Technical explanations can be accurate while leaving readers to reconstruct outcomes or act on open-ended caveats. Document outcome-first prose, product boundaries, actionable variability, precise actors, meaningful qualifiers, and proportional caveats.
The PR-review bot's prompt instructed it to flag lines over 80 characters,
but no such rule exists in the repo (markdownlint MD013 is disabled and
STYLE.md never mentions it). Remove that instruction from pr-review.yml.
Also clarify the STYLE.md word list so "turn on/off" applies to UI toggles
while "enable/disable" stays acceptable in general prose, matching STYLE.md's
own example. This stops the bot from flagging every "enable" as a violation.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
