From 57cbc726f6a4db1cd3b7c429c447a51bb039aab4 Mon Sep 17 00:00:00 2001 From: Alexandre <44178713+alexbelgium@users.noreply.github.com> Date: Wed, 12 Aug 2026 22:42:36 +0200 Subject: [PATCH] docs(skill): terse chat replies in the add-on workflow (#2969) Adds a short answer-style rule to the hassio-addon-workflow skill: no pleasantries, no tool-call narration, no dumped logs, no re-printing what is already in context. Uncertainty markers, negations, numbers and verbatim technical text are explicitly exempt, so the Verified / Checked / Assumed discipline in step 9 is not compressed away. Persisted text (commits, CHANGELOG, PR bodies, review replies, the report) stays prose. Co-authored-by: Claude Opus 5 --- .claude/skills/hassio-addon-workflow/SKILL.md | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/.claude/skills/hassio-addon-workflow/SKILL.md b/.claude/skills/hassio-addon-workflow/SKILL.md index 9b288648cc..0dafe4630c 100644 --- a/.claude/skills/hassio-addon-workflow/SKILL.md +++ b/.claude/skills/hassio-addon-workflow/SKILL.md @@ -11,6 +11,16 @@ description: >- # Home Assistant add-on workflow +**Answer style.** Chat replies are terse: no pleasantries, no tool-call narration, no decorative +tables or emoji, no dumped logs — quote the shortest decisive line, and don't re-read or re-print +what is already in context. Fragments and dropped articles are fine. Never compressed: uncertainty +markers ("likely", "assumed", "not verified"), negations (`not`/`never`/`no`/`only`), numbers, +units, technical terms, code blocks, error strings — step 9's Verified/Checked/Assumed distinction +outranks brevity every time. Write in full prose, not fragments, for security warnings, +irreversible-action confirmations, and any multi-step sequence a fragment could make ambiguous. +Persisted text is prose too: commits, CHANGELOG entries, PR bodies, review-thread replies, the +step 10 report. + Triage first, then one of two paths: - **Light** — typo/doc fixes, CHANGELOG edits, version bumps, one-file edits at ladder levels