AI Slop Detection Skill

Identify linguistic markers that reveal AI-generated content and provide remediation guidance.

Detection Philosophy

AI slop is not about individual words but patterns of usage. A single "delve" is fine; five instances with "tapestry," "embark," and "vibrant" signals generation. Detection focuses on:

1. Density: How many markers appear per 100 words
2. Clustering: Multiple markers in close proximity
3. Context: Whether usage fits the document type

Required TodoWrite Items

1. slop-detector:scan-initiated - Target files identified
2. slop-detector:vocabulary-checked - Word/phrase patterns scanned
3. slop-detector:structure-checked - Structural patterns analyzed
4. slop-detector:density-calculated - Slop density score computed
5. slop-detector:report-generated - Findings documented

Step 1: Scan Initialization

Identify target files and document types:

# Find markdown and text files
find . -name "*.md" -o -name "*.txt" -o -name "*.rst" | head -50

# Prioritize user-facing documentation
ls docs/ README.md CHANGELOG.md 2>/dev/null

Classify each file: - Technical docs: READMEs, API docs, guides - Narrative prose: Blog posts, tutorials, explanations - Fiction: Creative writing, stories - Comments/docstrings: Code documentation

Step 2: Vocabulary Pattern Detection

Load: @modules/vocabulary-patterns.md

Tier 1: High-Confidence Markers (Score: 3 each)

These words appear 10-100x more frequently in AI text than human text:

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

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