fix(review): gate routing on explicit review requests (#2716)

* fix(review): gate routing on explicit review requests

bmad-review's description matched any review-like phrasing, so coding
agents entered the review workflow for requests that never asked for
one — install commands, git operations, summary requests, build
handovers, and questions, including a question about the review skill
itself. A week of Codex session logs showed every invocation but one
was unintentional.

Rewrite the description around an explicit ask:

- Trigger only when the user asks to review a diff, a pull request,
  or an artifact — code or documents — and actually says "review".
- Acting on feedback from an earlier review is a change, not a review.
- Never volunteer, including on the agent's own just-made edits.

Validated with a 32-case routing eval, each case judged in an
isolated context, on two agent platforms; ten cases come from the
real over-trigger transcripts. The final wording scores 30/30 on
both platforms; an earlier draft's 29/30 drove the artifact clause
to name code explicitly.

* fix(review): count forwarded skill directives as review asks

Review-bot finding, confirmed by an isolated routing probe: with the
gate reading "when, and only when, the user asks", a literal reader
refuses the documented skill:bmad-review directive form that bmad-prd
and bmad-retrospective use to forward reviews.

Equate the directive with the ask instead of adding a second gate:
an explicit skill:bmad-review directive from another skill counts as
that ask.

The forwarded-directive scenario joins the routing eval as a scored
case; the full 33-case run scores 31/31 (two unscored probes), with
no previously excluded case loosened.

src/core-skills/bmad-review/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: bmad-review
-description: 'Review any diff, document, spec, or other artifact with one or more installed review methods (lenses) — shipped ones cover adversarial critique, edge cases, verification gaps, document structure, and prose. Runs whichever fit the content, or exactly the ones asked for. Use when the user says "review this", "critical review", "editorial review", "hunt edge cases", "review the structure", or "review the prose"'
+description: 'Runs one or more installed review lenses — adversarial critique, edge cases, verification gaps, structure, prose — and reports triaged findings. Use when, and only when, the user asks you to review a diff, a pull request, or an artifact — code or documents, one or many — and actually says "review"; an explicit skill:bmad-review directive from another skill counts as that ask. A request to act on feedback from an earlier review is a change, not a review. Never invoke this uninvited, including on edits you just made.'
 ---
 
 # BMad Review