iter cadence.4-fix: address quality-review importants + German-loanword sweep (English-only in-tree)

docs/specs/2026-05-11-audit-fieldtest-docwriter-cadence.md

@@ -20,7 +20,7 @@ The trio mixes three different cadence-needs:
 - **drift** and **regression** are intrinsic to a milestone close —
   they compound silently across milestones if deferred, so they
   *must* run at every close.
-- **fieldtest** measures usability-belief — it's a Praxistest run when
+- **fieldtest** measures usability-belief — it's a field test run when
   the orchestrator believes the iteration is correct. Findings are
   either simple bugs or catastrophic architecture problems; both
   decay slowly, so the cadence doesn't have to be per-milestone.
@@ -36,7 +36,7 @@ mandatory pipeline step. This spec splits them.
 Three Boss-orchestrated buckets:
 
 1. **Per-milestone, mandatory (audit)**: architect + bencher only.
-2. **Boss-judgment, post-audit, "the iter is fertig"**: fieldtest.
+2. **Boss-judgment, post-audit, "the iter is complete"**: fieldtest.
 3. **Boss-judgment, post-fieldtest, "API surface has settled"**:
    docwriter.
 
@@ -75,7 +75,7 @@ stability windows differ (iter-stable vs. surface-stable).
 - `skills/fieldtest/SKILL.md`: trigger section reframes from "after
   audit closes cleanly" (which sounded automatic) to "Boss-dispatched
   after audit closes cleanly, when the orchestrator believes the
-  iteration is correct and wants a Praxistest". The pre-condition is
+  iteration is correct and wants a field test". The pre-condition is
   still a clean audit; the trigger is the Boss's judgment-call.
 - Add a one-line note on what kind of findings to expect: either
   simple bugs (→ debug → implement mini) or catastrophic