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.

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."

Tier 2: Medium-Confidence Markers (Score: 2 each)

Common but context-dependent:

Tier 3: Phrase Patterns (Score: 2-4 each)

Step 3: Structural Pattern Detection

Load: @modules/structural-patterns.md

Em Dash Overuse

Count em dashes (—) per 1000 words:

• 0-2: Normal human range
• 3-5: Elevated, review usage
• 6+: Strong AI signal

# Count em dashes in file
grep -o '—' file.md | wc -l

Tricolon Detection

AI loves groups of three with alliteration:

• "fast, efficient, and reliable"
• "clear, concise, and compelling"
• "robust, reliable, and resilient"

Pattern: adjective, adjective, and adjective with similar sounds.

List-to-Prose Ratio

Count bullet points vs paragraph sentences:

• >60% bullets: AI tendency
• Emoji-led bullets: Strong AI signal in technical docs

Sentence Length Uniformity

Measure standard deviation of sentence lengths:

• Low variance (SD < 5 words): AI monotony
• High variance (SD > 10 words): Human variation

Paragraph Symmetry

AI produces "blocky" text with uniform paragraph lengths. Check if paragraphs cluster around the same word count.

Step 4: Sycophantic Pattern Detection

Especially relevant for conversational or instructional content:

These phrases add no information and signal generated content.

Step 5: Calculate Slop Density Score

slop_score = (tier1_count * 3 + tier2_count * 2 + phrase_count * avg_phrase_score) / word_count * 100

Step 6: Generate Report

Output format:

## Slop Detection Report: [filename]

**Overall Score**: X.X / 10 (Rating)
**Word Count**: N words
**Markers Found**: N total

### High-Confidence Markers
- Line 23: "delve into" -> consider: "explore"
- Line 45: "rich tapestry" -> consider: "variety"

### Structural Issues
- Em dash density: 8/1000 words (HIGH)
- Bullet ratio: 72% (ELEVATED)
- Sentence length SD: 3.2 words (LOW VARIANCE)

### Phrase Patterns
- Line 12: "In today's fast-paced world" (vapid opener)
- Line 89: "cannot be overstated" (empty emphasis)

### Recommendations
1. Replace [specific word] with [alternative]
2. Convert bullet list at line 34-56 to prose
3. Vary sentence structure in paragraphs 3-5

Module Reference

• See modules/fiction-patterns.md for narrative-specific slop markers
• See modules/remediation-strategies.md for fix recommendations

Integration with Remediation

After detection, invoke Skill(scribe:doc-generator) with --remediate flag to apply fixes, or manually edit using the report as a guide.

Exit Criteria

• All target files scanned
• Density scores calculated
• Report generated with actionable recommendations
• High-severity items flagged for immediate attention