docs: clarify bundled skill default behavior

README.md

@@ -82,7 +82,7 @@ After installation, the package registers one tool: `ask_user`.
 
 That is enough for the agent to gain this clarification capability. The extension already injects prompt guidance that encourages the agent to call `ask_user` when requirements are ambiguous or user preference matters, instead of guessing.
 
-This package also includes an optional skill profile at `skills/ask-user/SKILL.md` (`ask-user-decision-gate`) for stricter decision-gate behavior in high-stakes or ambiguous boundaries.
+This package also includes an auto-bundled skill profile at `skills/ask-user/SKILL.md` (`ask-user-decision-gate`) for stricter decision-gate behavior in high-stakes or ambiguous boundaries. It is enabled by default when the package is installed, but can be disabled via `pi config`.
 
 You can still add your own agent instruction if you want to further reinforce when and how the tool should be used.
 

docs/README.md

@@ -6,7 +6,7 @@ This folder keeps only the documentation needed to understand and maintain the e
 
 - `contract.md` — external behavior, result shape, and UX guarantees
 - `architecture.md` — module boundaries and invariants
-- `../skills/ask-user/SKILL.md` — optional agent-side decision-gate guidance
+- `../skills/ask-user/SKILL.md` — auto-bundled agent-side decision-gate guidance; enabled by default, but can be disabled via `pi config`
 
 ## Reading order
 

docs/contract.md

@@ -234,7 +234,7 @@ The fallback message includes normalized pending questions and options so the ca
 
 ## Skill alignment (advisory)
 
-The optional skill profile at `skills/ask-user/SKILL.md` defines agent-side decision-gate guidance for when to call `ask_user`.
+The auto-bundled skill profile at `skills/ask-user/SKILL.md` defines agent-side decision-gate guidance for when to call `ask_user`. It is enabled by default when the package is installed, but can be disabled via `pi config`.
 
 It is advisory only. If there is any conflict, contract + tests win.