diff --git a/src/bmm-skills/4-implementation/bmad-quick-dev/spec-template.md b/src/bmm-skills/4-implementation/bmad-quick-dev/spec-template.md
index 8c2356b80..2a7e0e775 100644
--- a/src/bmm-skills/4-implementation/bmad-quick-dev/spec-template.md
+++ b/src/bmm-skills/4-implementation/bmad-quick-dev/spec-template.md
@@ -54,7 +54,8 @@ context: [] # optional: project-wide standards/docs the implementation agent sho
 
 <!-- Tasks: backtick-quoted file path -- action -- rationale. Prefer one task per file; group tightly-coupled changes when splitting would be artificial. -->
 <!-- If an I/O Matrix is present, include a task to unit-test its edge cases. -->
-<!-- AC covers system-level behaviors not captured by the I/O Matrix. Do not duplicate I/O scenarios here. -->
+<!-- AC covers system-level behaviors not captured by the I/O Matrix. Do not duplicate I/O scenarios here.
+     If requirements were assigned from a parent artifact, every assigned requirement must have an AC here. -->
 
 **Execution:**
 - [ ] `FILE` -- ACTION -- RATIONALE
diff --git a/src/bmm-skills/4-implementation/bmad-quick-dev/step-02-plan.md b/src/bmm-skills/4-implementation/bmad-quick-dev/step-02-plan.md
index 361d4c566..a55ae66e5 100644
--- a/src/bmm-skills/4-implementation/bmad-quick-dev/step-02-plan.md
+++ b/src/bmm-skills/4-implementation/bmad-quick-dev/step-02-plan.md
@@ -14,7 +14,7 @@ deferred_work_file: '{implementation_artifacts}/deferred-work.md'
 
 1. Investigate codebase. _Isolate deep exploration in sub-agents/tasks where available. To prevent context snowballing, instruct subagents to give you distilled summaries only._
 2. Read `./spec-template.md` fully. Fill it out based on the intent and investigation, and write the result to `{wipFile}`.
-3. Self-review against READY FOR DEVELOPMENT standard.
+3. Self-review against READY FOR DEVELOPMENT standard. If the intent derives from a parent artifact (epic plan, PRD, story brief), verify that every requirement assigned to this scope has a corresponding AC.
 4. If intent gaps exist, do not fantasize, do not leave open questions, HALT and ask the human.
 5. Token count check (see SCOPE STANDARD). If spec exceeds 1600 tokens:
    - Show user the token count.