| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 8 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 24 | | tagDensity | 0.333 | | leniency | 0.667 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 85.82% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1410 | | totalAiIsmAdverbs | 4 | | found | | | highlights | | |
| 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) | |
| 78.72% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1410 | | totalAiIsms | 6 | | found | | | highlights | | 0 | "flickered" | | 1 | "footsteps" | | 2 | "echoed" | | 3 | "velvet" | | 4 | "pulse" |
| |
| 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 | 122 | | matches | (empty) | |
| 96.02% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 3 | | narrationSentences | 122 | | filterMatches | | | hedgeMatches | | 0 | "seemed to" | | 1 | "happened to" |
| |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 137 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | maxSentenceWordsSeen | 43 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1405 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 7 | | unquotedAttributions | 0 | | matches | (empty) | |
| 83.33% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 50 | | wordCount | 1058 | | uniqueNames | 22 | | maxNameDensity | 1.23 | | worstName | "Quinn" | | maxWindowNameDensity | 2.5 | | worstWindowName | "Herrera" | | discoveredNames | | Frith | 1 | | Street | 2 | | Raven | 1 | | Nest | 1 | | Vauxhall | 1 | | Tomás | 1 | | Herrera | 12 | | Soho | 1 | | West | 1 | | End | 1 | | Wardour | 1 | | Victorian | 2 | | Morris | 3 | | Deptford | 1 | | London | 1 | | Zoo | 1 | | Veil | 1 | | Market | 1 | | Camden | 2 | | Quinn | 13 | | Saint | 1 | | Christopher | 1 |
| | persons | | 0 | "Raven" | | 1 | "Tomás" | | 2 | "Herrera" | | 3 | "Morris" | | 4 | "Quinn" | | 5 | "Saint" | | 6 | "Christopher" |
| | places | | 0 | "Frith" | | 1 | "Street" | | 2 | "Vauxhall" | | 3 | "Soho" | | 4 | "West" | | 5 | "End" | | 6 | "Wardour" | | 7 | "Victorian" | | 8 | "Deptford" | | 9 | "London" | | 10 | "Market" |
| | globalScore | 0.886 | | windowScore | 0.833 | |
| 20.13% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 77 | | glossingSentenceCount | 4 | | matches | | 0 | "as if signalling his departure" | | 1 | "symbols that seemed to shift when she looked at them directly" | | 2 | "looked like teeth on velvet cloth" | | 3 | "felt like a talisman from another world" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1405 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 1 | | totalSentences | 137 | | matches | | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 56 | | mean | 25.09 | | std | 18.92 | | cv | 0.754 | | sampleLengths | | 0 | 56 | | 1 | 42 | | 2 | 46 | | 3 | 26 | | 4 | 6 | | 5 | 39 | | 6 | 3 | | 7 | 6 | | 8 | 38 | | 9 | 33 | | 10 | 29 | | 11 | 1 | | 12 | 6 | | 13 | 29 | | 14 | 5 | | 15 | 36 | | 16 | 17 | | 17 | 4 | | 18 | 49 | | 19 | 14 | | 20 | 5 | | 21 | 45 | | 22 | 12 | | 23 | 10 | | 24 | 65 | | 25 | 45 | | 26 | 39 | | 27 | 46 | | 28 | 26 | | 29 | 2 | | 30 | 35 | | 31 | 6 | | 32 | 4 | | 33 | 50 | | 34 | 2 | | 35 | 42 | | 36 | 9 | | 37 | 51 | | 38 | 13 | | 39 | 34 | | 40 | 4 | | 41 | 76 | | 42 | 16 | | 43 | 26 | | 44 | 6 | | 45 | 43 | | 46 | 22 | | 47 | 30 | | 48 | 6 | | 49 | 48 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 1 | | totalSentences | 122 | | matches | | |
| 95.29% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 3 | | totalVerbs | 191 | | matches | | 0 | "was heading" | | 1 | "were leaning" | | 2 | "was watching" |
| |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 137 | | ratio | 0 | | matches | (empty) | |
| 98.78% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1063 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 44 | | adverbRatio | 0.041392285983066796 | | lyAdverbCount | 14 | | lyAdverbRatio | 0.01317027281279398 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 137 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 137 | | mean | 10.26 | | std | 8.62 | | cv | 0.84 | | sampleLengths | | 0 | 18 | | 1 | 26 | | 2 | 12 | | 3 | 7 | | 4 | 10 | | 5 | 5 | | 6 | 20 | | 7 | 11 | | 8 | 16 | | 9 | 19 | | 10 | 3 | | 11 | 2 | | 12 | 18 | | 13 | 3 | | 14 | 6 | | 15 | 9 | | 16 | 12 | | 17 | 7 | | 18 | 6 | | 19 | 5 | | 20 | 3 | | 21 | 3 | | 22 | 3 | | 23 | 12 | | 24 | 10 | | 25 | 16 | | 26 | 4 | | 27 | 2 | | 28 | 17 | | 29 | 10 | | 30 | 9 | | 31 | 4 | | 32 | 16 | | 33 | 1 | | 34 | 4 | | 35 | 2 | | 36 | 5 | | 37 | 15 | | 38 | 3 | | 39 | 6 | | 40 | 5 | | 41 | 7 | | 42 | 15 | | 43 | 14 | | 44 | 5 | | 45 | 2 | | 46 | 7 | | 47 | 3 | | 48 | 4 | | 49 | 7 |
| |
| 66.18% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 6 | | diversityRatio | 0.4233576642335766 | | totalSentences | 137 | | uniqueOpeners | 58 | |
| 61.16% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 2 | | totalSentences | 109 | | matches | | 0 | "Too many to have come" | | 1 | "Just smooth skin where features" |
| | ratio | 0.018 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 18 | | totalSentences | 109 | | matches | | 0 | "She'd been watching the Raven's" | | 1 | "She rounded the corner at" | | 2 | "Her worn leather watch caught" | | 3 | "His olive skin caught the" | | 4 | "It was calculation." | | 5 | "He cut left into Wardour" | | 6 | "He didn't stop." | | 7 | "They never stopped." | | 8 | "His footsteps echoed ahead." | | 9 | "She swept the light across" | | 10 | "Her radio crackled with static." | | 11 | "She was alone." | | 12 | "He'd gone through a door" | | 13 | "She'd found pieces of him" | | 14 | "She pushed the door open." | | 15 | "Her torch flickered, died, came" | | 16 | "It felt like a talisman" | | 17 | "She thought about Morris." |
| | ratio | 0.165 | |
| 83.85% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 82 | | totalSentences | 109 | | matches | | 0 | "Quinn's boots hit the wet" | | 1 | "She'd been watching the Raven's" | | 2 | "The green neon sign had" | | 3 | "She rounded the corner at" | | 4 | "Herrera was fast, faster than" | | 5 | "A bus shelter's advertisement for" | | 6 | "Her worn leather watch caught" | | 7 | "Herrera glanced back." | | 8 | "His olive skin caught the" | | 9 | "It was calculation." | | 10 | "He cut left into Wardour" | | 11 | "Quinn followed, her salt-and-pepper hair" | | 12 | "Some runners panicked, made mistakes," | | 13 | "Others had a destination in" | | 14 | "Herrera was the second type." | | 15 | "He didn't stop." | | 16 | "They never stopped." | | 17 | "A delivery driver swore as" | | 18 | "Polystyrene containers scattered across the" | | 19 | "Quinn hurdled them, her sharp" |
| | ratio | 0.752 | |
| 91.74% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 2 | | totalSentences | 109 | | matches | | 0 | "To her right, an elderly" | | 1 | "If they were people." |
| | ratio | 0.018 | |
| 20.91% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 41 | | technicalSentenceCount | 7 | | matches | | 0 | "The green neon sign had flickered twice as if signalling his departure." | | 1 | "His olive skin caught the streetlight, and she saw something in his warm brown eyes that wasn't fear." | | 2 | "The smell changed as she went down, from rotting vegetables to incense and copper and something that reminded her of the reptile house at London Zoo." | | 3 | "The tile work said Camden, but the proportions were wrong, stretched and warped as if the station had grown organically rather than being built." | | 4 | "Others wore their wrongness openly, too-long limbs, eyes that reflected light like animals, skin that rippled." | | 5 | "Six months of building a case, tracking his movements, documenting the patients who visited his unlisted clinic at odd hours." | | 6 | "About the three years she'd spent trying to understand what had happened to him, hitting dead ends and sealed files and colleagues who wouldn't meet her eyes." |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 8 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 66.67% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 4 | | fancyCount | 2 | | fancyTags | | 0 | "the vendor continued (continue)" | | 1 | "The vendor pressed (press)" |
| | dialogueSentences | 24 | | tagDensity | 0.167 | | leniency | 0.333 | | rawRatio | 0.5 | | effectiveRatio | 0.167 | |