From 820b0a1f77342d1d3c169d83f170c498dbd5441b Mon Sep 17 00:00:00 2001 From: Louis Rossmann Date: Sun, 24 May 2026 19:28:54 -0500 Subject: [PATCH] Generalize banned-words exclusion zones (drop wiki-specific markup refs) Co-Authored-By: Claude Opus 4.7 (1M context) --- .claude/skills/no-ai-slop/references/ai-writing-detection.md | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/.claude/skills/no-ai-slop/references/ai-writing-detection.md b/.claude/skills/no-ai-slop/references/ai-writing-detection.md index 875da70..29fb6d9 100644 --- a/.claude/skills/no-ai-slop/references/ai-writing-detection.md +++ b/.claude/skills/no-ai-slop/references/ai-writing-detection.md @@ -354,9 +354,8 @@ Different AI model families produce distinct stylistic fingerprints based on the ### Exclusion Zones Lexical scans must NOT flag text inside: - Direct quotes (`"..."`) from cited sources -- `` tag contents (citation text, template fields) -- `{{Cite web}}` `|title=` and `|author=` values -- Wikitext comments (``) +- Titles, names, and other verbatim values taken from a source +- Code, configuration, or markup that is being shown as an example ### Context-Aware Severity If a banned word appears immediately adjacent to specific named entities (proper nouns, statute numbers, dates, dollar amounts), it is more likely being used with technical meaning than as AI filler. Reduce flag severity.