docs(boss,specify): propagate the intent-in-English provenance rule to decision-log writers

21a745d rewrote issue rule 4's self-containment carve-out: a chat
decision's provenance is its intention rendered in English, a verbatim
quote only where the exact wording is load-bearing, and then translated.
The three sites that instruct writing such provenance still prescribed
the old verbatim-quote form:

- boss/SKILL.md — the decision-log comment rules, the common-mistakes
  row, and the red-flags entry now demand the intent statement instead
  of quoting the user's words.
- specify/SKILL.md — the fork-resolution comment templates' Basis lines
  carry the intent form.
- specify/agents/spec-skeptic.md — the grounding lens accepts a
  provenance record in the intent form, not only a verbatim statement.

specify/SKILL.md

@@ -162,8 +162,10 @@ A comment records one of two distinct things, and the distinction is
 load-bearing:
 
 - A **user decision** the conversation settled — minuted with
-  **provenance** (a verbatim user statement, or explicit attribution +
-  date). Legitimate: you are recording what the user chose.
+  **provenance** (the user's decision intent stated in English + explicit
+  attribution + date; a verbatim quote only where the exact wording is
+  load-bearing, and then translated — `../issue/SKILL.md` rule 4).
+  Legitimate: you are recording what the user chose.
 - A **derived orchestrator decision** — recorded with its **rationale**
   (why one option is groundably better). Legitimate under the new stance,
   but it must be labelled as what it is: a derived call, never disguised
@@ -183,8 +185,8 @@ skill's conventions). One comment, this shape:
 Spec: <spec-name>. The fork(s) below are still listed open on this
 issue; this records their resolution.
 - **Fork: <name>** → <decision>.
-  Basis: <verbatim user statement + attribution, OR "derived:" + the
-  groundable rationale>.
+  Basis: <user decision intent in English + attribution, OR "derived:" +
+  the groundable rationale>.
 ```
 
 `Basis:` carries either provenance (user decision) or rationale (derived
@@ -210,7 +212,7 @@ This issue seeds <one-line identity of the work>. The design was settled
 in an in-context discussion with no prior tracker issue; this records it.
 Load-bearing fork(s) resolved:
 - **Fork: <name>** → <decision>.
-  Basis: <verbatim user statement + attribution, OR "derived:" + rationale>.
+  Basis: <user decision intent in English + attribution, OR "derived:" + rationale>.
 ```
 
 The body names the *work*, not the spec file — the spec does not exist

specify/agents/spec-skeptic.md

@@ -94,8 +94,10 @@ In addition, every dispatch:
   the discussion, or, for a cycle that had *no* seeding issue, the
   *body* of the issue `specify` created to record it. Either counts as
   the sources resolving the fork **only if it carries provenance** — a
-  record of the user's decision (a verbatim statement, or explicit
-  attribution + date). A bare `decision: X` with no provenance is an
+  record of the user's decision (its intent stated in English + explicit
+  attribution + date; a verbatim quote only where the exact wording is
+  load-bearing, and then translated). A bare `decision: X` with no
+  provenance is an
   orchestrator self-assertion dressed as settled, not a source: it does
   **not** resolve the fork, and a load-bearing decision whose only
   support is such a record is a refutation. If the project declares no