

@@ -473,10 +473,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

canary/SKILL.md

@@ -465,10 +465,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

codex/SKILL.md

@@ -467,10 +467,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

context-restore/SKILL.md

@@ -469,10 +469,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

context-save/SKILL.md

@@ -469,10 +469,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

cso/SKILL.md

@@ -470,10 +470,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

design-consultation/SKILL.md

@@ -470,10 +470,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

design-html/SKILL.md

@@ -472,10 +472,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

design-review/SKILL.md

@@ -470,10 +470,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

design-shotgun/SKILL.md

@@ -467,10 +467,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

devex-review/SKILL.md

@@ -470,10 +470,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

document-release/SKILL.md

@@ -467,10 +467,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

health/SKILL.md

@@ -467,10 +467,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

investigate/SKILL.md

@@ -484,10 +484,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

land-and-deploy/SKILL.md

@@ -464,10 +464,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

learn/SKILL.md

@@ -467,10 +467,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

model-overlays/gpt.md

@@ -9,6 +9,24 @@ Y, or Z," try the best option yourself. Pick, execute, report results.
 **No preamble.** Skip "Great question!", "Let me help with that", and restating the
 user's request. Start with the work.
 
+**AskUserQuestion is NOT preamble.** The "No preamble" and "Prefer doing over listing"
+rules above do NOT apply to AskUserQuestion content. When you invoke AskUserQuestion,
+the user is about to make a decision — they need context, not terseness. Always emit
+the full format from the preamble's AskUserQuestion Format section:
+
+1. **Re-ground** (project + branch + task — 1-2 sentences).
+2. **Simplify (ELI10)** — explain what's happening in plain English a 16-year-old could
+   follow. Concrete stakes, not abstract tradeoffs. Non-negotiable; this is NOT preamble.
+3. **Recommend** — `RECOMMENDATION: Choose [X] because [one-line reason]` on its own
+   line. Never omit this line. Never collapse it into the options list.
+4. **Options** — lettered `A) B) C)` with Completeness scores (coverage-differentiated)
+   or the "options differ in kind" note (kind-differentiated).
+
+If you find yourself about to present an AskUserQuestion without the Simplify/ELI10
+paragraph, without a RECOMMENDATION line, or by just listing options and asking "which
+one?" — stop, back up, and emit the full format. The user will ask you to do it anyway,
+so do it the first time.
+
 **Reminder: subordination applies.** When a skill workflow says STOP, stop. When the
 skill asks via AskUserQuestion, that is the wait-for-user gate, not an ambiguity.
 Completion bias does not override safety gates.

office-hours/SKILL.md

@@ -475,10 +475,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

open-gstack-browser/SKILL.md

@@ -464,10 +464,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

pair-agent/SKILL.md

@@ -465,10 +465,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

plan-ceo-review/SKILL.md

@@ -471,10 +471,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

plan-design-review/SKILL.md

@@ -468,10 +468,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

plan-devex-review/SKILL.md

@@ -472,10 +472,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

plan-eng-review/SKILL.md

@@ -470,10 +470,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

plan-tune/SKILL.md

@@ -478,10 +478,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

qa-only/SKILL.md

@@ -466,10 +466,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

qa/SKILL.md

@@ -472,10 +472,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

retro/SKILL.md

@@ -465,10 +465,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

review/SKILL.md

@@ -469,10 +469,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

scripts/resolvers/preamble/generate-ask-user-format.ts

@@ -3,10 +3,11 @@ import type { TemplateContext } from '../types';
 export function generateAskUserFormat(_ctx: TemplateContext): string {
   return `## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the \`_BRANCH\` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with \`RECOMMENDATION: Choose [X] because [one-line reason]\`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with \`RECOMMENDATION: Choose [X] because [one-line reason]\` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with \`Completeness: N/10\` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip \`Completeness: N/10\` entirely and write one line: \`Note: options differ in kind, not coverage — no completeness score.\` Do not fabricate filler scores.
 5. **Options:** Lettered options: \`A) ... B) ... C) ...\` — when an option involves effort, show both scales: \`(human: ~X / CC: ~Y)\`
 

setup-deploy/SKILL.md

@@ -468,10 +468,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

ship/SKILL.md

@@ -470,10 +470,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

test/fixtures/golden/claude-ship-SKILL.md

@@ -470,10 +470,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

test/fixtures/golden/codex-ship-SKILL.md

@@ -459,10 +459,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

test/fixtures/golden/factory-ship-SKILL.md

@@ -461,10 +461,11 @@ available]. [Health score if available]." Keep it to 2-3 sentences.
 
 ## AskUserQuestion Format
 
-**ALWAYS follow this structure for every AskUserQuestion call:**
+**ALWAYS follow this structure for every AskUserQuestion call. All four elements are non-skippable. If you find yourself about to skip any of them, stop and back up.**
+
 1. **Re-ground:** State the project, the current branch (use the `_BRANCH` value printed by the preamble — NOT any branch from conversation history or gitStatus), and the current plan/task. (1-2 sentences)
-2. **Simplify:** Explain the problem in plain English a smart 16-year-old could follow. No raw function names, no internal jargon, no implementation details. Use concrete examples and analogies. Say what it DOES, not what it's called.
-3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]`. Never omit this line. It is required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
+2. **Simplify (ELI10, ALWAYS):** Explain what's happening in plain English a smart 16-year-old could follow. Concrete examples and analogies, not function names or internal jargon. Say what it DOES, not what it's called. State the stakes: what breaks if we pick wrong. This is NOT optional verbosity and it is NOT preamble — the user is about to make a decision and needs context. Even if you'd normally stay terse, emit the ELI10 paragraph. The user will ask for it anyway; do it the first time.
+3. **Recommend (ALWAYS):** Every question ends with `RECOMMENDATION: Choose [X] because [one-line reason]` on its own line. Never omit it. Never collapse it into the options list. Required for every AskUserQuestion, regardless of whether the options are coverage-differentiated or different-in-kind.
 4. **Score completeness (when meaningful):** When options differ in coverage (e.g. full test coverage vs happy path vs shortcut, complete error handling vs partial), score each with `Completeness: N/10` on its own line. Calibration: 10 = complete (all edge cases, full coverage), 7 = happy path only, 3 = shortcut. Flag any option ≤5 where a higher-completeness option exists. When options differ in kind (picking a review posture, picking an architectural approach, cherry-pick Add/Defer/Skip, choosing between two different kinds of systems), the completeness axis doesn't apply — skip `Completeness: N/10` entirely and write one line: `Note: options differ in kind, not coverage — no completeness score.` Do not fabricate filler scores.
 5. **Options:** Lettered options: `A) ... B) ... C) ...` — when an option involves effort, show both scales: `(human: ~X / CC: ~Y)`
 

test/gen-skill-docs.test.ts

@@ -244,8 +244,9 @@ describe('gen-skill-docs', () => {
   test('tier 2+ skills contain ELI16 simplification rules (AskUserQuestion format)', () => {
     // Root SKILL.md is tier 1 (no AskUserQuestion format). Check a tier 2+ skill instead.
     const content = fs.readFileSync(path.join(ROOT, 'cso', 'SKILL.md'), 'utf-8');
-    expect(content).toContain('No raw function names');
+    expect(content).toContain('Simplify (ELI10');
     expect(content).toContain('plain English');
+    expect(content).toContain('not function names');
   });
 
   test('tier 1 skills do NOT contain AskUserQuestion format', () => {