slop-detector

# AI Slop Detection AI slop is identified by patterns of usage rather than individual words. While a single "delve" might be acceptable, its proximity to markers like "tapestry" or "embark" signals generated text. We analyze the density of these markers per 100 words, their clustering, and whether the overall tone fits the document type. ## Execution Workflow Start by identifying target files and classifying them as technical docs, narrative prose, or code comments. This allows for context-aware scoring during analysis. ### Language Detection - Auto-detect language from text content using function word frequency - Override with explicit `--lang` parameter (en, de, fr, es) - Load language-specific patterns from `data/languages/{lang}.yaml` - Fall back to English if detection confidence is low - See `modules/language-support.md` for details on cultural calibration ### Vocabulary and Phrase Detection Load: `@modules/vocabulary-patterns.md` We categorize markers into three tiers based on confidence. Tier 1 words appear dramatically more often in AI text and include "delve," "multifaceted," and "leverage." Tier 2 covers context-dependent transitions like "moreover" or "subsequently," while Tier 3 identifies vapid phrases such as "In today's fast-paced world" or "cannot be overstated." | Word | Context | Human Alternative | |------|---------|-------------------| | delve | "delve into" | explore, examine, look at | | tapestry | "rich tapestry" | mix, combination, variety | ...