| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 5 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 19 | | tagDensity | 0.263 | | leniency | 0.526 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 92.09% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1264 | | totalAiIsmAdverbs | 2 | | 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) | |
| 92.09% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1264 | | totalAiIsms | 2 | | found | | | highlights | | |
| 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 | 1 | | narrationSentences | 121 | | matches | | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 0 | | narrationSentences | 121 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 135 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 47 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1263 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 12 | | unquotedAttributions | 0 | | matches | (empty) | |
| 83.33% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 37 | | wordCount | 1068 | | uniqueNames | 19 | | maxNameDensity | 1.03 | | worstName | "Quinn" | | maxWindowNameDensity | 2.5 | | worstWindowName | "Quinn" | | discoveredNames | | Northern | 1 | | Line | 1 | | Camden | 2 | | Lock | 1 | | Tube | 2 | | Quinn | 11 | | Victorian | 1 | | Underground | 1 | | Raven | 1 | | Nest | 1 | | Veil | 1 | | Market | 1 | | Vice | 1 | | Herrera | 1 | | Saint | 1 | | Christopher | 1 | | Seville | 1 | | Tomás | 5 | | Morris | 3 |
| | persons | | 0 | "Line" | | 1 | "Quinn" | | 2 | "Underground" | | 3 | "Raven" | | 4 | "Market" | | 5 | "Herrera" | | 6 | "Saint" | | 7 | "Christopher" | | 8 | "Tomás" | | 9 | "Morris" |
| | places | | 0 | "Victorian" | | 1 | "Vice" | | 2 | "Seville" |
| | globalScore | 0.985 | | windowScore | 0.833 | |
| 48.65% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 74 | | glossingSentenceCount | 3 | | matches | | 0 | "looked like teeth in jars" | | 1 | "seemed surprised to see a copper" | | 2 | "looked like solid brick a moment before" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1263 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 135 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 60 | | mean | 21.05 | | std | 15.79 | | cv | 0.75 | | sampleLengths | | 0 | 13 | | 1 | 3 | | 2 | 56 | | 3 | 14 | | 4 | 21 | | 5 | 4 | | 6 | 33 | | 7 | 29 | | 8 | 9 | | 9 | 22 | | 10 | 3 | | 11 | 10 | | 12 | 25 | | 13 | 8 | | 14 | 50 | | 15 | 4 | | 16 | 26 | | 17 | 51 | | 18 | 34 | | 19 | 23 | | 20 | 17 | | 21 | 2 | | 22 | 57 | | 23 | 12 | | 24 | 1 | | 25 | 59 | | 26 | 17 | | 27 | 7 | | 28 | 21 | | 29 | 21 | | 30 | 27 | | 31 | 9 | | 32 | 26 | | 33 | 19 | | 34 | 36 | | 35 | 26 | | 36 | 4 | | 37 | 53 | | 38 | 31 | | 39 | 5 | | 40 | 29 | | 41 | 2 | | 42 | 15 | | 43 | 25 | | 44 | 27 | | 45 | 8 | | 46 | 18 | | 47 | 2 | | 48 | 22 | | 49 | 44 |
| |
| 99.46% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 2 | | totalSentences | 121 | | matches | | 0 | "been locked" | | 1 | "get laughed" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 2 | | totalVerbs | 188 | | matches | | 0 | "was falling" | | 1 | "was already moving" |
| |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 1 | | semicolonCount | 0 | | flaggedSentences | 1 | | totalSentences | 135 | | ratio | 0.007 | | matches | | 0 | "\"—Quinn? Quinn, do you copy? We lost you near Hawley—\"" |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 369 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 4 | | adverbRatio | 0.01084010840108401 | | lyAdverbCount | 0 | | lyAdverbRatio | 0 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 135 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 135 | | mean | 9.36 | | std | 7.5 | | cv | 0.802 | | sampleLengths | | 0 | 13 | | 1 | 3 | | 2 | 18 | | 3 | 6 | | 4 | 4 | | 5 | 28 | | 6 | 7 | | 7 | 7 | | 8 | 7 | | 9 | 14 | | 10 | 4 | | 11 | 3 | | 12 | 16 | | 13 | 1 | | 14 | 5 | | 15 | 6 | | 16 | 2 | | 17 | 29 | | 18 | 2 | | 19 | 7 | | 20 | 7 | | 21 | 9 | | 22 | 3 | | 23 | 2 | | 24 | 1 | | 25 | 3 | | 26 | 10 | | 27 | 4 | | 28 | 9 | | 29 | 5 | | 30 | 7 | | 31 | 8 | | 32 | 20 | | 33 | 6 | | 34 | 9 | | 35 | 15 | | 36 | 4 | | 37 | 4 | | 38 | 13 | | 39 | 9 | | 40 | 14 | | 41 | 17 | | 42 | 5 | | 43 | 9 | | 44 | 3 | | 45 | 3 | | 46 | 3 | | 47 | 15 | | 48 | 7 | | 49 | 4 |
| |
| 69.14% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 10 | | diversityRatio | 0.45925925925925926 | | totalSentences | 135 | | uniqueOpeners | 62 | |
| 60.06% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 2 | | totalSentences | 111 | | matches | | 0 | "Then the tunnel opened." | | 1 | "More than one set." |
| | ratio | 0.018 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 26 | | totalSentences | 111 | | matches | | 0 | "He vaulted the barrier and" | | 1 | "She ignored the burn." | | 2 | "It hadn't stopped pouring since" | | 3 | "He didn't stop." | | 4 | "He twisted, elbow catching her" | | 5 | "It blinded her for two" | | 6 | "Her radio crackled." | | 7 | "She thumbed it off." | | 8 | "She clicked her torch on" | | 9 | "Her boots splashed through an" | | 10 | "She had her baton, cuffs," | | 11 | "His olive skin shone with" | | 12 | "he said, low, in that" | | 13 | "He pulled her closer to" | | 14 | "His fingers were strong, paramedic" | | 15 | "He let go." | | 16 | "He'd said nothing at the" | | 17 | "She didn't look." | | 18 | "His anorak had fallen off" | | 19 | "He was thinner than she'd" |
| | ratio | 0.234 | |
| 59.10% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 89 | | totalSentences | 111 | | matches | | 0 | "He vaulted the barrier and" | | 1 | "Quinn was already over the" | | 2 | "The leather of her watch" | | 3 | "She ignored the burn." | | 4 | "The kid couldn't have been" | | 5 | "The rails stung her vision" | | 6 | "It hadn't stopped pouring since" | | 7 | "A low vibration hummed through" | | 8 | "Quinn grabbed the kid by" | | 9 | "He didn't stop." | | 10 | "He twisted, elbow catching her" | | 11 | "Bone dust, chalky and cold." | | 12 | "It blinded her for two" | | 13 | "The taste was copper and" | | 14 | "The door hung open on" | | 15 | "Her radio crackled." | | 16 | "\"—Quinn? Quinn, do you copy?" | | 17 | "She thumbed it off." | | 18 | "Dispatch would send uniform down" | | 19 | "That would take six minutes." |
| | ratio | 0.802 | |
| 90.09% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 2 | | totalSentences | 111 | | matches | | 0 | "Because now she saw it." | | 1 | "To the boy." |
| | ratio | 0.018 | |
| 81.63% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 35 | | technicalSentenceCount | 3 | | matches | | 0 | "The kid couldn't have been more than twenty, lanky in a soaked black anorak, but he ran like someone who knew the city was falling apart behind him." | | 1 | "Tomás Herrera stood behind a makeshift table covered in field dressings, bottled saline, and things that were not supposed to be in saline bottles." | | 2 | "Quinn stared at the kid's empty palm, at Morris's watch ticking against his skin, at the black water swirling around her boots in this impossible market that wa…" |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 5 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 4 | | fancyCount | 0 | | fancyTags | (empty) | | dialogueSentences | 19 | | tagDensity | 0.211 | | leniency | 0.421 | | rawRatio | 0 | | effectiveRatio | 0 | |