| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 13 | | adverbTagCount | 1 | | adverbTags | | 0 | "Sanders shrugged already [already]" |
| | dialogueSentences | 24 | | tagDensity | 0.542 | | leniency | 1 | | rawRatio | 0.077 | | effectiveRatio | 0.077 | |
| 100.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 683 | | totalAiIsmAdverbs | 0 | | found | (empty) | | highlights | (empty) | |
| 100.00% | AI-ism character names | Target: 0 AI-default names (17 tracked, −20% each) | | codexExemptions | (empty) | | found | (empty) | |
| 100.00% | AI-ism location names | Target: 0 AI-default location names (33 tracked, −20% each) | | codexExemptions | (empty) | | found | (empty) | |
| 12.15% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 683 | | totalAiIsms | 12 | | found | | | highlights | | 0 | "mosaic" | | 1 | "flickered" | | 2 | "traced" | | 3 | "silence" | | 4 | "standard" | | 5 | "etched" | | 6 | "intricate" | | 7 | "familiar" | | 8 | "gloom" | | 9 | "potential" |
| |
| 100.00% | Cliché density | Target: ≤1 cliche(s) per 800-word window | | totalCliches | 0 | | maxInWindow | 0 | | found | (empty) | | highlights | (empty) | |
| 100.00% | Emotion telling (show vs. tell) | Target: ≤3% sentences with emotion telling | | emotionTells | 0 | | narrationSentences | 36 | | matches | (empty) | |
| 63.49% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 1 | | narrationSentences | 36 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 47 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | maxSentenceWordsSeen | 31 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 683 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 2 | | unquotedAttributions | 0 | | matches | (empty) | |
| 27.23% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 25 | | wordCount | 448 | | uniqueNames | 8 | | maxNameDensity | 2.46 | | worstName | "Quinn" | | maxWindowNameDensity | 3.5 | | worstWindowName | "Quinn" | | discoveredNames | | Harlow | 1 | | Quinn | 11 | | Underground | 1 | | Camden | 1 | | Sanders | 4 | | Kowalski | 1 | | Eva | 5 | | Morris | 1 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Sanders" | | 3 | "Kowalski" | | 4 | "Eva" | | 5 | "Morris" |
| | places | (empty) | | globalScore | 0.272 | | windowScore | 0.5 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 30 | | glossingSentenceCount | 0 | | matches | (empty) | |
| 53.59% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 1 | | per1kWords | 1.464 | | wordCount | 683 | | matches | | 0 | "not north, but directly at the wall behind them" |
| |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 47 | | matches | (empty) | |
| 72.47% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 22 | | mean | 31.05 | | std | 12.53 | | cv | 0.404 | | sampleLengths | | 0 | 46 | | 1 | 37 | | 2 | 48 | | 3 | 31 | | 4 | 38 | | 5 | 21 | | 6 | 34 | | 7 | 42 | | 8 | 17 | | 9 | 30 | | 10 | 9 | | 11 | 38 | | 12 | 23 | | 13 | 45 | | 14 | 21 | | 15 | 34 | | 16 | 14 | | 17 | 34 | | 18 | 2 | | 19 | 49 | | 20 | 39 | | 21 | 31 |
| |
| 85.77% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 2 | | totalSentences | 36 | | matches | | 0 | "been removed" | | 1 | "was pulled" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 81 | | matches | (empty) | |
| 21.28% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 2 | | semicolonCount | 0 | | flaggedSentences | 2 | | totalSentences | 47 | | ratio | 0.043 | | matches | | 0 | "The body had been removed hours ago, but the scene remained untouched - a mosaic of evidence markers dotting the grimy floor like fluorescent bread crumbs." | | 1 | "The platform lights flickered again, and in that moment of darkness, both women heard it - a sound like stone grinding against stone, coming from the wall where the compass pointed." |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 448 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 6 | | adverbRatio | 0.013392857142857142 | | lyAdverbCount | 4 | | lyAdverbRatio | 0.008928571428571428 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 47 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 47 | | mean | 14.53 | | std | 8.18 | | cv | 0.563 | | sampleLengths | | 0 | 20 | | 1 | 26 | | 2 | 15 | | 3 | 22 | | 4 | 15 | | 5 | 16 | | 6 | 17 | | 7 | 20 | | 8 | 11 | | 9 | 3 | | 10 | 24 | | 11 | 11 | | 12 | 21 | | 13 | 28 | | 14 | 6 | | 15 | 26 | | 16 | 16 | | 17 | 12 | | 18 | 5 | | 19 | 4 | | 20 | 26 | | 21 | 7 | | 22 | 2 | | 23 | 17 | | 24 | 14 | | 25 | 7 | | 26 | 16 | | 27 | 7 | | 28 | 10 | | 29 | 27 | | 30 | 8 | | 31 | 4 | | 32 | 17 | | 33 | 8 | | 34 | 26 | | 35 | 4 | | 36 | 10 | | 37 | 15 | | 38 | 19 | | 39 | 2 | | 40 | 5 | | 41 | 31 | | 42 | 13 | | 43 | 6 | | 44 | 17 | | 45 | 16 | | 46 | 31 |
| |
| 93.62% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 1 | | diversityRatio | 0.574468085106383 | | totalSentences | 47 | | uniqueOpeners | 27 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 36 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 10 | | totalSentences | 36 | | matches | | 0 | "Her worn leather watch ticked" | | 1 | "She stood with military precision," | | 2 | "She slipped on a latex" | | 3 | "Her curly red hair was" | | 4 | "She clutched her worn leather" | | 5 | "She approached, her eyes darting" | | 6 | "He retreated toward the escalators," | | 7 | "She traced the air above" | | 8 | "She glanced at Quinn's pocket," | | 9 | "It was the same feeling" |
| | ratio | 0.278 | |
| 0.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 35 | | totalSentences | 36 | | matches | | 0 | "Detective Harlow Quinn crouched beside" | | 1 | "The body had been removed" | | 2 | "The platform lights flickered, casting" | | 3 | "Quinn traced her finger along" | | 4 | "The pattern formed an incomplete" | | 5 | "Her worn leather watch ticked" | | 6 | "Detective Sanders shuffled closer, his" | | 7 | "Quinn's jaw tightened." | | 8 | "She stood with military precision," | | 9 | "Sanders shrugged, already reaching for" | | 10 | "Quinn pulled out her phone," | | 11 | "She slipped on a latex" | | 12 | "A patina of verdigris coated" | | 13 | "Sanders peered over her shoulder" | | 14 | "Quinn shook her head." | | 15 | "The compass needle whirred and" | | 16 | "A familiar voice cut through" | | 17 | "Eva Kowalski stood at the" | | 18 | "Her curly red hair was" | | 19 | "She clutched her worn leather" |
| | ratio | 0.972 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 36 | | matches | (empty) | | ratio | 0 | |
| 0.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 15 | | technicalSentenceCount | 3 | | matches | | 0 | "The pattern formed an incomplete circle, its lines jagged and deep, as if carved by lightning." | | 1 | "She slipped on a latex glove and retrieved what appeared to be an antique compass, its case etched with intricate patterns that matched the scorched tiles." | | 2 | "The pieces began shifting in her mind, forming a picture she wasn't sure she wanted to see." |
| |
| 0.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 13 | | uselessAdditionCount | 4 | | matches | | 0 | "Detective Sanders shuffled, his shoes scuffing against the platform edge" | | 1 | "She stood, her movements economical" | | 2 | "She approached, her eyes darting to the scorched markings" | | 3 | "Eva said, crouching to examine them" |
| |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 1 | | fancyCount | 0 | | fancyTags | (empty) | | dialogueSentences | 24 | | tagDensity | 0.042 | | leniency | 0.083 | | rawRatio | 0 | | effectiveRatio | 0 | |