justin/no_ai_slop_writing_rules
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Generalize banned-words exclusion zones (drop wiki-specific markup refs)

Browse Source 
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Louis Rossmann
2026-05-24 19:28:54 -05:00
parent ce03e044f3
commit 820b0a1f77
1 changed files with 2 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.claude/skills/no-ai-slop/references/ai-writing-detection.md
+2 -3
View File
@@ -354,9 +354,8 @@ Different AI model families produce distinct stylistic fingerprints based on the
### Exclusion Zones ### Exclusion Zones
Lexical scans must NOT flag text inside: Lexical scans must NOT flag text inside:
- Direct quotes (`"..."`) from cited sources - Direct quotes (`"..."`) from cited sources
- `<ref>` tag contents (citation text, template fields) - Titles, names, and other verbatim values taken from a source
- `{{Cite web}}` `|title=` and `|author=` values - Code, configuration, or markup that is being shown as an example
- Wikitext comments (`<!-- -->`)
### Context-Aware Severity ### 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. 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.